JP7800260B2 - Information processing device and program - Google Patents

Description

The present invention relates to a technique for searching for outliers in graphs.

Conventionally, systems have been known that store the test results administered to students in a database and allow them to be viewed on a computer. Patent documents 1 and 2 disclose systems that calculate grade fluctuations based on the test in question and tests administered prior to that test, and highlight the grades of specific students.

Japanese Patent Application Laid-Open No. 2021-63900 Japanese Patent Application Laid-Open No. 2021-63901

Teachers and other learning support staff often centrally manage multiple data sets, including test results, and use graphs to grasp overall information for the entire class or grade. In such cases, learning support staff need to provide appropriate instruction by checking individual information for each student and grouping students with similar attributes.

The present invention has been made to solve the above-mentioned problems, and its main objective is to provide an information processing device that identifies students who fall into outliers in a graph created based on multiple pieces of learning-related data.

In one aspect of the present invention, an information processing device includes: a storage unit that stores identification information of multiple learners and performance information related to the learning of the learners in association with each other; a graph creation unit that creates a scatter plot as a graph, with different test items on the vertical and horizontal axes, and plotting each learner's icon based on the performance information corresponding to the test items ; a group classification unit that classifies the learners into groups in the graph; an outlier identification unit that identifies outliers from learners who do not belong to the groups in the graph; and an output unit that outputs the graph, the groups, and the outliers, where the test items are an index representing the test format and its results, or a questionnaire that evaluates the test and its results . According to this aspect, the information processing device can easily identify outliers in the graph on which each learner's icon is plotted. This reduces the burden of identifying outliers in the graph.

In one aspect of the information processing device, the performance information includes indices related to a plurality of test items , and the outlier identification unit identifies, in the graph, learners who do not belong to the group and whose indices included in the performance information are lower than a first threshold, as outliers. According to this aspect, the information processing device can identify, for example, only learners with poor performance as outliers based on the first threshold.

One aspect of the above information processing device includes a graph division unit that divides the graph into multiple regions of the same size; a learner proportion calculation unit that calculates a learner proportion, which is the proportion of the number of learners whose icons are plotted in each region; a detection unit that detects regions where the learner proportion is equal to or greater than a second threshold as detection regions; and an integration unit that integrates adjacent detection regions to form integrated regions, and the group classification unit classifies learners whose icons are plotted in the same integrated region into the same group. According to this aspect, the information processing device can classify learners into groups based on the learner proportion in each region into which the graph is divided. Therefore, learners who are grouped together on the graph can be classified into the same group.

In one aspect of the information processing device, if there is an area adjacent to the detection area where the learner proportion is less than the second threshold but not zero, the integration unit also integrates that area into an integrated area. According to this aspect, the information processing device can classify a learner whose icon is plotted in an area adjacent to the detection area into the same group as the learner whose icon is plotted in the detection area, even if the learner proportion does not meet the threshold. Therefore, learners whose icons are plotted close to each other on the graph can be classified into the same group.

In one aspect of the information processing device, the device includes a distance calculation unit that calculates the distance between the center of gravity of the integrated area and the icon of a learner that is not plotted on any integrated area, and the outlier identification unit identifies a learner whose icon is the distance equal to or greater than a third threshold as an outlier. According to this aspect, the information processing device can identify, from among learners who do not belong to any group, a learner who is farther away from any group by the third threshold or more as an outlier.

In one aspect of the information processing device, the group classification unit classifies learners whose icons are less than a threshold distance from the integrated area into the same group as learners whose icons are plotted in the integrated area. According to this aspect, the information processing device can classify learners who do not belong to any group into groups that are close in distance on the graph.

In one aspect of the information processing device, an input information acquisition unit acquires different test items as input information for the vertical and horizontal axes of the graph, and the graph creation unit creates the scatter diagram as a graph based on the input information and the performance information. According to this aspect, the information processing device creates a scatter graph with the test-related indicators and test evaluations included in the input information as the vertical and horizontal axes, respectively, and can visualize the performance information of each learner using the graph.

In one aspect of the information processing device, the output unit outputs, based on the grade information, either the test-related index or test evaluation for the vertical axis of the outlier learner. Also, either the test-related index or test evaluation for the horizontal axis of the outlier learner. According to this aspect, the information processing device can output the test-related index or test evaluation for the outlier learner, along with the graph, the group on the graph, and the outlier. Therefore, learning supporters and others can check information about the outlier learner along with the graph.

In another aspect of the present invention, a program executed by an information processing device including a computer causes the computer to function as: a memory unit that stores identification information of multiple learners in association with performance information related to the learning of the learners; a graph creation unit that creates a scatter plot as a graph, with different test items on the vertical and horizontal axes, and plotting icons of each learner based on the performance information corresponding to the test items ; a group classification unit that classifies the learners into groups in the graph; an outlier identification unit that identifies outliers from learners who do not belong to any of the groups in the graph; and an output unit that outputs the graph, the groups, and the outliers , wherein the test items are an index representing the format of the test and its results, or a questionnaire that is an evaluation of the test and its results . By installing and executing this program on a computer, the information processing device of the present invention can be configured.

The information processing device according to the present invention makes it possible to identify students who fall into outlier categories in a graph created based on multiple pieces of learning-related data.

1 shows a configuration of an information display system according to an embodiment. FIG. 2 is a block diagram showing the internal configuration of a management server. 1 is an example of a data configuration of a test DB. 10 is an example of a data configuration of an evaluation DB. This is an example of an evaluation index. 10 is an example of a data configuration of a questionnaire DB. 10 is an example of the data structure of a grade DB. This is an example of a scatter plot with test scores on the vertical axis and rubric evaluation scores on the horizontal axis. FIG. 10 is a diagram illustrating a first outlier pattern in a graph. FIG. 10 is a diagram illustrating a second outlier pattern in a graph. FIG. 10 is a diagram illustrating a third outlier pattern in a graph. FIG. 10 is a diagram illustrating a fourth outlier pattern in a graph. FIG. 10 is a diagram illustrating calculation of the student ratio for each area obtained by dividing a graph. FIG. 10 is a diagram illustrating detection of an area in a graph. FIG. 10 is a diagram illustrating group classification of students in a graph. FIG. 10 is a diagram illustrating the identification of students who fall under outliers. 10 is an example of a graph screen. 10 is a flowchart of a graph creation process. 10 shows a configuration of an information display system according to a modified example.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
<Embodiment>
[Overall configuration]
1 shows the configuration of an information display system to which an information processing device of the present invention is applied. The information display system 100 is configured so that a plurality of terminal devices 10 and a management server 20 can communicate with each other via a network 5. In this embodiment, as an example, the learners are students and the learning supporters are teachers.

The terminal device 10 is used by the teacher and may be, for example, a desktop PC, laptop PC, or tablet PC. The terminal device 10 is equipped with a display unit such as an LCD display, and is used to output grade information based on test results, etc.

The management server 20 is connected to a student database (hereinafter, "database" will be referred to as "DB") 31, a test DB 32, an assessment DB 33, a questionnaire DB 34, and a grade DB 35. The management server 20 creates a two-axis scatter plot (hereinafter simply referred to as a "scatter plot") that visualizes the learning status of all students and the learning status of each individual student, with the vertical and horizontal axes representing different perspectives, and references the grade DB 35. The management server 20 then classifies students into multiple groups on the graph and identifies outliers from among students who do not belong to any group. The management server 20 also creates a graph screen that displays information about the created graph, the classified groups, and the identified outliers, and transmits the information on the graph screen to the terminal device 10 used by the teacher. This allows the terminal device 10 to display the graph screen on its display.

Note that communication between the management server 20 and the terminal device 10 via the network 5 may be wired or wireless.

[Management Server Configuration]
2 is a block diagram showing the internal configuration of the management server 20. The management server 20 includes a communication unit 21, an input information acquisition unit 22, a grade information acquisition unit 23, a graph creation unit 24, a group classification unit 25, an outlier identification unit 26, and a graph screen output unit 27. These components, a student DB 31, a test DB 32, an evaluation DB 33, a questionnaire DB 34, and a grade DB 35 are interconnected via a bus 29.

The communication unit 21 is a communication unit for communicating with the terminal device 10 via the network 5. Specifically, the communication unit 21 receives input information from the terminal device 10 used by the teacher and transmits information about the created graph screen to the terminal device 10.

Student DB31 stores student information about students. Specifically, student DB31 stores student information such as a student ID, which is student identification information, the student's name, grade, class, etc.

Test DB32 stores test information related to test-style exams in which students enter answers. Figure 3 is an example of the data structure of test DB32. As shown in the figure, test DB32 stores information such as test type, test items, subject, and test ID. Test type is the type of exam, such as "first semester midterm" or "first semester final." Test items indicate the format of the exam and an indicator of its results; for test-style exams, this would be "test scores," and for evaluation-style exams described below, this would be "rubric evaluation points." Test items also indicate a questionnaire that evaluates the exam and an indicator of its results; for questionnaires, this would be "survey responses." Subject is the subject of the test, such as "mathematics," "Japanese," or "English." Test ID is identification information for the exam.

Note that test DB32 only needs to be able to check test information related to test-style exams, and its data structure can be set arbitrarily. For example, in this embodiment, the exam type is set to a regular exam including the semester in which it was conducted, but the present invention is not limited to this and can be set arbitrarily. Similarly, test items and subjects can also be set arbitrarily.

Evaluation DB33 stores evaluation information related to evaluation-style tests that evaluate student performance. In this embodiment, rubric evaluation is also considered to be a type of test and an evaluation-style test. Rubric evaluation is a method of evaluating a student's learning achievement using specified evaluation criteria, and can evaluate thinking ability and expressiveness based on performance in presentations, discussions, etc., rather than test scores. Figure 4 shows an example of the data structure of evaluation DB33. As shown, evaluation DB33 stores information such as test type, test items, evaluation items, subjects, test IDs, evaluation scores, and evaluation criteria. The test type, test items, subjects, and test IDs are the same as those in test DB32 described above.

Evaluation items are the evaluation criteria for rubric evaluation, such as "thinking, judgment, and expression." In this embodiment, there is only one evaluation criteria for rubric evaluation: "thinking, judgment, and expression." Evaluation points are scores that evaluate a student's performance, etc., and in this embodiment, they range from "0" to "10" in increments of one point, with lower scores indicating lower evaluations and higher scores indicating higher evaluations. Evaluation criteria are the standards for assigning evaluation points to a student's performance, and are linked to each evaluation point.

The evaluation DB 33 only needs to be able to confirm evaluation information related to the evaluation format of the test, and its data structure can be set arbitrarily. For example, in this embodiment, the evaluation items are based on one type of perspective, "thinking, judgment, and expression," but the evaluation items may be based on multiple types of perspectives, such as "thinking," "judgment," and "expression." The evaluation DB 33 may also include evaluation indices that associate evaluation items, evaluation scores, and evaluation criteria, and may use the evaluation indices to determine the evaluation score of a student's performance.

Here, we will explain how to specifically calculate evaluation scores using evaluation indices. Figure 5(a) shows an example of an evaluation indices when evaluation items are based on multiple perspectives. In this case, as shown in Figure 5(a), the vertical axis of the evaluation indices represents three types of evaluation items: "Thinking," "Judgment," and "Expression," and the horizontal axis represents evaluation scores of "1" to "3" for each evaluation item. The squares where the evaluation items on the vertical axis intersect with the evaluation scores on the horizontal axis represent the evaluation criteria for each evaluation item corresponding to each evaluation score. On the other hand, Figure 5(b) shows an example of an evaluation indices when thinking, judgment, and expression are combined into one type. In this case, as shown in Figure 5(b), the vertical axis of the evaluation indices represents one type of evaluation item: "Thinking, Judgment, and Expression," and the horizontal axis represents the evaluation score for the evaluation item "Thinking, Judgment, and Expression." Note that any evaluation criteria can be set.

Specifically, the teacher refers to the evaluation index shown in Figure 5(a) and compares the student's performance against the evaluation criteria for each evaluation item to determine the evaluation score for each of the evaluation items "Thinking," "Judgment," and "Expression." Furthermore, if there is only one evaluation item, the teacher looks at the evaluation results for each evaluation item comprehensively to determine the evaluation score for the evaluation item "Thinking, Judgment, and Expression." Specifically, the teacher refers to the evaluation index shown in Figure 5(b) and determines the evaluation score for the evaluation item "Thinking, Judgment, and Expression" based on the total evaluation score for each evaluation item.

In this embodiment, the horizontal axis of the evaluation index is the evaluation score, but the present invention is not limited to this and may also be the evaluation stage. Furthermore, the number of evaluation points and the number of stages in the evaluation stage can be set arbitrarily, and may be set to letters rather than numbers.

Furthermore, the method of calculating the grade is not limited to the method of conducting a graded assessment for each of the evaluation items "thinking," "judgment," and "expression," and then determining the grade for the evaluation item "thinking, judgment, and expression" by comprehensively examining the results of these assessments. It is also possible for a teacher or other person to create an exam and assessment index that combines the evaluation items "thinking, judgment, and expression," and then directly determine the grade based on that exam.

Furthermore, the evaluation DB 33 stores evaluation scores and evaluation criteria as evaluation information, but the management server 20 may store and manage the evaluation scores and evaluation criteria in a separate DB.

The questionnaire DB34 stores questionnaire information related to questionnaires in which students enter answer numbers. Questionnaires include evaluations and impressions of exams. Figure 6 shows an example of the data structure of the questionnaire DB34. As shown in the figure, the questionnaire DB34 stores information such as the exam type, exam item, subject, exam ID, survey content, answer number, and answer content. The exam type, exam item, subject, and exam ID are the same as those in the test DB32 described above.

The survey contents are questions posed to students, such as questions to gauge their level of understanding, such as "How much of the material on this test did you understand?" Answer numbers and answer contents are linked, and the survey answer number and its content are, for example, "I didn't understand it at all" corresponding to answer number "1" and "I understood it perfectly" corresponding to answer number "5." In this embodiment, surveys to gauge their level of understanding of each subject are administered at the time of regular exams, such as "mid-term of first semester" and "end-of-first semester," as indicated by the exam type. In this case, the smaller the answer number, the lower the student's level of understanding, and the higher the answer number, the higher the student's level of understanding.

The survey DB 34 only needs to be able to check survey information related to the survey, and its data structure can be set arbitrarily. The survey DB 34 stores the survey content, answer number, and answer content as survey information, but the management server 20 may store and manage the survey content, answer number, and answer content in a separate DB.

Result DB35 stores grade information related to the results of a student's exams and surveys, in association with the student's student ID. Figure 7 shows an example of the data structure of result DB35. As shown in the figure, result DB35 stores information such as student ID, exam type, exam item, exam ID, and test results. Specifically, test results are scores if the exam is in test format, grades if in assessment format, and answer numbers if in survey format. Results DB35 is updated once the marking, evaluation, and response collection of a student's exam have been completed and confirmed.

Note that the grade DB 35 only needs to continuously store the results of each test, such as a test or rubric evaluation, and the results of a survey for each student, and the data structure can be set as desired. Furthermore, in this embodiment, the management server 20 connects and manages the various DBs mentioned above, but the present invention is not limited to this. Information from multiple DBs may be consolidated into one, or information from one DB may be divided into multiple databases and managed.

The input information acquisition unit 22 acquires information about the exam that is the subject of the graph. Specifically, the teacher uses the terminal device 10 to specify on a specific screen the exam type, subject, test items to be displayed on the vertical axis of the graph, and test items to be displayed on the horizontal axis of the graph, and sends this information to the management server 20 as input information.

In addition, in this embodiment, the students who are the subject of the graph are students who belong to a specific grade. The affiliation of students who are the subject of the graph is not limited to grade level, but can be set arbitrarily, such as by class level. The affiliation of students who are the subject of the graph may be specified by a teacher and transmitted to the management server 20 as input information.

The grade information acquisition unit 23 acquires grade information for students in a specified grade from the grade DB 35 based on the input information. Specifically, the grade information acquisition unit 23 first references the student DB 31 to identify the student IDs of students in a specified grade. Furthermore, based on the test type, subject, test items on the vertical axis, and test items on the horizontal axis included in the input information, the grade information acquisition unit 23 references the test DB 32, assessment DB 33, and questionnaire DB 34 to identify the test IDs of the tests that will form the vertical axis of the graph and the test IDs of the tests that will form the horizontal axis. The grade information acquisition unit 23 then acquires grade information from the grade DB 35 based on the identified student IDs and test IDs.

Based on the grade information, the graph creation unit 24 creates a scatter diagram in which icons representing each student (hereinafter, "icons representing students" will also be referred to as "student icons") are plotted at the intersection of the test results on the horizontal axis and the test results on the vertical axis. Here, an icon is a simple symbol or graphic representation, such as a black circle or a human figure. Figure 8 is an example of a scatter diagram with test scores on the vertical axis and rubric evaluation scores on the horizontal axis. Note that graph 40 plots the icons of 100 students per grade, but because some icons overlap, for convenience, Figure 8 only depicts icons for approximately 30 students.

Specifically, as shown in FIG. 8, graph 40 has its vertical axis representing test scores, which are the results of tests indicated by the test type "End of First Semester," the subject "Japanese," and the test item "Test Score." Graph 40 also has its horizontal axis representing evaluation scores, which are the results of tests indicated by the test type "End of First Semester," the subject "Japanese," and the test item "Rubric Evaluation." Graph 40 plots human-shaped icons representing each student at the points where the test scores on the vertical axis intersect with the test evaluation scores on the horizontal axis. In this embodiment, since the rubric evaluation only uses one evaluation item, "Thinking, Judgment, and Expression," the horizontal axis of graph 40 displays "End of First Semester Thinking, Judgment, and Evaluation."

The group classification unit 25 classifies students into groups based on the positions of the icons plotted on the graph. In this embodiment, a group is a group of students with similar grades. Furthermore, the outlier identification unit 26 identifies students who are outliers from among students who do not belong to a group based on the icons plotted on the graph. In this embodiment, outliers are students who have poor grades or low survey ratings and who do not belong to a group on the graph.

Figure 9 is a diagram illustrating a first outlier pattern in a graph. In graph 40, the group classification unit 25 classifies students into three groups 42, 43, and 44 based on the position of the icons, as shown in Figure 9. In this case, the outlier identification unit 26 identifies students 45, 46, and 47, whose icons are plotted at positions away from groups 42, 43, and 44 and whose scores on the vertical axis and/or evaluation points on the horizontal axis are lower than the threshold, as outliers. Here, the threshold for scores on the vertical axis is set to 15 points, and the threshold for evaluation points on the horizontal axis is set to 3 points. Note that the score threshold and the evaluation point threshold are examples of the first threshold.

Figure 10 is a diagram illustrating a second outlier pattern in a graph. In graph 48, the group classification unit 25 classifies students into groups 49, 50, and 51 based on the position of the icon, as shown in Figure 10. In this case, the outlier identification unit 26 identifies student 53, whose icon is plotted at a position away from all of groups 49, 50, and 51 and whose score on the vertical axis and/or evaluation score on the horizontal axis are lower than the respective thresholds, as an outlier. Student 52, whose icon is plotted at a position away from all of groups 49, 50, and 51, does not qualify as an outlier because both the score on the vertical axis and the evaluation score on the horizontal axis are higher than the respective thresholds and the student has good grades.

Figure 11 is a diagram illustrating a third outlier pattern in a graph. In graph 54, the group classification unit 25 classifies students into groups 55, 56, and 57 based on the position of their icons, as shown in Figure 11. In this case, the outlier identification unit 26 identifies students 59 and 60 as outliers, whose icons are plotted away from groups 55, 56, and 57 and whose scores on the vertical axis and/or evaluation scores on the horizontal axis are lower than the respective thresholds. Student 58's icon is plotted outside the encircling lines representing each group, and his score on the vertical axis is lower than the score threshold, but his icon is close to that of group 55, so he is not an outlier. In other words, student 58 is considered to belong to group 55.

Figure 12 is a diagram illustrating the fourth outlier pattern on a graph. In graph 70, the student icons are uniformly distributed and no groups are formed. Therefore, there are no outliers. If the graph looks like this, it is likely that there is a problem with the test or assessment itself.

Here, we will explain in detail how to classify students into groups on a graph. Figure 13 is a diagram illustrating the calculation of the student ratio for each region into which the graph is divided. The group classification unit 25 divides the graph 40 into multiple regions of the same width and height. Specifically, as shown in Figure 13, the group classification unit 25 divides the graph 40 into 100 regions of the same size. The group classification unit 25 then calculates the student ratio, which is the ratio of the number of students whose icons are plotted in each region. For example, if 100 student icons are plotted on the graph 40, the icon of one student is plotted in region 61 indicated by a thick line, so the student ratio for region 61 is "0.01." Furthermore, the icons of 10 students are plotted in region 62 indicated by a thick line, so the student ratio for region 62 is "0.1." Furthermore, the icons of four students are plotted in regions 63 and 64 indicated by a thick line, so the student ratio for both regions 63 and 64 is "0.04." Note that the student ratio for regions without student icons is "0." Also, in the example of Figure 13, the regions into which the graph 40 is divided have the same width and height, but the present invention is not limited to this and any rectangular region may be used.

Figure 14 is a diagram illustrating the detection of regions in a graph. Figure 14(a) is a diagram in which the color and pattern of the regions are changed according to the calculated student ratio of each region. For convenience, in Figure 14(a), regions with a student ratio of "0" are displayed in white, regions with a student ratio of "0.1 or greater" are displayed in black, and regions with a student ratio of "greater than 0 and less than 0.1" are displayed in different patterns. The group classification unit 25 detects regions where the student ratio is equal to or greater than a predetermined student ratio threshold as detection regions. Here, the student ratio threshold is set to "0.05." Note that the student ratio threshold is an example of a second threshold. In this case, the group classification unit 25 also detects regions adjacent to the detection region where the student ratio is less than the threshold "0.05" but is "greater than 0" as adjacent regions. The group classification unit 25 may also detect regions adjacent to adjacent regions as adjacent regions.

For convenience, in Figure 14(b), the detection area is shown in black and the adjacent areas are shown in a diagonal line pattern. Specifically, area 61, which is not adjacent to the detection area and has a student ratio of "0.01", is shown in white. Area 62, which has a student ratio of "0.1", is shown in black as a detection area, along with adjacent areas with a student ratio equal to or greater than the threshold value of "0.05". Furthermore, area 63, which has a student ratio of "0.04" adjacent to detection area 65, and area 64, which has a student ratio of "0.04" adjacent to area 63, are shown in a diagonal line pattern as adjacent areas.

The group classification unit 25 combines adjacent detection areas to form a combined area. Specifically, as shown in FIG. 14(b), the group classification unit 25 combines adjacent detection areas in the upper right of the graph 40 to form combined area 66 surrounded by a dotted line. It also combines adjacent detection areas in the center of the graph 40 to form combined area 67 surrounded by a dotted line. It also combines adjacent detection areas in the lower left of the graph 40 with adjacent areas 63 and 64 to form combined area 68 surrounded by a dotted line.

Figure 15 is a diagram illustrating the group classification of students on a graph. The group classification unit 25 classifies students whose icons are plotted in the same integrated area into the same group. Specifically, as shown in Figure 15, the group classification unit 25 classifies, on graph 40, students whose icons are plotted in integrated area 66 into group 42, students whose icons are plotted in integrated area 67 into group 43, and students whose icons are plotted in integrated area 68 into group 44.

Next, we will explain how to identify students who are outliers. Figure 16 is a diagram that explains how to identify students who are outliers. The group classification unit 25 calculates the distance between the center of gravity of the integrated area corresponding to each group in the graph and the icon of a student who does not belong to any group in a brute-force manner. If the calculated distance is equal to or greater than a predetermined icon distance threshold, the outlier identification unit 26 identifies the student as an outlier. On the other hand, if the calculated distance is less than the icon distance threshold, the group classification unit 25 classifies the student into the same group as the student whose icon is plotted on the closest integrated area. Note that the icon distance threshold is an example of a third threshold.

For example, as shown in FIG. 16(a), the group classification unit 25 calculates the distance between the center of gravity of the integrated area 67 corresponding to group 43 and students 45, 46, 47, 71, 72, and 73 who do not belong to any group. Specifically, the group classification unit 25 calculates the distance between the center of gravity of the integrated area 67 and the position where the icons of each student who does not belong to any group are plotted. Similarly, although arrows are omitted in FIG. 16(a) for convenience, the group classification unit 25 calculates the distance between the center of gravity of the integrated area 66 corresponding to group 42 and students 45, 46, 47, 71, 72, and 73. Furthermore, the group classification unit 25 calculates the distance between the center of gravity of the integrated area 68 corresponding to group 44 and students 45, 46, 47, 71, 72, and 73.

In this case, the group classification unit 25 determines that the distance between integrated area 67 and students 72 and 73 is less than the icon distance threshold and that it is the closest integrated area. The group classification unit 25 then classifies students 72 and 73 into group 43, the same group as the students whose icons are plotted on integrated area 67. In other words, students 72 and 73 are considered to belong to group 43.

Furthermore, the outlier identification unit 26 identifies as outliers students who do not belong to a group on the graph those whose test indices corresponding to the vertical and horizontal axes exceed predetermined thresholds. Specifically, if the threshold for scores corresponding to the vertical axis is 15 points and the threshold for evaluation points corresponding to the horizontal axis is 3 points, and students who fall below one or more of these are identified as outliers, as shown in FIG. 16(b), the outlier identification unit 26 identifies students 45, 46, and 47 as outliers on graph 40. Note that student 71 does not qualify as an outlier because neither the test score corresponding to the vertical axis nor the rubric evaluation point corresponding to the horizontal axis is below the respective threshold.

The graph screen output unit 27 creates a graph screen including the graph created by the graph creation unit 24, the groups classified by the group classification unit 25, and information about students who fall into the outlier category identified by the outlier identification unit 26, and transmits screen information about the graph screen to the terminal device 10. By displaying the graph screen based on the screen information received by the terminal device 10, the teacher can check the scatter plot graph corresponding to the input information, the groups into which students with similar grades are classified in the graph, and information about students who fall into the outlier category.

The graph screen output unit 27 may also create a screen for the teacher to enter input information and transmit screen information related to that screen to the terminal device 10. In this embodiment, as will be described in detail later, the graph screen output unit 27 creates a screen for entering input information and outputting graphs, etc., and transmits information related to that screen to the terminal device 10 in response to login and various requests.

In the above configuration, the grade DB 35 of the management server 20 is an example of the storage unit of the present invention. Also, in the above configuration, the input information acquisition unit 22, outlier identification unit 26, and graph screen output unit 27 of the management server 20 are examples of the input information acquisition unit, outlier identification unit, and output unit of the present invention, respectively. Also, in the above configuration, the grade information acquisition unit 23 and graph creation unit 24 are examples of the graph creation unit of the present invention. Also, in the above configuration, the group classification unit 25 is an example of the group classification unit, graph division unit, learner proportion calculation unit, detection unit, integration unit, and distance calculation unit of the present invention.

[screen]
Next, we will explain the screens created and output by the graph screen output unit 27. The teacher displays the screen by logging in to a specific site using the terminal device 10 and inputs information about the test that will be the subject of the graph. In addition, when the teacher makes a request by pressing a specific button on the screen, a graph or the like corresponding to the input information is displayed on the screen.

Figure 17 is an example of a graph screen. As shown in Figure 17, the graph screen has a test type selection area 81, a subject selection area 82, a vertical axis item selection area 83, a horizontal axis item selection area 84, a scatter plot creation button 85, a graph display area 86, and a detailed display area 87.

The exam type selection area 81 is an area where the teacher selects any exam type they wish to visualize as a graph. The subject selection area 82 is an area where the teacher selects any subject they wish to visualize as a graph. The vertical axis item selection area 83 is an area where the teacher selects vertical axis items, which are the exam items they wish to display as the vertical axis of the graph. The horizontal axis item selection area 84 is an area where the teacher selects horizontal axis items, which are the exam items they wish to display as the horizontal axis of the graph. The information selected in the exam type selection area 81, subject selection area 82, vertical axis item selection area 83, and horizontal axis item selection area 84 is obtained as input information by the management server 20.

When the teacher has finished selecting the exam type, subject, vertical axis items, and horizontal axis items using the terminal device 10, he or she presses the scatter plot creation button 85 to send a graph output request to the management server 20. Upon receiving the graph output request, the management server 20 retrieves grade information from the grade DB 35 based on the input information, creates a graph, classifies students into groups, and identifies outliers. The management server 20 then creates a graph screen containing a scatter plot graph, groups into which students with similar grades are classified in the graph, and information about students who fall into the outlier category, and sends screen information about the graph screen to the terminal device 10. In this way, when the teacher presses the scatter plot creation button 85, the graph screen displays the graph, groups into which students are classified, and information about students who fall into the outlier category.

The graph display area 86 is an area that displays a graph of the created scatter plot. Specifically, as shown in FIG. 17, the graph display area 86 displays the graph 40, highlighting the solid lines surrounding each group and the dotted lines surrounding the outliers. The details display area 87 also displays detailed information about the outlier student, such as the name of the student, the test-related indicators on the vertical axis, and the test-related indicators on the horizontal axis. Specifically, as shown in FIG. 17, the details display area 87 displays the name of the outlier student, the test type "End of first semester" and test score for the subject "Japanese" on the vertical axis, and the evaluation score for the rubric evaluation item "Thinking, Judgment, and Evaluation" for the test type "End of first semester" and subject "Japanese" on the horizontal axis as detailed information.

The graph screen allows teachers to easily send input information to the management server 20. Furthermore, the graph screen allows teachers to easily view scatter plot graphs corresponding to the test type, subject, vertical axis items, and horizontal axis items selected by the teacher, as well as the groups into which students are classified on the graph, and information about students who are outliers on the graph.

When logging in to a specific site, only the range indicated by the input at the top of the screen shown in Figure 17 is displayed, and by pressing the scatter plot creation button 85, the range indicated by the output at the bottom of the screen is displayed. The screen shown in Figure 17 is only an example, and the present invention is not limited to this; the screen configuration can be set as desired. For example, the test type, subject, vertical axis items, and horizontal axis items may be input rather than selected using radio buttons, and subjects may be selected for the vertical and horizontal axes, respectively.

[Graph creation process]
17 is a flowchart of the graph creation process according to this embodiment. This process creates a graph with the teacher's vertical and horizontal axes specified based on the input information and grade information, and identifies students who fall into outliers on the graph. Specifically, this process is realized by the computer constituting the management server 20 executing a program prepared in advance.

Teachers log in to a specific site using their terminal device 10 to display the graph screen and select the test type, subject, vertical axis items, and horizontal axis items. Once selections are complete, the teacher presses a specific button on the screen to send the input information to the management server 20 and request graph output.

The management server 20 acquires input information from the terminal device 10 (step S11). Based on the acquired input information, the management server 20 acquires grade information from the grade DB 35 (step S12). The management server 20 then creates a scatter graph by plotting the test results of the corresponding students based on the grade information, with the test-related indicators specified by the teacher based on the input information on the vertical and horizontal axes (step S13).

Next, the management server 20 classifies the students into groups based on the student icons plotted on the created graph (step S14). The management server 20 then identifies outliers from among the students who do not belong to any group on the graph, students with poor grades whose test-related indicators on the vertical and horizontal axes are below a threshold (step S15). The management server 20 then creates a graph screen containing the created graph, the classified groups, and information about the identified outlier students, and sends information about the graph screen to the terminal device 10 (step S16). This completes the graph creation process. The teacher can display the graph screen on the terminal device 10 and check the graph, groups, and students who are outliers.

In this embodiment, the test-style exam and the evaluation-style exam are in separate formats, but the evaluation-style exam may also be included in the test-style exam, and the evaluation points may be included in the score.

In addition, in this embodiment, the test items "Test Score" and "Rubric Evaluation" are specified as the vertical and horizontal axes of the scatter plot graph, but the present invention is not limited to this, and any of the test items "Test Score," "Rubric Evaluation," and "Survey Response" may be selected as the vertical and horizontal axes. As mentioned above, in this embodiment, the survey is a question asking about the level of understanding, and the smaller the answer number, the lower the student's level of understanding, and the higher the answer number, the higher the student's level of understanding. Therefore, in the survey as well, students whose answer numbers are below a predetermined threshold for survey responses can be considered to be students with poor grades, so the management server 20 can apply graph creation processing.

In addition, in this embodiment, the indicators are scores, evaluation points, and answer numbers, which are indicators of grades, but the present invention is not limited to this and can be set to any indicator related to learning. Furthermore, various thresholds can be set arbitrarily.

Furthermore, in this embodiment, students whose distance from the center of gravity of the integrated area is less than a threshold are classified into the same group as students whose icons are plotted in the closest integrated area. However, the present invention is not limited to this, and the management server 20 may classify into the same group only students whose icons are plotted in the same integrated area. In this case, the management server 20 identifies as outliers students whose distance from the center of gravity of the integrated area is greater than or equal to the icon distance threshold and whose indicators corresponding to the vertical and horizontal axes are less than the corresponding thresholds.

Identifying learners who fall under outliers on a graph requires a high workload, as it requires consideration of not only the individual learner's performance information but also the overall situation of the learners. For example, while conventional k-means clustering methods can group learners plotted on a graph, it is difficult to identify outliers. However, the information display system 100 of the present invention can automatically identify outlier learners in scatter plots that visualize regular test scores, rubric assessment scores, learner survey results, and more. This reduces the workload of learning support staff, makes it easier to propose individually optimized instruction for outlier learners, and improves learning efficiency.

<Variations>

In the above embodiment, the teacher uses the terminal device 10, but the present invention is not limited to this, and the teacher may use a teacher terminal that has the functions of the management server 20. Like the terminal device 10, the teacher terminal may be, for example, a desktop PC, laptop PC, tablet PC, etc.

Figure 19 shows an example configuration of an information display system 200 in this case. As shown, a student DB 91, a test DB 92, an evaluation DB 93, a questionnaire DB 94, and a grade DB 95 are connected to the teacher terminal 90 in the information display system 200. The teacher terminal 90 can execute the processing previously performed by the management server 20 (corresponding to steps S11 to S16 in Figure 18) to create and display information on a graph screen. The teacher terminal 90 can also print graphs, groups, and information on students corresponding to outliers displayed on the graph screen. In this case, the teacher terminal 90 is an example of an information processing device of the present invention.

5 Network 10 Terminal device 20 Management server 21 Communication unit 22 Input information acquisition unit 23 Grade information acquisition unit 24 Graph creation unit 25 Group classification unit 26 Outlier identification unit 27 Graph screen output unit 31, 91 Student DB
32, 92 Test DB
33, 93 Evaluation DB
34, 94 Survey DB
35, 95 Grade DB
90 Teacher's terminal 100, 200 Information display system

Claims (9)

a storage unit that stores identification information of a plurality of learners and performance information related to the learning of the learners in association with each other;
a graph creation unit that creates a scatter diagram as a graph, in which the vertical axis and the horizontal axis represent different test items and the icons of each learner are plotted based on the performance information corresponding to the test items ;
a group classification unit that classifies the learners into groups in the graph;
an outlier identifying unit that identifies an outlier learner from among learners who do not belong to the group in the graph;
an output unit that outputs the graph, the group, and the outlier;
Equipped with
The test items are an index showing the format of a test and its results, or a questionnaire that is an evaluation of a test and its results . the performance information includes indicators relating to a plurality of test items ;
The information processing device according to claim 1 , wherein the outlier identifying unit identifies, in the graph, a learner who does not belong to the group and whose index included in the performance information is lower than a first threshold, as an outlier. a graph division unit for dividing the graph into a plurality of regions of equal size;
a learner ratio calculation unit that calculates a learner ratio, which is the ratio of the number of learners whose icons are plotted in each area;
a detection unit that detects an area where the learner ratio is equal to or greater than a second threshold as a detection area;
an integration unit that integrates adjacent detection regions into an integrated region,
The information processing device according to claim 2 , wherein the group classification unit classifies learners whose icons are plotted in the same integrated area into the same group. The information processing device described in claim 3, wherein if there is an area adjacent to the detection area where the learner ratio is less than the second threshold but not zero, the integration unit also integrates the area into an integrated area. a distance calculation unit that calculates the distance between the center of gravity of the integrated area and an icon of a learner that is not plotted on any integrated area;
The information processing apparatus according to claim 3 , wherein the outlier identifying unit identifies a learner whose icon has the distance equal to or greater than a third threshold as an outlier. The information processing device described in claim 5, wherein the group classification unit classifies learners whose icons are less than a threshold distance from the integrated area into the same group as learners whose icons are plotted in the integrated area. an input information acquisition unit that acquires different test items as input information for the vertical and horizontal axes of the graph;
The information processing apparatus according to claim 2 , wherein the graph creation unit creates the scatter diagram as a graph based on the input information and the performance information. 8. The information processing device according to claim 7, wherein the output unit outputs, based on the performance information, either an index related to the test item that is the target of the vertical axis or an evaluation of the test item , and either an index related to the test item that is the target of the horizontal axis or an evaluation of the test item , for the learner who falls under the outlier. A program executed by an information processing device having a computer,
a storage unit that stores identification information of a plurality of learners and performance information related to learning by the learners in association with each other;
a graph creation unit that creates a scatter diagram as a graph, in which the vertical axis and the horizontal axis are different test items and icons of each learner are plotted based on the performance information corresponding to the test items;
a group classification unit that classifies the learners into groups in the graph;
an outlier identifying unit that identifies, in the graph, a learner who is an outlier from among learners who do not belong to the group;
an output unit that outputs the graph, the group, and the outlier;
causing the computer to function as
The test items are a program that includes a test format and an index showing the results, or a questionnaire that is an evaluation of the test and an index showing the results .