Learning support systems, methods, and programs

Abstract

We provide technology that supports learning, enabling students to correctly and deeply understand what they need to learn. [Solution] The learning support system includes a dialogue unit that engages in a dialogue with the learner to have the learner explain a predetermined learning item, an accuracy determination unit that determines the accuracy of the explanation in the dialogue, and an understanding determination unit that determines the depth of the learner's understanding of the learning item.

Description

Technical Field

[0001] This disclosure relates to a technology for assisting learning.

Background Art

[0002] Active learning in which learners actively and proactively engage in learning is known to have a high learning effect. Active learning includes learning methods such as group discussion, experiencing by oneself, and teaching others. In particular, the learning method of teaching oneself by teaching others through dialogue is said to have a high learning effect. However, it is not easy to implement the learning method of teaching others. Since it cannot be implemented by a single learner, it is necessary to secure others and provide a place for implementation. In addition, teaching others itself takes a certain amount of time, and others will be restricted during that time. In addition, the act of teaching others is a rather difficult act for learners, and psychological factors such as not wanting to be ashamed or not wanting to do it work, which hinders implementation.

[0003] Patent Document 1 discloses a technology for assisting the implementation of learning through dialogue using a computer. The system disclosed in Patent Document 1 stores problem information regarding a predetermined problem statement of a problem presented to a learner and a plurality of correct answer constituent phrases included in the correct answer of the problem, presents the problem to the learner, and realizes dialogue with the learner by acquiring a response from the learner. Then, the correct answer constituent phrases included in the response from the learner are specified, and the correct answer constituent phrases not included in the response are further presented as hints. According to this system, a learner can perform learning through dialogue alone without hesitation with a computer as a partner.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] The system described in Patent Document 1 evaluates the learner's level of understanding based on how many correct constituent words are included in the learner's utterance. However, even if the content of the learner's response is correct, it does not necessarily mean that the learner has deeply understood and internalized that knowledge. In this respect, while the system described in Patent Document 1 can evaluate the accuracy of the learner's understanding based on whether or not the correct constituent words are included in the learner's utterance, it is difficult to evaluate the depth of the learner's understanding. One of the purposes included in this disclosure is to provide technology that supports learning in order to correctly and deeply understand what needs to be learned. [Means for solving the problem]

[0006] A learning support system according to one aspect of the present invention includes a dialogue unit that engages in a dialogue with a learner to have the learner explain a predetermined learning item; an accuracy determination unit that determines the accuracy of the explanation in the dialogue; and an understanding determination unit that determines the depth of the learner's understanding of the learning item. [Effects of the Invention]

[0007] One aspect included in this disclosure makes it possible to support learning in order to correctly and deeply understand what needs to be learned. [Brief explanation of the drawing]

[0008] [Figure 1] This is a block diagram showing the functional configuration of the learning support system of this embodiment. [Figure 2] This diagram shows the hardware configuration of the learning support system of this embodiment. [Figure 3] This is a flowchart of the interactive learning process using a learning support system. [Figure 4] This is a conceptual diagram illustrating how interactive learning using a learning support system works. [Figure 5]This figure shows an example of information on the accuracy evaluation method (points awarded). [Figure 6] This figure shows an example of how scores are displayed. [Figure 7] This figure shows an example of accuracy evaluation method information (weighting). [Figure 8] This figure shows an example of information on methods for evaluating comprehension. [Figure 9] This figure shows an example of how growth analysis results are displayed. [Figure 10] This diagram illustrates the logic for deciding whether or not to provide a model explanation. [Modes for carrying out the invention]

[0009] Embodiments of the present invention will be described with reference to the drawings. Figure 1 is a block diagram showing the functional configuration of the learning support system according to this embodiment.

[0010] The learning support system 10 includes a reading unit 11, a dialogue unit 12, an accuracy determination unit 13, an understanding determination unit 16, an overall determination unit 19, a motivation processing unit 20, and a feedback unit 23. The accuracy determination unit 13 includes a speech analysis unit 14 and a text evaluation unit 15. The understanding determination unit 16 includes a paralinguistic measurement unit 17 and a paralinguistic evaluation unit 18. The motivation processing unit 20 includes a ranking unit 21 and a growth visualization unit 22.

[0011] The dialogue unit 12 works in conjunction with the generative artificial intelligence 81, interacting with the learner 80 as an avatar instructor and prompting the learner 80 to explain predetermined learning items. The reading unit 11 outputs the utterances of the avatar instructor, generated by the dialogue unit 12, as spoken audio to the learner 80. The speech analysis unit 14 converts the audio of the explanation about the learned material spoken by the learner 80 into text. The text is sent to the text evaluation unit 15. The text evaluation unit 15 calculates the accuracy of the explanations presented in the text. Accuracy represents the correctness of the explanations. The accuracy is sent to the overall judgment unit 19. The paralanguage measurement unit 17 measures the paralanguage (e.g., speech rate and intonation) included in the learner 80's speech. The measurement result is sent to the paralanguage evaluation unit 18.

[0012] The paralanguage evaluation unit 18 calculates a predetermined paralanguage evaluation index and calculates the degree of understanding based on the paralanguage index. The degree of understanding is the depth of understanding of the learning items of the learner 80. The degree of understanding is sent to the comprehensive determination unit 19.

[0013] The comprehensive determination unit 19 calculates the proficiency level based on the accuracy and the degree of understanding. The proficiency level is an index that comprehensively evaluates how proficient the learner 80 is in the learning items, in other words, how well the learner can use the knowledge of the learning items. Information on the accuracy, the degree of understanding, and the proficiency level is sent to the ranking unit 21 and the growth visualization unit 22 of the motivation processing unit 20, and to the feedback unit 23. The ranking unit 21 totals the degree of proficiency for each learner, ranks the learners, and presents them to the learner 80.

[0014] The growth visualization unit 22 records, in association with the learning items, the number of times of learning by teaching the learning items and the proficiency level calculated in that session, and performs a visible display of the state of change in the proficiency level with each passing session.

[0015] The feedback unit 23 provides encouraging words to the learner in the dialogue based on at least one of the accuracy, the degree of understanding, and the proficiency level. Also, the feedback unit 23 determines whether or not to teach a model explanation to the learner 80 based on one or more of the accuracy, the degree of understanding, and the proficiency level, and if it is determined that a model explanation should be taught, provides the model explanation to the learner 80 in the dialogue. FIG. 2 is a block diagram showing the hardware configuration of the learning support system of the present embodiment. The learning support system 10 is composed of a server 30 and an information terminal 40. The server 30 and the information terminal 40 can communicate with each other via a communication network 82.

[0016] The server 30 comprises a processor 31, main memory 32, storage device 33, communication device 34, input device 35, and display device 36. The processor 31, main memory 32, storage device 33, communication device 34, input device 35, and display device 36 are connected to each other via a bus 37 so that they can communicate with one another.

[0017] The processor 31 is composed of, for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), etc. The processor 31 reads and executes various programs stored in the main memory 32 or storage device 33, thereby realizing various functions of the learning support system 10.

[0018] Main memory 32 is the primary memory that stores programs and data, and can be, for example, Random Access Memory (RAM), Read Only Memory (ROM), or Non-Volatile RAM (NVRAM).

[0019] The storage device 33 is, for example, a Hard Disc Drive (HDD), Solid State Drive (SSD), storage system, Integrated Circuit (IC) card, Secure Digital (SD) memory card, or a reading and writing device for optical recording media (such as Compact Disc (CD) or Digital Versatile Disc (DVD)), or the storage area of ​​a cloud server.

[0020] The cache and registers of the processor 31, the main memory 32, and the storage device 33 are sometimes collectively referred to as memory. Information processing in the learning support system 10 is performed when the necessary programs and data are loaded into memory and executed. Various parameters such as thresholds may also be stored in memory. Programs, databases, datasets, etc., may also be stored in memory.

[0021] The communication device 34 is a wired or wireless communication interface that enables communication with other devices such as an external server (not shown) or an information terminal 40 via the communication network 82. For example, the communication device 34 may be a Network Interface Card (NIC), a wireless communication module, a Universal Serial Interface (USB) module, or a serial communication module.

[0022] Input device 35 is a device that receives input from the administrator. Input device 35 may be, for example, a keyboard, mouse, touch panel, card reader, or voice input device.

[0023] The display device 36 is a device that provides various information to the administrator. The display device 36 may be, for example, a screen display device (Liquid Crystal Display (LCD), Head Mounted Display (HMD), etc.), an audio output device, a printing device, etc. The communication network 82 is a wired or wireless communication method such as a Local Area Network (LAN) or the Internet.

[0024] The information terminal 40 is a device that accesses the server 30 and provides services offered by the server 30 to the learner 80 via a browser 43. Examples of such devices include a smartphone, a tablet, or a personal computer. The information terminal 40 is equipped with a speaker 41 and a microphone 42, and further includes a processor, memory, input device, display device, and communication device (not shown), and the processor executes software programs. The microphone 42 can acquire the voice of the learner 80 who is in front of the information terminal 40. The speaker 41 can output voice to the learner 80. Figure 3 is a flowchart of the dialogue learning process by the learning support system. The dialogue learning process is the process in which the learning support system 10 provides dialogue learning services to the learner 80.

[0025] Referring to Figure 3, first, in step S101, the dialogue unit 12 initiates a dialogue with the learner 80 using an avatar instructor. The dialogue is branched, with a certain number of dialogue scenarios prepared in advance, which branch depending on the development of the conversation with the learner 80. Based on these scenarios, the generative artificial intelligence 81 is used to generate utterances for the avatar instructor to converse with the learner 80. The dialogue begins, for example, with the avatar instructor asking the learner 80 to explain a predetermined learning item. As an example, the avatar instructor might say, "Mr. / Ms. XX, please explain the term xxx. If possible, please give examples of how to use the term or explain it clearly using metaphors." The dialogue then proceeds with the learner 80 explaining the learning item in response to this request.

[0026] The comprehension assessment unit 16 continuously measures paralanguage contained in learner 80's utterances while a dialogue takes place and learner 80 is explaining the learning material. Paralanguage includes, for example, speech rate, number of fillers, term selection, number of silences, word endings, and speech waveform frequencies.

[0027] Speech rate is an indicator based on the speed of speech, and one example is the number of utterance units per unit of time in an utterance. Utterance units include, for example, words and moras. Speech rate can be expressed as, for example, the number of moras per second or the number of words per minute. Filler count is an indicator based on the number of fillers inserted between utterances, and one example is the number of fillers that appear per unit of time in an utterance. Fillers include, for example, "um," "uh," and "well." Terminology selection is whether technical terms are used correctly. Silence count is an indicator based on the number of silences that occur between utterances, and one example is the total number of silences in a series of explanatory utterances. Silence refers to a state in which there is no utterance for a predetermined period of time or longer. If the period of silence continues for a certain amount of time or longer, it is judged as silence, and the number of such silences is counted. Sentence ending style is the style of the ending of a sequence of utterances. For example, it is judged by whether the ending is clear or unclear. Speech waveform frequency is the waveform or frequency of spoken speech. Speech frequency increases as emotions intensify. Figure 4 is a conceptual diagram illustrating interactive learning using a learning support system. It shows an avatar instructor interacting with a learner. The information terminal 40 displays an avatar instructor 61 and a score display area 62.

[0028] The avatar instructor's (61) voice (63) is output from the speaker (41) of the information terminal (40). The learner's (80) voice (64) is acquired by the microphone (42) and taken into the information terminal (40). This enables a dialogue between the avatar instructor (61) and the learner (80). The score display area (62) shows the accuracy of the learner's (80) explanation of the learning material in real time.

[0029] Returning to Figure 3, in step S102, the accuracy determination unit 13 measures the accuracy of the explanation from the learner's utterance based on the accuracy evaluation method information.

[0030] Figure 5 shows an example of accuracy evaluation method information (points). Accuracy evaluation method information 71a is information for calculating the accuracy of the explanation of the learned material. The method for evaluating accuracy varies depending on the type of learning material being evaluated. The evaluation method employs a point-based system where points are added for each prescribed explanation that is provided. The types of learning material include vocabulary explanations, the purpose of the system, basic information (5W1H), basic information (chronological order), system comparisons, case studies, and case law knowledge.

[0031] A glossary of terms describes the meaning of terms used in the laws that define the system. The evaluation method for glossary of terms is as follows: (1) If you can accurately explain the meaning of the technical terms, you can earn up to 80 additional points. (2) Furthermore, up to 20 points will be added if examples of how to use the technical terms are provided or if metaphors are used to explain them clearly.

[0032] The purpose of the system is the reason for which the system was established. The method for evaluating the purpose of the system is as follows: (1) If you can accurately explain the purpose of the system, you can earn up to 80 additional points. (2) Furthermore, up to 20 points will be added if the purpose of the system is explained with specific examples.

[0033] The basic information (5W1H) concerns "who," "to whom," "when," "what," and "how" related to the system. The evaluation method for the basic information (5W1H) is as follows. (1) If you can explain the outline of the system in the order of "who," "to whom," "when," "what," and "how," you will be awarded points for each item, up to a maximum of 5 x 15 = 75 points. (2) If you can explain these points in relation to the purpose of the system, you can earn up to 25 additional points.

[0034] Basic matters (time series) are multiple items that have a chronological order. The method for evaluating basic matters (time series) is as follows: (1) Points will be awarded for each item if you can explain multiple items that have a chronological order that outlines the system, up to a maximum of 75 points. (2) If you can explain those matters in relation to the purpose of the system, you will receive up to 25 additional points.

[0035] The system comparison involves contrasting two systems (System 1 and System 2). The evaluation method for the system comparison is as follows: (1) Points will be added for each point on which you can compare and explain the differences between System 1 and System 2. A maximum of 75 points will be added if you can compare and explain the differences for all points. (2) If the explanation of the difference is based on the purpose of the system and includes an explanation of the reason, a predetermined number of points will be added for each point. If an explanation of the reason is given for all points, a maximum of 25 points will be added.

[0036] Case studies are problems that require students to draw conclusions about a given case. The evaluation method for case studies is as follows: (1) You can earn up to 25 points if you can accurately explain what the case study presented by the avatar instructor is asking. (2) If you can correctly explain your approach to solving the case problem, you will receive up to 25 additional points. (3) If you can explain the conclusion you reached after solving the case problem, you will receive up to 50 additional points.

[0037] Case law knowledge is knowledge related to case law. The method for evaluating case law knowledge is as follows: (1) You can earn up to 25 points if you can explain the background of the case in question. (2) Points will be added for each point of contention in the case if you can explain it. A maximum of 25 points will be added if you can explain all points of contention. (3) You can earn up to 50 additional points if you can explain the judgments that have been rendered on the issues at issue.

[0038] Based on the above evaluation method, for each learning item, multiple words that should be included in the learner's (80) explanation of that learning item, or multiple words and the order in which those words appear, are predetermined. By comparing the predetermined words with the words that appear in the learner's (80) explanation of that learning item, it becomes possible to evaluate the learner's (80) explanation of that learning item by adding points. For example, if multiple words are predetermined, points can be added each time one of those words appears in the utterance. Also, for example, if multiple words and the order in which those words appear are predetermined, points can be added each time the predetermined words appear in the utterance in the predetermined order.

[0039] Alternatively, a model explanatory text could be prepared in advance, containing multiple words or words in a predetermined order, and points could be awarded based on the similarity (distance between vectors) between the learner's explanatory text vector and the text vector representing the model explanatory text. Returning to Figure 3, in step S103, the accuracy determination unit 13 updates the display in the score display area 62 with the newly calculated accuracy.

[0040] Figure 6 shows an example of the display in the score display area. As shown in Figure 6, the score display area 62 displays a real-time accuracy value and its graph, which are updated sequentially in conjunction with the dialogue. The entertainment value of being able to see the score increase as one demonstrates correct understanding during the explanation can increase learners' motivation.

[0041] Returning to Figure 3, if the explanation of the learning items is not completed in step S104, the process returns to step S102 and the accuracy measurement is repeated. If the explanation of the learning items is completed, in step S105, the accuracy determination unit 13 weights the accuracy according to the weights corresponding to the learning items.

[0042] Figure 7 shows an example of accuracy evaluation method information (weighting). Accuracy evaluation method information 71b is information for adding weight to the accuracy of the explanation of the learning material. The difficulty level of the learning material varies depending on its type. Therefore, weighting is applied according to the difficulty level, and the difficulty level is reflected in the accuracy evaluation.

[0043] As mentioned above, the types of learning material include vocabulary explanations, the purpose of the system, basic matters (5W1H), basic matters (chronological order), system comparisons, case problems, and case law knowledge. Here, the value of the vocabulary explanation is multiplied by a weight of 1, the value of the purpose of the system is multiplied by a weight of 2, the value of the basic matters (5W1H) is multiplied by a weight of 4, the value of the basic matters (chronological order) is multiplied by a weight of 4, the value of the system comparison is multiplied by a weight of 6, the value of the case problems is multiplied by a weight of 8, and the value of the case law knowledge is multiplied by a weight of 10. Returning to Figure 3, in step S106, the comprehension determination unit 16 calculates the level of comprehension from the measured paralinguistic information based on the comprehension evaluation method information. Figure 8 shows an example of information on methods for evaluating comprehension.

[0044] Information 72 on the comprehension evaluation method defines a method for calculating comprehension for each paralanguage to be analyzed. Specifically, the method for calculating the index value of comprehension for each paralanguage is defined in Figure 8. As mentioned above, the paralinguistic parameters measured include speech rate, filler count, term selection, silence count, word endings, and speech waveform frequency.

[0045] For speech rate, if the speech rate is above the threshold, the index value is A; if the speech rate is below the threshold, the index value is B (A and B are natural numbers such that A > B). For filler count, if the number of fillers is below the threshold, the index value is C; if the number of fillers is above the threshold, the index value is D (C and D are natural numbers such that C > D). For terminology selection, if the specialized knowledge is used correctly, the index value is E; if the specialized knowledge is not used correctly, the index value is F (E and F are natural numbers such that E > F). For silence count, if the number of silence counts is below the threshold, the index value is G; if the number of silence counts is above the threshold, the index value is H (G and H are natural numbers such that G > H). For word endings, if the number of times the word ending was unclear is below the threshold, the index value is I; if the number of times was above the threshold, the index value is J (I and J are natural numbers such that I > J). For audio waveform frequencies, the learner's emotional value L (where L is a natural number), measured based on the audio waveform, is used as the index value. Here, as an example, the sum of the index values ​​calculated by each paralanguage is used as the level of understanding.

[0046] Returning to Figure 3, in step S107, the comprehensive evaluation unit 19 calculates a proficiency level indicating how well the learner has mastered the learned material, based on accuracy and comprehension. The method for calculating proficiency is not particularly limited, but as an example, it may be calculated using the following formula (1). This formula is based on the idea that depth of understanding is taken into account on the premise that there is accurate understanding.

[0047]

number

[0048] Here, we have shown an example of calculating proficiency that takes into account the depth of understanding by adding the level of understanding to the weighted accuracy when the accuracy before weighting is above a certain value, but this is not the only way. As another example, one could calculate proficiency that takes into account the depth of understanding by multiplying the accuracy after weighting by the level of understanding when the accuracy before weighting is above a certain value. Furthermore, for example, weights could be applied not only to accuracy but also to understanding, using weights corresponding to the difficulty level.

[0049] Next, in step S108, the ranking unit 21 determines the learner's ranking based on their proficiency level and presents the learner with information regarding that ranking. The ranking unit 21 constantly records the latest proficiency levels of all learners and determines the learner's ranking among all learners based on the newly calculated proficiency level.

[0050] Next, in step S109, the growth visualization unit 22 records the number of times the learning has been performed up to this point and the proficiency level calculated for this session, corresponding to the learning items that were taught in this session. The unit then displays the changes in proficiency level with each subsequent session in a visually understandable way. The learner 80 can confirm their own learning progress by comparing it with others, and continuous learning is effectively supported.

[0051] Figure 9 shows an example of a growth graph displaying changes in proficiency. Growth graph 65 is a line graph showing proficiency levels for each session in which learning was conducted through teaching, as an example. Learner 80 can visually confirm that their proficiency is improving with each learning session, which helps maintain or improve their motivation.

[0052] Returning to Figure 3, in step S110, the feedback unit 23 provides a summary of the learner's learning, such as encouragement, example presentations, and advice, tailored to the learner's accuracy, depth, and proficiency in the learning material.

[0053] For example, the feedback unit 23 determines whether or not to provide the learner 80 with an exemplary explanation based on one or more of the accuracy, comprehension, and proficiency levels. If it determines that the learner 80 should be provided with an exemplary explanation, it provides the learner 80 with an exemplary explanation via video and audio from an avatar instructor.

[0054] Figure 10 shows an example of the logic for determining whether or not to present a model explanation. In this example, a threshold is set for the accuracy before weighting; if the accuracy before weighting is above the threshold, it is judged as "high," and if it is below the threshold, it is judged as "low." Similarly, a threshold is set for the level of comprehension; if the level of comprehension is above the threshold, it is judged as "high," and if it is below the threshold, it is judged as "low." As shown in the shaded area of ​​Figure 10, if either the accuracy before weighting or the level of comprehension is "low," it is decided that a model explanation should be presented to learner 80. On the other hand, as shown in the unshaded area of ​​Figure 10, if both the accuracy before weighting and the level of comprehension are "high," it is decided that there is no need to present a model explanation to learner 80. In that case, for example, encouraging words indicating that the learner has understood well may be provided. When it is determined that it is desirable for learner 80 to improve the accuracy and depth of their understanding in their own learning through teaching, the learning effect of learner 80 can be enhanced by a user experience that teaches learner 80 exemplary explanations and methods through dialogue.

[0055] Furthermore, the feedback unit 23 provides encouraging words to the learner 80 in the dialogue based on at least one of accuracy, comprehension, and proficiency, thereby enabling the learner 80 to receive encouragement as their learning progresses and effectively supporting continuous learning.

[0056] The embodiments of the present invention described above are illustrative for the purpose of explaining the present invention and are not intended to limit the scope of the present invention to those embodiments only. Those skilled in the art can implement the present invention in various other forms without departing from the spirit of the invention.

[0057] Furthermore, this embodiment includes the following items. However, the items included in this embodiment are not limited to those listed below.

[0058] (Item 1) A dialogue unit that engages in a dialogue with the learner so that the learner explains the prescribed learning items, A precision determination unit that determines the accuracy of the explanation in the aforementioned dialogue, A comprehension level determination unit that determines the level of understanding of the learner regarding the aforementioned learning material, A learning support system that has the following features. According to this, in a learning method where one learns by teaching, the accuracy and depth of understanding are judged from the learner's utterances, making it possible to provide learning support that evaluates not only whether the explanation is accurate but also the depth of understanding.

[0059] (Item 2) In the learning support system described in item 1, The comprehension determination unit calculates one or more paralinguistic indicators from the learner's utterances in the dialogue, and calculates the comprehension level based on the paralinguistic indicators. This allows for accurate measurement of the depth of learners' understanding of learned material as expressed in paralinguistic statements in their speech.

[0060] (Item 3) In the learning support system described in item 2, The paralinguistic indicators include one or more of the following: speech rate, which is an indicator based on the speed of speech; filler count, which is an indicator based on the number of fillers inserted between utterances; silence count, which is an indicator based on the number of silences that occur between utterances; and word endings, which are the endings of a sequence of utterances.

[0061] (Item 4) In the learning support system described in item 2, The accuracy determination unit converts the learner's spoken audio into text and calculates the accuracy by adding points based on the comparison of words appearing in the text with words predetermined for the learning material. This allows for an accurate measurement of how well learners understand the material by evaluating the text generated from audio recordings of learners explaining the material.

[0062] (Item 5) In the learning support system described in item 4, The aforementioned learning items include: explanations of terms used in the laws establishing the system; the purpose of the system; basic matters concerning the system; a comparison of the first and second systems; case problems requiring conclusions on given cases; and case law knowledge. The accuracy determination unit determines the accuracy as follows: Regarding the explanation of the aforementioned terms, points will be awarded if the meaning of the terms is explained correctly, and further points will be awarded if the usage of the terms is illustrated, or if a metaphor is used in the explanation of the meaning of the terms. Regarding the purpose of the aforementioned system, points will be awarded if the purpose of the system is explained correctly, and further points will be awarded if the purpose of the system is explained with specific examples. Regarding the aforementioned basic matters, points will be awarded for each of the aforementioned matters if they can be explained in the prescribed order, and further points will be awarded if the explanation is linked to the purpose of the system. Regarding the comparison of the aforementioned systems, points will be awarded for each point on which the differences between the first and second systems should be compared can be explained, and further points will be awarded if the explanation of the differences includes an explanation of the reasons based on the purpose of the respective systems. For the aforementioned case problem, points will be awarded if the student can correctly explain what the given problem is asking, further points will be awarded if the student can correctly explain the problem and the approach to solving it, and further points will be awarded if the student can explain the conclusion reached after solving the problem. Regarding the aforementioned case law knowledge, points will be awarded if you can explain the background of the case, further points will be awarded if you can explain the issues in the case, and even further points will be awarded if you can explain the judgment rendered on those issues.

[0063] (Item 6) In the learning support system described in item 5, The accuracy determination unit updates the accuracy simultaneously with the dialogue and presents the updated accuracy to the learner. According to this, the entertainment value of the user experience of the dialogue itself, where users can see their score increase by demonstrating correct understanding within the explanation, can increase learners' motivation.

[0064] (Item 7) In the learning support system described in item 4, The system further includes a comprehensive evaluation unit that calculates a level of proficiency indicating how well the learner has mastered the learned material, based on the accuracy and comprehension levels.

[0065] (Item 8) In the learning support system described in item 7, The accuracy determination unit calculates a weighted accuracy by further weighting the unweighted accuracy, which is calculated based on the comparison of words appearing in the text converted from the learner's spoken audio with words predetermined for the learning item, with weights corresponding to the difficulty level of the learning item. The comprehensive determination unit calculates the proficiency level by adding the comprehension level to the weighted accuracy level if the accuracy before weighting is above a predetermined threshold, and if the accuracy before weighting is below the threshold, the weighted accuracy level is used as the proficiency level. According to this approach, by taking into account the depth of understanding expressed in the paralanguage only when the accuracy of understanding expressed in the audio-text reaches a certain level, it becomes possible to effectively support learning at an appropriate level of proficiency.

[0066] (Item 9) In the learning support system described in item 7, The system further includes a feedback unit that determines whether or not to instruct the learner with an exemplary explanation based on one or more of the accuracy, understanding, and proficiency levels, and if it determines that the learner should be instructed with an exemplary explanation, provides the exemplary explanation to the learner in the dialogue. This allows for a user experience that teaches learners exemplary explanations and methods in a dialogue, which is desirable when learners want to improve the accuracy and depth of their understanding in their own learning.

[0067] (Item 10) In the learning support system described in item 7, The system further includes a growth visualization unit that records the number of times learning has been performed by teaching the aforementioned learning item, the level of proficiency calculated in each session, and displays the changes in the level of proficiency with each subsequent session in a visually understandable manner. According to this, it is possible to effectively support continuous learning by enabling learners to visually confirm their own learning progress.

[0068] (Item 11) In the learning support system described in item 7, The system further includes a ranking unit that determines the learner's ranking based on their proficiency level and presents the learner with information regarding their ranking. According to this approach, continuous learning can be effectively supported by enabling learners to confirm their own learning progress through comparison with others.

[0069] (Item 12) In the learning support system described in item 7, The system further includes a feedback unit that provides words of encouragement to the learner in the dialogue based on at least one of the accuracy, comprehension, and proficiency. According to this, continuous learning can be effectively supported by providing learners with encouragement as they progress through their studies.

[0070] (Item 13) Computers The teacher engages in dialogue with the learner so that the learner explains the designated learning items. The accuracy of the explanation in the aforementioned dialogue is determined, The degree of understanding of the learner regarding the aforementioned learning material is determined. A learning support method for putting something into practice.

[0071] (Item 14) On the computer, The teacher engages in dialogue with the learner so that the learner explains the designated learning items. The accuracy of the explanation in the aforementioned dialogue is determined, The degree of understanding of the learner regarding the aforementioned learning material is determined. A learning support program that helps people accomplish tasks. [Explanation of Symbols]

[0072] 10...Learning support system, 12...Dialogue unit, 13...Accuracy judgment unit, 14...Speech analysis unit, 15...Text evaluation unit, 16...Comprehension judgment unit, 17...Paralinguistic measurement unit, 18...Paralinguistic evaluation unit, 19...Overall judgment unit, 20...Motivation processing unit, 21...Ranking unit, 22...Growth visualization unit, 23...Feedback unit, 30...Server, 31...Processor, 32...Main memory, 33...Storage device, 34...Communication device, 35...Input device, 36...Display device, 37...Bus, 40...Information terminal, 41...Speaker, 42...Microphone, 43...Browser, 61...Avatar instructor, 62...Score display area, 63...Spoken voice, 64...Spoken voice, 65...Growth graph, 71a...Accuracy evaluation method information, 71b...Accuracy evaluation method information, 72...Comprehension evaluation method information, 80...Learner, 81...Generative artificial intelligence, 82...Communication network

Claims

1. A dialogue unit that engages in a dialogue with the learner so that the learner explains the prescribed learning items, A precision determination unit that determines the accuracy of the explanation in the aforementioned dialogue, A comprehension level determination unit that determines the level of understanding of the learner regarding the aforementioned learning material, A learning support system that has the following features.

2. The comprehension determination unit calculates one or more paralinguistic indicators from the learner's utterances in the dialogue, and calculates the comprehension level based on the paralinguistic indicators. The learning support system according to claim 1.

3. The paralinguistic indicators include one or more of the following: speech rate, which is an indicator based on the speed of speech; filler count, which is an indicator based on the number of fillers inserted between utterances; silence count, which is an indicator based on the number of silences that occur between utterances; and word endings, which are the endings of a sequence of utterances. The learning support system according to claim 2.

4. The accuracy determination unit converts the learner's spoken audio into text and calculates the accuracy by adding points based on the comparison of words appearing in the text with words predetermined for the learning material. The learning support system according to claim 2.

5. The aforementioned learning items include: explanations of terms used in the laws establishing the system; the purpose of the system; basic matters concerning the system; a comparison of the first and second systems; case problems requiring conclusions on given cases; and case law knowledge. The accuracy determination unit determines the accuracy as follows: Regarding the explanation of the aforementioned terms, points will be awarded if the meaning of the terms is explained correctly, and further points will be awarded if the usage of the terms is illustrated, or if a metaphor is used in the explanation of the meaning of the terms. Regarding the purpose of the aforementioned system, points will be awarded if the purpose of the system is explained correctly, and further points will be awarded if the purpose of the system is explained with specific examples. Regarding the aforementioned basic matters, points will be awarded for each of the aforementioned matters if they can be explained in the prescribed order, and further points will be awarded if the explanation is linked to the purpose of the system. Regarding the comparison of the aforementioned systems, points will be awarded for each point on which the differences between the first and second systems should be compared can be explained, and further points will be awarded if the explanation of the differences includes an explanation of the reasons based on the purpose of the respective systems. For the aforementioned case problem, points will be awarded if the student can correctly explain what the given problem is asking, further points will be awarded if the student can correctly explain the problem and the approach to solving it, and further points will be awarded if the student can explain the conclusion reached after solving the problem. Regarding the aforementioned case law knowledge, points will be awarded if you can explain the background of the case, further points will be awarded if you can explain the issues in the case, and even further points will be awarded if you can explain the judgment rendered on those issues. The learning support system according to claim 4.

6. The accuracy determination unit updates the accuracy simultaneously with the dialogue and presents the updated accuracy to the learner. The learning support system according to claim 5.

7. The system further includes a comprehensive evaluation unit that calculates a proficiency level indicating how well the learner has mastered the learned material, based on the accuracy and understanding levels. The learning support system according to claim 4.

8. The accuracy determination unit calculates a weighted accuracy by further weighting the unweighted accuracy, which is calculated based on the comparison of words appearing in the text converted from the learner's spoken audio with words predetermined for the learning item, with weights corresponding to the difficulty level of the learning item. The comprehensive determination unit calculates the proficiency level by adding the comprehension level to the weighted accuracy level if the accuracy before weighting is above a predetermined threshold, and if the accuracy before weighting is below the threshold, the weighted accuracy level is used as the proficiency level. The learning support system according to claim 7.

9. The system further includes a feedback unit that determines whether or not to instruct the learner with an exemplary explanation based on one or more of the accuracy, understanding, and proficiency, and if it determines that the learner should be instructed with an exemplary explanation, provides the exemplary explanation to the learner in the dialogue. The learning support system according to claim 7.

10. The system further includes a growth visualization unit that records the number of times learning has been performed by teaching the aforementioned learning item, the level of proficiency calculated in each session, and displays the changes in the level of proficiency with each subsequent session in a visually accessible manner. The learning support system according to claim 7.

11. The system further includes a ranking unit that determines the learner's ranking based on their proficiency level and presents the learner with information regarding their ranking. The learning support system according to claim 7.

12. The system further includes a feedback unit that provides words of encouragement to the learner in the dialogue based on at least one of the accuracy, understanding, and proficiency. The learning support system according to claim 7.

13. Computers The teacher engages in dialogue with the learner so that the learner explains the designated learning items. The accuracy of the explanation in the aforementioned dialogue is determined, The degree of understanding of the learner regarding the aforementioned learning material is determined. A learning support method for putting something into practice.

14. On the computer, The teacher engages in dialogue with the learner so that the learner explains the designated learning items. The accuracy of the explanation in the aforementioned dialogue is determined, The degree of understanding of the learner regarding the aforementioned learning material is determined. A learning support program that helps people accomplish tasks.

Images