Learning assistance system, method and program

Abstract

To predict a future time slot in which the state of the concentration level of a learner higher than or equal to a prescribed threshold continues for a prescribed time or more, on the basis of the concentration level of the learner at the present or the latest prescribed time up to the present.SOLUTION: A vital information measurement unit 10 acquires vital information from the sample of a learner group. A concentration level measurement unit 20 measures the current concentration level C of a learner or each sample on the basis of at least some of the vital information of the learner or each sample, such as the number of blinks N or the heart rate H. A learning unit 30 accumulates the time-series data of the concentration level C of the learner or each sample as a learning log. A prediction unit 40 predicts the future concentration level of the learner on the basis of the time-series data of the concentration level C. A learning assistance unit 50 proposes a time slot in which the state of the predicted concentration level C higher than or equal to a prescribed threshold continues for a prescribed time or more, as a recommended learning time slot.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a learning support system, method, and program, and in particular to a learning support system, method, and program for predicting a future time period during which the concentration level of a learner receiving support will be above a predetermined threshold and will continue for more than a predetermined period of time. [Background technology]

[0002] Due to the COVID-19 pandemic and advances in digitalization, online learning opportunities and content are on the rise. Online learning is expected to continue to expand in the future as it can be pursued according to one's own convenience regarding time and place.

[0003] Patent Document 1 discloses a technique for recommending learning materials that a learner should study next based on the learner's level of understanding and concentration. Patent Document 2 discloses a technique for recommending learning materials that a learner should study next based on the learner's level of understanding and motivation.

[0004] Non-Patent Documents 1 and 2 describe the relationship between body temperature and concentration level. Non-Patent Document 3 discloses a technique for estimating concentration level based on blinking. Non-Patent Document 4 discloses a technique for estimating concentration level based on heart rate. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 6977901 [Patent Document 2] Patent No. 7327455 [Non-patent literature]

[0006] [Non-Patent Document 1] Heat reduces concentration [Do you know, teacher? (43)];https: / / www.jmedj.co.jp / journal / paper / detail.php?id=17696 [Non-Patent Document 2] Health column: "What happens when your body temperature is low? Symptoms to watch out for, causes and how to deal with them"; https: / / www.citizen-systems.co.jp / health / column / article / article_12.html [Non-Patent Document 3] https: / / jinsmeme.com / brain / [Non-Patent Document 4] https: / / news.yahoo.co.jp / articles / 8ad2010ecaa0c279e014640d39b6c33bda3e8adf Summary of the Invention [Problem to be solved by the invention]

[0007] It is empirically and experimentally known that the learning effect varies greatly depending on the level of concentration. In addition, the relationship between the level of concentration and time of day varies from person to person, and even for the same person, the relationship between the level of concentration and time of day changes depending on various factors.

[0008] On the other hand, the techniques disclosed in the above patent documents and non-patent documents can predict the current concentration level but cannot predict the future concentration level, and therefore cannot predict a time period during which a high concentration state will continue for a predetermined period of time, i.e., a time period suitable for intensive learning.

[0009] The object of the present invention is to solve the above-mentioned technical problems and provide a learning support system, method, and program that predicts a future time period during which the concentration level of a learner receiving support will be above a predetermined threshold and will continue for more than a predetermined period of time, based on the learner's current concentration level or the most recent predetermined period leading up to the present. [Means for solving the problem]

[0010] In order to achieve the above object, the present invention provides a learning support system for supporting learning in accordance with a learner's level of concentration, the system being characterized by having the following configuration.

[0011] (1) The system comprises a means for measuring vital information of learners and a sample of their groups, a means for measuring concentration levels based on the vital information, a means for accumulating time-series data on the concentration levels, and a means for predicting the future concentration levels of a learner based on the time-series data on the concentration levels and the measurement results of the learner's concentration levels.

[0012] (2) The means for making the prediction is arranged to predict a time period during which a state in which a learner's concentration level is equal to or higher than a predetermined threshold will continue for a predetermined period of time or more.

[0013] (3) A means is provided for selecting, from the sample time series data, time series data which shows a higher correlation with the measurement result of the concentration level of a particular learner, and the predicting means is adapted to predict the future concentration level of a particular learner based on the selected time series data.

[0014] According to the present invention, the following effects can be achieved:

[0015] (1) It becomes possible to predict a time period during which a learner's concentration level will be above a predetermined threshold and will continue for a predetermined period of time or more.

[0016] (2) It is possible to predict the time period during which a learner's concentration level will be above a predetermined threshold and will continue for a predetermined period of time or more, so that it is possible to support the learner in studying during the time period when learning efficiency is high. [Brief description of the drawings]

[0017] [Figure 1] 1 is a functional block diagram showing a configuration of a main part of a learning support system according to a first embodiment of the present invention. [Diagram 2] FIG. 1 shows a method for predicting concentration (part 1). [Diagram 3]FIG. 13 is a diagram showing a method for predicting the concentration level (part 2). [Figure 4] FIG. 11 is a functional block diagram showing a configuration of a main part of a learning support system according to a second embodiment of the present invention. [Diagram 5] FIG. 13 shows an example (part 1) of constructing a learning model based on a learning log. [Figure 6] FIG. 11 is a functional block diagram showing a configuration of a main part of a learning support system according to a third embodiment of the present invention. [Figure 7] FIG. 2 shows an example (part 2) of constructing a learning model based on a learning log. [Figure 8] FIG. 13 is a functional block diagram showing a configuration of a main part of a learning support system according to a fourth embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0018] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Fig. 1 is a functional block diagram showing the configuration of the main part of a learning support system 1 according to a first embodiment of the present invention, and the main components are a vital information measuring unit 10, a concentration measuring unit 20, a learning unit 30, a prediction unit 40, and a learning support unit 50.

[0019] Such a learning support system 1 can be configured by implementing applications (programs) that realize the functions detailed below on a general-purpose computer or server equipped with a CPU, ROM, RAM, bus, interface, etc., or on a portable smartphone or tablet terminal. Alternatively, it can be configured as a dedicated machine or a single-function machine in which part of the application is implemented as hardware or software.

[0020] The vital information measurement unit 10 measures vital information of a learner receiving support or a portion (sample) of a large group of learners who have similar learning attributes to the learner. In this embodiment, the vital information measurement unit 10 includes a heart rate measurement unit 101, a body temperature measurement unit 102, a sleep measurement unit 103, and a blink detection unit 104, and measures the heart rate H, body temperature T, sleep state S (sleep onset time S1, wake-up time S2, sleep duration Sd), and blink count N of the learner or sample.

[0021] The concentration measurement unit 20 measures the current concentration level C of the learner and each specimen based on at least a part of the vital information of the learner and each specimen, for example, the number of blinks N and the heart rate H. The learning unit 30 includes a learning log accumulation unit 301, which accumulates time series data on the measurement results of the concentration level C of the learner and each specimen as a learning log. The prediction unit 40 predicts the future concentration level of the learner based on the time series data of the concentration level C.

[0022] 2 and 3 are diagrams that show a model of a method for predicting a learner's future concentration level. In this embodiment, the prediction unit 40 includes a selection unit 401, and selects time series data that shows a higher correlation with the measurement result of the learner's concentration level from among a large number of time series data related to the concentration level C acquired from a sample. The prediction unit 40 predicts the learner's future concentration level C, expecting that the learner's future concentration level C will transition in the same manner as the selected time series data.

[0023] 2, the selection unit 401 selects time-series data in which the sample concentration level at the time when the learner's concentration level C is measured is closer to the learner's concentration level C. In the example shown in the figure, the learner's current concentration level C is closer to pattern 1 than to pattern 2, so the learner's concentration level C from now on is predicted based on pattern 1.

[0024] 3, the selection unit 401 selects time series data in which the concentration level C of a sample during a predetermined period in which the concentration level of a learner was measured is closer to the concentration level C of the learner. In the example shown, the time series of the concentration level C (solid line) during the most recent predetermined period up to the present, for example, the time from the learner's wake-up time or the period from a predetermined time to the present, is more similar to pattern 1 than to pattern 2, so that the concentration level C of the learner from the present onwards is predicted based on pattern 1.

[0025] The learning support unit 50 proposes, as a recommended learning time period Drec, time periods D1 and D2 in which the predicted concentration level C remains equal to or greater than a predetermined threshold for a predetermined period of time or longer.

[0026] FIG. 4 is a functional block diagram showing the configuration of the main parts of a learning support system 1 according to a second embodiment of the present invention. Since the same reference numerals as those described above represent the same or equivalent parts, the description thereof will be omitted.

[0027] In this embodiment, the learning log accumulation unit 301 of the learning unit 30 accumulates time series data of the heart rate H, body temperature T, sleep state S, learning time D, and concentration level C at that time of the learner and each sample as a learning log, as shown in an example in Figure 5.

[0028] The learning unit 30 further includes a model construction unit 302, which constructs a learning model M based on the accumulated numerous learning logs by learning using the heart rate H, body temperature T, and sleep state S of each sample as explanatory variables, and the learning time D and the concentration level C during that time as objective variables.

[0029] The prediction unit 40 predicts the study time during which the state in which the concentration level C is equal to or greater than a predetermined value will continue for a predetermined period of time from now onwards by applying the current vital information H, T, and S of the learner who wishes to receive support to the learning model M. The learning support unit 50 proposes the study time as a recommended study time slot Drec.

[0030] 6 is a functional block diagram showing the configuration of a learning support system 1 according to a third embodiment of the present invention, and the same reference numerals as those described above represent the same or equivalent parts, so the description thereof will be omitted. This embodiment is characterized in that it includes a learning material database (DB) 60, and proposes the recommended study time period Drec in association with unlearned learning materials that are desirable to study during that time period.

[0031] In the learning materials DB60, subjects that have not yet been studied by the learner who is seeking support are registered along with the time required for studying and the level of difficulty. For example, "Subject A (15 minutes, Level 1)" indicates that it takes 15 minutes to study subject A and that it is a learning material that can be studied even with a low level of concentration. "Subject A (15 minutes, Level 2)" indicates that it takes 15 minutes to study subject A and that it is a learning material that can be studied with a medium level of concentration.

[0032] When the length of the recommended study time slot Drec is 15 minutes, the learning support unit 50 can suggest studying 15 minutes of learning material A or learning material B during that time slot. At this time, if the concentration level of the recommended study time slot Drec is equivalent to or higher than Level 2, it is desirable to suggest studying "subject A (15 minutes, Level 2)", and if it is less than Level 2, to suggest studying "subject A (15 minutes, Level 1)" or "subject B (15 minutes, Level 1)".

[0033] In addition, subjects that the learner who is to receive support has not yet studied may be registered together with the time required for studying the subject, the level of difficulty, and the level of urgency in the study materials DB 60. Here, the level of urgency is set according to the number of days until the exam date or the length of the validity period when the exam date for the subject is approaching or the validity period of the study materials to be used for the subject is approaching.

[0034] Generally, since the urgency level is the top priority condition in learning, when "Subject A (15 minutes, Level 1)" and "Subject B (15 minutes, Level 1)" are selected as candidates based on the time required for learning and the level of difficulty, if, for example, the exam date for subject A is approaching, studying "Subject A (15 minutes, Level 1)" may be suggested last.

[0035] According to this embodiment, it becomes possible to recommend optimal learning materials that enable efficient learning from among unstudied learning materials, depending on the duration of the recommended study time period and the level of concentration.

[0036] In the above embodiment, when the concentration level of a learner is measured during learning and a learning log is registered, the name of the learning material being studied and information about the subject are also added to the learning log, and a learning model M is also constructed for each subject, as shown in an example in Fig. 7. This makes it possible to predict the recommended study time slot Drec and the concentration level at that time for each subject. Therefore, the combination of the recommended study time slot Drec and the subject that will maximize the concentration level may be proposed to the learner.

[0037] In addition, in the above embodiment, the heart rate H, body temperature T, and sleep state S are measured as the learner's vital information, but the present invention is not limited to this, and instead of or in addition to these vital information, blood pressure, behavior, changes in posture, etc. may be obtained and added to the learning log to construct a learning model M.

[0038] Furthermore, in the above second and third embodiments, the learning support system 1 is described as having a learning unit 30 and collecting and accumulating learning logs to construct the learning model M, but the present invention is not limited to this, and it is also possible to obtain a learning model M constructed by a third institution rather than constructing the learning model M by itself, and apply current vital information to the learning model M.

[0039] According to each of the above embodiments, the time periods when learners are likely to be highly concentrated can be predicted in advance and suggested as recommended study times, so that online learning opportunities can be allocated to those times when students are likely to be highly concentrated. This makes it possible to contribute to Goal 9 "Build resilient infrastructure and promote inclusive and sustainable industrialization" and Goal 11 "Make cities inclusive, safe, resilient and sustainable" of the Sustainable Development Goals (SDGs) led by the United Nations. [Explanation of symbols]

[0040] 10... vital information measurement unit, 20... concentration measurement unit, 30... learning unit, 40... prediction unit, 50... learning support unit, 60... learning material DB, 101... heart rate measurement unit, 102... body temperature measurement unit, 103... sleep measurement unit, 201... blink detection unit, 202... heart rate measurement unit, 301... past log accumulation unit, 302... model construction unit, 401... selection unit

Claims

1. A learning support system that supports learning according to the learner's concentration level. a means for measuring vital information of learners and a sample of the learners' population; A means for measuring a concentration level based on the vital sign information; A means for accumulating time series data of the concentration degree; and a means for predicting a future concentration level of a particular learner based on the time-series data of the concentration level and the measurement results of the concentration level of the particular learner.

2. 2. The learning support system according to claim 1, wherein the predicting means predicts a time period during which a state in which the one learner's concentration level is equal to or higher than a predetermined threshold value will continue for a predetermined period of time or longer.

3. a means for selecting, from the sample time series data, time series data that shows a higher correlation with the measurement result of the degree of concentration of the one learner; 3. The learning support system according to claim 1, wherein said predicting means predicts a future concentration level of one learner based on the selected time-series data.

4. The learning support system according to claim 3, characterized in that the selecting means selects time series data in which the sample concentration level at the time when the concentration level of the one learner is measured is closest to the concentration level of the one learner.

5. The learning support system according to claim 3, characterized in that the selecting means selects time series data in which a sample concentration level during a specified period in which the concentration level of the one learner was measured is closest to the concentration level of the one learner during the specified period.

6. the means for accumulating the time series data further accumulates time series data of vital information corresponding to the time series data of the concentration degree; constructing a learning model by learning each of the time-series data using the vital information of the specimen as an explanatory variable and the learning time and the concentration as an objective variable; The learning support system according to claim 1, characterized in that the predicting means applies the measurement results of the vital information of the one learner to the learning model, and predicts the learning time during which the one learner's concentration level remains above a predetermined threshold for a predetermined period of time or more, and the concentration level.

7. a database for managing unlearned learning materials by the one learner together with information on the time required for learning the learning materials; 7. The learning support system according to claim 6, wherein the predicting means predicts a time period during which a learner's concentration level exceeds the predetermined threshold value exceeds the time required to learn the unlearned learning material.

8. The database manages the unlearned learning materials together with the time and difficulty required for learning the learning materials, The learning support system according to claim 7, characterized in that the predicting means predicts a time period during which a learner's concentration level exceeds the specified threshold value that is equal to or longer than the time required to study the unstudied learning material and during which the concentration level is equal to or higher than the concentration level corresponding to the difficulty level.

9. A learning support method in which a computer supports a learner's learning in accordance with the learner's level of concentration, comprising: Measure vital information for learners and a sample of their groups; Measure a concentration level based on the vital sign information; Accumulating time series data of the concentration degree; A learning support method comprising predicting a future concentration level of a learner based on the time-series data of the concentration level and the measurement results of the concentration level of the learner.

10. 10. The learning support method according to claim 9, wherein the prediction of the concentration level includes predicting a time period during which the state in which the concentration level of the one learner is equal to or higher than a predetermined threshold value continues for a predetermined period of time or more.

11. selecting, from the sample time series data, time series data that shows a higher correlation with the measurement result of the concentration level of the one learner; 11. The learning support method according to claim 9, wherein the prediction of the concentration level includes predicting a future concentration level of one learner based on the selected time-series data.

12. In this learning support program, we support students according to their level of concentration. A procedure for measuring vital information of learners and a sample of the group; measuring a concentration level based on the vital sign information; A step of accumulating time series data of the concentration degree; and a step of predicting a future concentration level of a learner based on the time-series data of the concentration level and the measurement results of the concentration level of the learner.

13. 13. The learning support program according to claim 12, wherein the predicting step predicts a time period during which a state in which the one learner's concentration level is equal to or higher than a predetermined threshold will continue for a predetermined period of time or longer.

14. selecting, from the sample time-series data, time-series data that shows a higher correlation with the measurement result of the degree of concentration of the one learner; 14. The learning support program according to claim 12, wherein in said predicting step, a future concentration level of one learner is predicted based on the selected time-series data.

Images