Learning support device, learning support system, learning support method and program

Abstract

To provide a device for supporting learning of users by generating explanations for answers to problems.SOLUTION: A learning support device 200 includes: a transmitting / receiving unit 210 that receives a problem 10 and an answer 20 to the problem input by a user from a user terminal 100, transmits the problem and answer to generative AI 300, after transmitting the problem and answer, further receives a question 30 input by the user from the user terminal and transmits the question to the generative AI; and a generation unit 220 that receives an answer 50 to the question from the generative AI and generates an explanation 40 for the user based on the answer. Thereby, the learning support device can input the answer to the problem as well as the problem, to the generative AI, then further input the question from the user to the generative AI, and generate the explanation for the user based on the answer generated by the generative AI, thereby answering the user's question, the thing that the user does not understand (a query).SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a learning support device, a learning support system, a learning support method, and a program that support a user's learning by generating an explanation for an answer to a question. [Background technology]

[0002] In learning, explanations of problems are important for deepening understanding. However, explanations are sometimes omitted due to space limitations, and often insufficient explanations are obtained. Even if a question is sent to a generation AI to generate an explanation, it is difficult to obtain an explanation that deepens the user's understanding. Here, Non-Patent Document 1 states that the March 2023 version of GPT-4 (registered trademark) showed an accuracy of 84% in distinguishing prime numbers from composite numbers, while the June 2023 version showed an accuracy of 51% in distinguishing prime numbers from composite numbers, indicating that the operation of large-scale language model services may change significantly in a relatively short period of time. [Prior art document] [Non-patent literature] [Non-Patent Document 1] Chen et al. "How Is ChatGPT's Behavior Changing over Time?", arXiv:2307.09009 [cs.CL], July 18, 2023 Summary of the Invention [Means for solving the problem]

[0003] In a first aspect of the present invention, there is provided a learning support device that supports a user's learning by generating an explanation for an answer to a question, the learning support device comprising: a transceiver unit that receives a question and the answer entered by a user from a user terminal, transmits the question and the answer to a generation AI, and after transmitting the question and the answer, further receives a question entered by the user from the user terminal and transmits the question to the generation AI; and a generation unit that receives the answer to the question from the generation AI and generates an explanation for the user based on the answer.

[0004] In a second aspect of the present invention, there is provided a system comprising the problem explanation device of the first aspect, the user terminal, and the generation AI.

[0005] In a third aspect of the present invention, there is provided a learning support method for supporting a user's learning by generating an explanation for an answer to a question, the learning support method comprising the steps of receiving a question and the answer input by a user from a user terminal and transmitting the question and the answer to a generation AI, and after transmitting the question and the answer, receiving a question input by the user from the user terminal and transmitting the question to the generation AI, and receiving an answer to the question from the generation AI and generating an explanation for the user based on the answer.

[0006] In a fourth aspect of the present invention, a program is provided that causes a computer to execute the following steps to generate an explanation for an answer to a question: receiving a question and the answer to the question input by a user from a user terminal, and sending the question and the answer to a generation AI; after sending the question and the answer, receiving a question input by the user from the user terminal and sending the question to the generation AI; and receiving an answer to the question from the generation AI, and generating an explanation for the user based on the answer.

[0007] The above summary of the invention does not list all of the features of the present invention. Also, subcombinations of these features may also be inventions. [Brief description of the drawings]

[0008] [Figure 1] 1 shows a configuration of a learning support system according to an embodiment of the present invention. [Diagram 2] 1 shows the operation flow of the learning support system. [Diagram 3] 13 shows an example of a user terminal screen at the start of an operation. [Figure 4] 1 shows an example of a user terminal screen when a question and an answer are sent (before the question is sent). [Figure 5A] Here is an example of the problem: [Figure 5B] An example of an answer is shown below. [Figure 6] The detailed flow of sending and receiving questions and answers is shown below. [Figure 7] 1 shows an example of a user terminal screen when a question and an answer are sent (the state after the question is sent but before the answer is sent). [Figure 8A] 13 shows an example of a user terminal screen when a question and an answer are sent (status after the answer is sent). [Figure 8B] 1 shows an example of a user terminal screen when a question and answer are being sent (when the answer is not at hand). [Figure 9] 13 shows an example of a user terminal screen when a question is sent. [Figure 10] An example of a question is shown below. [Figure 11] An example of a response is shown below. [Figure 12] 1 shows a detailed flow of generating an explanation in question answering. [Figure 13] Here is an example of several key points: [Figure 14A] An example of an explanation is shown below. [Figure 14B] Here is an example of an explanation of the different generation methods: [Figure 15] 13 shows an example of a user terminal screen when an explanation for a question is received. [Figure 16] 13 shows an example of a user terminal screen when an explanation for an additional question is received. [Figure 17] The operational flow of the learning support system when selecting key points is shown below. [Figure 18] The operational flow of the learning support system when grading answers is shown below. [Figure 19] 13 shows an example of a user terminal screen when a grading request is made. [Figure 20] An example of an answer is shown below. [Figure 21] 13 shows an example of a user terminal screen when receiving the scoring results and explanations. [Figure 22] 1 shows an example of a computer configuration. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0010] 1 shows the configuration of a learning support system 1 according to this embodiment. The learning support system 1 is a system that generates highly accurate explanations in response to questions from users and improves the learning effect of the users, and includes a user terminal 100, a learning support device 200, a generating artificial intelligence (generating AI) 300, and an optical character recognition device (OCR device) 400. These are connected to each other so as to be able to communicate with each other via a network 500 such as the Internet.

[0011] The user terminal 100 is a communication terminal owned or used by a user, such as a smartphone, a tablet terminal, or a personal computer. A plurality of user terminals 100 may be included in the learning support system 1, each having individual individual recognition information, and may transmit individual recognition information such as an ID, a tag, or a user name during communication. This allows a plurality of users to independently communicate with the learning support device 200 using their respective user terminals 100. In this embodiment, the configuration and functions of the learning support system 1 will be described with a focus on one user terminal 100 used by one user.

[0012] The user terminal 100 includes a central processing unit (CPU), a communication device, and a storage device (all not shown). The CPU executes a dedicated program to realize a question and explanation recording function. The dedicated program is stored in, for example, a ROM (not shown) and read by the CPU, or is stored in a storage medium such as an SD card and read by the CPU using a reading device (not shown), or is stored in a cloud (multiple distributed servers or multiple subsystems, etc.) and read by the CPU from the cloud via a communication device and deployed in RAM to be started. The communication device is a means for mutually communicating with the learning support device 200 and the OCR device 400 via the network 500, and can communicate using a protocol such as TCP / IP, for example. The communication device may adopt either a wired communication method or a wireless communication method. The storage device is a storage device such as a NAND type flash memory that stores the history of the questions 10, answers 20, questions 30, and explanations 40, which will be described later. The user terminal 100 can communicate with the learning support device 200 via a network 500 and provide the learning support device 200 with the problems 10, answers 20, and questions 30 required for generating an explanation.

[0013] The user terminal 100 may have a photographing function such as a camera. In such a case, the user can use the user terminal 100 to convert the questions 10, the answers 20, and the questions 30 into image information using the photographing function and provide the image information to the learning support device 200. The user may include each of the questions 10, the answers 20, and the questions 30 in separate image information and provide the image information by specifying the area of ​​each image information, or may store the image information in the user terminal 100 after photographing and specifying the area in advance, and read it out to provide it. Also, two or more of the questions 10, the answers 20, and the questions 30 may be included in one image information and provided by specifying the area of ​​each image information.

[0014] The learning support device 200 is a computer device that uses the generation AI 300 to generate a highly accurate explanation in response to a user's question. The learning support device 200 includes a central processing unit (CPU), a communication device, and a storage device (all not shown). The CPU executes a dedicated program to realize the explanation generation function. The dedicated program is stored in, for example, a ROM (not shown), and is read by the CPU, or is stored in a storage medium such as a CD-ROM, and is read by the CPU using a reading device (not shown), or is stored in a cloud (multiple distributed servers or multiple subsystems, etc.), and is read by the CPU from the cloud via the communication device and deployed in RAM to be started. The communication device is a means for mutually communicating with the user terminal 100, the generation AI 300, and the OCR device 400 via the network 500, and can communicate using a protocol such as TCP / IP, for example. The communication device may employ either a wired communication method or a wireless communication method. The storage device is a storage device such as a hard disk drive (HDD) that stores various information such as the problem 10, the answer 20, the question 30, and the explanation 40. In this embodiment, the storage device is provided in the learning support device 200. The learning support device 200 communicates with the generation AI 300 via the network 500 to provide the problem 10, the answer 20, and the question 30 required for generating an explanation to the generation AI 300, and communicates with the user terminal 100 via the network 500 to provide the generated explanation 40 to the user terminal 100. An external storage device (not shown) may be used as the storage device.

[0015] The generation AI 300 is an AI that learns patterns and relationships based on collected training data and generates content. In this embodiment, a text generation AI is used for the generation AI 300, but this is not necessary. The generation AI 300 may use a commercial generation AI, and examples of commercial text generation AI include GPT-4 (registered trademark), Llama2, and PaLM2. By using a commercial generation AI, preparation such as collecting training data is not required, and the system can be easily constructed.

[0016] The OCR device 400 is a device that extracts characters from image information and converts them into text information. The OCR device 400 may be a device equipped with commercial OCR software, a commercial OCR device, or a commercial online OCR service, and examples of the commercial OCR software or online OCR service include SmartRead (registered trademark), Smart OCR (registered trademark), and Seisho (registered trademark). In this embodiment, the OCR device 400 is connected via a network 500, but is not limited to this and may be incorporated into the learning support device 200.

[0017] Fig. 2 illustrates the operation flow of the learning support system 1 according to this embodiment. Fig. 3 shows an example of the screen display of the user terminal 100 at the start of operation. Three options are displayed on the screen of the user terminal 100: "Take a photo of a question," "Ask a question," and "Grade." When the user selects "Take a photo of a question" on the user terminal 100, "Request explanation" is executed, and the flow begins.

[0018] In step S10, the user photographs the question 10 and the answer 20 with the user terminal 100, and instructs the user terminal 100 to transmit the question 10 and the answer 20. As shown in FIG. 4, a message 1001 "Take a picture of the question you don't understand or select an image of the question" is displayed on the screen of the user terminal 100 to prompt the user to transmit the question 10. In response to this, the user photographs the question 10 and the answer 20.

[0019] FIG. 5A shows an example of question 10. Question 10 is, for example, a question found in a textbook or a workbook, and the subject is not particularly limited. Here, the user may generate image information of question 10 using the camera of the user terminal 100, and may cut out a portion including question 10 from the captured image information. Note that image information of question 10 that was previously generated and stored in the user terminal 100 may be read out and used.

[0020] In this example, question 10 is a question about permutations in mathematics. The main question is "Make a permutation using all the letters of something. In this case, how many of the following are there?", and the main question is divided into five sub-questions: "(1) s and g are at both ends," "(2) o, m, and e are adjacent," "(3) o and m are not adjacent," "(4) h, i, n, and g are in the same order," and "(5) s is to the left of t and h is to the right of t."

[0021] Although the subject or field of question 10 is not limited, if the question includes an illustration, the illustration may be transmitted to the learning support device 200 as image information and the question text as text information. Even if the user transmits question 10 to the learning support device 200 as image information, the learning support device 200 may delete the information about the illustration if the solution can be derived from the question text alone without the illustration. If the question cannot be transmitted all at once because it is long, for example, the question may be transmitted and received in multiple batches.

[0022] In this embodiment, the questions 10 are generated as image information, but they may be generated as text information or audio information. In such a case, the user terminal 100 may display a screen to prompt the user to generate the questions 10 as text information or audio information.

[0023] FIG. 5B shows an example of the answer 20. The answer 20 is an answer to the problem 10, and is written in, for example, an answer collection or an explanation collection that accompanies a textbook or a problem collection, and the subject is not limited. Here, the user may generate image information of the answer 20 using the camera of the user terminal 100, and may cut out a portion including the answer 20 from the captured image information. In addition, image information of the answer 20 that was generated in the past and stored in the user terminal 100 may be read out and used.

[0024] In this example, answer 20 is the solution to problem 10, which is about permutations in mathematics. As the solution to problem 10, answers (1) and (2) are shown, and each is explained as follows: "(1) There are two ways to put s and g. The other letters can be arranged normally, so there are 2 x 7! = 10080 (ways)," and "(2) If o, m, and e are considered as one, the whole can be considered as seven letters. There are 7! ways to arrange them, and for each of those, there are 3! ways to swap o, m, and e, so there are 7! x 3! = 30240 (ways)."

[0025] Answer 20 only needs to include the part of the answer that the user wants to ask a question about, and does not need to include answers to all of the sub-questions included in the main question when the user asks a question about a sub-question. In the case of an explanation with an inserted figure, the figure information will be lost if information other than image information is transmitted, so the figure may be transmitted to learning support device 200 as image information and the question text as text information. Even if the user transmits answer 20 to learning support device 200 as image information, learning support device 200 may delete the figure information if it is not necessary.

[0026] In this embodiment, the answer 20 is generated as image information, but it may be generated as text information or audio information. In such a case, the user terminal 100 may display a screen to prompt the user to generate the answer 20 as text information or audio information.

[0027] When the user operates the user terminal 100 (eg, by tapping the screen), the generated questions 10 and answers 20 are transmitted from the user terminal 100 to the learning support device 200.

[0028] In step S100, the learning support device 200 receives the questions 10 and the answers 20 from the user terminal 100. Fig. 6 shows a detailed flow of step S100.

[0029] In step S110, the transmitting / receiving unit 210 receives the question 10 (see FIG. 5A) from the user terminal 100. As shown in FIG. 7, when the learning support device 200 receives the question 10 from the user terminal 100, it transmits a message 1003 "Take a picture of your answer or select an image of your answer" to prompt the user terminal 100 to transmit the answer 20. Note that in FIG. 7 and other drawings showing the display screen of the user terminal 100, the message displayed on the left side of the screen of the user terminal 100 is a message transmitted from the learning support device 200 and received by the user terminal 100, and the message displayed on the right side is a message transmitted from the user terminal 100 to the learning support device 200. Furthermore, the user terminal 100 displays "Answer not at hand" and "Photograph the answer" selectable by the user.

[0030] In step S120, the transmitting / receiving unit 210 receives the answer 20 (see FIG. 5B) from the user terminal 100. As shown in FIG. 8A, when the learning support device 200 receives the answer 20 from the user terminal 100, the transmitted answer 20 is displayed on the screen.

[0031] 8B, if the user selects "answer not available" when the answer 20 cannot be transmitted from the user terminal 100, the learning support device 200 transmits a warning message 1005 "explanation accuracy may decrease if there is no answer" to the user terminal 100, which warns that the accuracy of the explanation may decrease. If the transmitting / receiving unit 210 cannot obtain the answer 20 from the user terminal 100, the learning support device 200 may search for and obtain an explanation of the same problem or a problem with a similar structure from the user's question history or the transmission history of all users recorded therein.

[0032] In step S130, the questions 10 and answers 20, which are image information, are converted into text information. Here, the transmitting / receiving unit 210 transmits the image information of the questions 10 and answers 20 to the OCR device 400. The OCR device 400 converts the image information into text information and returns it to the transmitting / receiving unit 210. If the questions 10 and answers 20 are text information, step S130 is omitted. This allows the questions 10 or answers 20 input as image information to be input to the generation AI 300 as character information, which improves the accuracy of the answers 50 compared to inputting the questions 10 or answers 20 as image information to the generation AI 300 as is, and generates a highly accurate explanation 40 for the user based on the answers 50, thereby answering the user's questions 30, i.e., the questions about the questions 10 and answers 20.

[0033] In step S140, the transmitting / receiving unit 210 transmits the question 10 and the answer 20, which are text information, to the generating AI 300. This completes step S100, and the learning support device 200 goes into a standby state. Meanwhile, the generating AI 300 receives the question 10 and the answer 20.

[0034] After the learning support device 200 goes into standby mode, when the user selects "Ask a question" on the screen of the user terminal 100 (see FIG. 3), the process proceeds to step S20. In response to this, the learning support device 200 transmits a message 1101 to the user terminal 100 prompting the user to transmit a question 30. As a result, the message 1101 "What kind of question do you have today?" is displayed on the screen of the user terminal 100, as shown in FIG.

[0035] In step S20, the user inputs the question 30 into the user terminal 100 and instructs the user terminal 100 to transmit the question 30. Here, the user creates the question 30 on the user terminal 100.

[0036] 10 shows an example of a question 30. The question 30 is created as a question based on a user's doubt about the problem 10 and the answer 20. In this embodiment, the question 30 is generated as text information, but is not limited to this and may be generated as image information or audio information.

[0037] In this example, question 30 is a question about problem 10 and answer 20, which are about permutations in mathematics. Question 30 asks about the meaning of (2) in answer 20 to problem 10, "That arrangement results in 7!". Question 30 only needs to have content that can identify which part of problem 10 or answer 20 the user is asking about. For example, question 30 may specify the number of a sub-question or the number of lines in answer 20, or it may quote the text of the part about which the user is asking.

[0038] When the user operates the user terminal 100 (eg, by tapping the screen), the created question 30 is transmitted from the user terminal 100 to the learning support device 200.

[0039] In step S200, the transmitting / receiving unit 210 transmits and receives the question 30. First, the transmitting / receiving unit 210 receives the question 30 (see FIG. 10) from the user terminal 100. In this embodiment, the question 30 is text information. If the question 30 is image information, the transmitting / receiving unit 210 converts the question 30 into text information as in step S130, and if the question 30 is voice information, it converts it into text information using built-in or online voice recognition software. Then, the transmitting / receiving unit 210 transmits the question 30, which is text information, to the generating AI 300. At this time, the transmitting / receiving unit 210 may transmit a message to the generating AI 300 saying, "Please answer the question 30 based on the question 10 and the answer 20," to instruct the generating AI 300 to create an answer to the question 30. Meanwhile, the generating AI 300 receives the question 30 and the message.

[0040] In step S30, after the generation AI 300 receives the question 30, the generation AI 300 generates an answer 50 to the question 30 based on the problem 10 and the answer 20, and transmits it to the learning support device 200. FIG. 11 shows an example of the answer 50. In this case, in response to the question 30 (see FIG. 10) of "I don't understand the meaning of 7!," the answer is "'7!' is pronounced '7 factorial.' This means multiplying all positive integers from 7 to 1. In other words, 7 x 6 x 5 x 4 x 3 x 2 x 1 = 5040." However, the answer 50 does not include an explanation of what 7! means in this problem.

[0041] In step S300, the generation unit 220 generates the explanation 40. Fig. 12 shows a detailed flow of step S300 of generating the explanation.

[0042] In step S310, the generation unit 220 receives the problem 10, the answer 20, and the answer 50 generated based on the question 30 from the generation AI 300.

[0043] In step S320, the generation unit 220 instructs the generation AI 300 to summarize multiple key points 60. The multiple key points 60 are knowledge necessary for solving the problem 10 or for understanding the answer 20. The generation unit 220 can cause the generation AI 300 to summarize multiple key points 60 of the answer 20 by inputting to the generation AI 300, for example, "Please list all the knowledge necessary to solve this problem. Also, please tell me the specific properties and theorems contained in that knowledge."

[0044] In step S40, the generation AI 300 summarizes the main points 60 and returns them to the learning support device 200.

[0045] FIG. 13 shows an example of the multiple key points 60 in the problem 10 (see FIG. 5A) and the answer 20 (see FIG. 5B). In this example, the multiple key points 60 are composed of four items: "Permutations: Permutations represent a method or pattern for arranging a set of elements in a specific order. When calculating the number of permutations, a formula is required for selecting r elements from n elements."; "Combinations: Combinations represent a method or pattern for selecting a set of elements regardless of order. When calculating the number of combinations, a formula is required for selecting r elements from n elements."; "Factorial: Factorial represents the successive product of natural numbers. The factorial of n is represented by n!. n!=n×(n-1)×(n-2)×…×2×1"; and "Permutation calculation formula: When calculating the number of permutations, the following formula is used: P(n,r)=n! / (nr)!".

[0046] In step S330, the generation unit 220 receives the multiple main points 60 returned from the generation AI 300. Note that the summary of the multiple main points 60 may be selectively skipped, and in such a case, steps S320 to S330 may be omitted.

[0047] In step S340, the generation unit 220 generates the explanation 40 by adding all or part of the main points 60 following the answer 50. As a result, not only the question 10 but also the answer 20 to the question 10 is input to the generation AI 300, and then the question 30 from the user is input to the generation AI 300, and the generation AI 300 generates the answer 50 to the question 30 based on the question 10 and the answer 20, and generates an explanation 40 for the user based on the answer 50, thereby answering the user's question 30, i.e., the doubt about the question 10 and the answer 20. In addition, according to this, the main points 60 of the question 10 and the answer 20 are included in the explanation 40, so that the user can grasp the main points 60 of the question 10 and the answer 20 and identify the main points that he or she does not understand, thereby improving the learning effect.

[0048] In addition, when at least one of the problem 10, the answer 20, and the question 30 is transmitted and received as image information, the problem 10, the answer 20, and the question 30 can be input as image information, thereby reducing the user's text input work. Furthermore, by having the generation AI 300 generate an answer 50 to the problem 10, the answer 20, or the question 30 that includes an illustration, and generating an explanation 40 for the user based on the answer 50, it is possible to answer the user's question 30, i.e., the question about the problem 10 and the answer 20, even if the problem 10, the answer 20, and the question 30 include an illustration.

[0049] 14A illustrates an example of an explanation 40 generated by the generation unit 220 based on the problem 10, the answer 20, and the question 30. The explanation 40 corresponds to an explanation to the question 30 based on the problem 10 and the answer 20. As described above, the explanation 40 is generated by the generation unit 220 by combining the answer 50 to the question 30 based on the problem 10 and the answer 20 generated by the generation AI 300, and further a part of the contents of the multiple main points 60 in the problem 10 and the answer 20 generated by the generation AI 300. The explanation 40 may be stored in a storage device of the learning support device 200.

[0050] In this example, explanation 40 is an explanation for question 30 on problem 10 and answer 20 on mathematical permutations. Explanation 40 is composed of answer 50, "'7!' is read as 'factorial of 7'. This means multiplying all positive integers from 7 to 1. In other words, 7 x 6 x 5 x 4 x 3 x 2 x 1 = 5040." and two main points 60, "In this problem, '7!' has seven elements (here, letters) and represents all the possibilities of how to arrange them. For example, in the case of 'abc', there are six ways (3!): 'abc', 'acb', 'bac', 'bca', 'cab', and 'cba'." and "Based on this, going back to problem (2), if we consider 'o, m, and e' as one element and each of the other letters as one element, there are a total of seven elements. All the possibilities of how to arrange these seven elements are '7!'."

[0051] If any of the problem 10, answer 20, and question 30 is transmitted or received as image information and a figure is included in the image information, the explanation 40 may be a quote of the figure. Also, if the content of the question 30 corresponds to multiple parts of the problem 10 and answer 20 and the content of the explanation differs depending on the part, the generation unit 220 may prepare and output separate explanations for each part.

[0052] FIG. 14B illustrates an example of an explanation 41 generated in a different manner. The explanation 41 is an explanation to a question 30 for a problem 10 and an answer 20 about a mathematical permutation, and is an explanation for a user who is unable to understand what is unclear about the problem 10 and the answer 20, rather than the explanation 40. The explanation 41 is generated in a form that lists an answer 50 (see FIG. 11) and a plurality of main points 60 (see FIG. 13). Such a generation method may be selected when a user sets to view all the main points on the user terminal 100. When displayed on the user terminal 100, the explanation 41 may display the plurality of main points 60 in a form that allows each of them to be selected, or may allow the user to reply with the number of the main point, so that the user can select a main point about which he / she wants to know a detailed explanation from among the plurality of main points 60.

[0053] It is to be noted that the summary of the main points 60 (steps S320 and S40) may be omitted. In such a case, the learning support device 200 generates the explanation 40 using only the answer 50 received from the generation AI 300 in step S310.

[0054] In step S400, the explanation 40 generated in step S300 is transmitted to the user terminal 100.

[0055] In step S50, the user terminal 100 receives the explanation 40 from the output unit 230 and displays it on the screen. FIG. 15 shows an example of the screen display of the user terminal 100 in step S50. In this example, the user transmits a question 30, "I don't understand the meaning of that arrangement of 7!," to the learning support device 200 on the user terminal 100 in step S20, and receives an explanation 40 starting with "Of course, I'll explain it! '7!' is..." from the learning support device 200 in step S40. This allows the explanation 40 to be output to the user terminal 100, and the explanation 40 can be confirmed on the user terminal 100. The user can also input an additional question 70 after confirming the explanation 40.

[0056] In step S60, the user inputs an additional question 70 on the user terminal 100 and instructs transmission. As a result, the additional question 70 is transmitted from the user terminal 100 to the learning support device 200.

[0057] In step S500, the transmitting / receiving unit 210 transmits and receives the additional question 70. First, the transmitting / receiving unit 210 receives the additional question 70 from the user terminal 100. In this embodiment, the additional question 70 is text information. If the additional question 70 is image information, the transmitting / receiving unit 210 converts the additional question 70 into text information as in step S130. If the additional question 70 is voice information, the transmitting / receiving unit 210 converts the additional question 70 into text information using built-in or online voice recognition software. Then, the transmitting / receiving unit 210 transmits the additional question 70, which is text information, to the generation AI 300. According to this, the user's additional question 70 for the explanation 40 is further input to the generation AI 300, an answer 51 to the additional question 70 is generated, and an explanation 42 for the user is generated based on the answer 51. This makes it possible to answer the user's additional question 70, i.e., the question in the explanation 40, even if the explanation 40 is insufficient.

[0058] Step S70 and the subsequent steps S600, S80, S700, and S90 are similar to steps S30, S300, S40, S400, and S50, respectively, and the details of these steps will be omitted.

[0059] 16 shows an example of a screen display of the user terminal 100 in step S90. In this example, the user transmits a question 30, "I don't understand the meaning of that arrangement of 7!," to the learning support device 200 in step S20 on the user terminal 100, receives an explanation 40 starting with "Of course, I'll explain it! '7!' is..." from the learning support device 200 in step S50, and then transmits an additional question 70, "Why do you think 'o, m, e' are considered as one element?" to the learning support device 200 in step S60, and receives an explanation 42 starting with "In problem (2),..." from the learning support device 200.

[0060] The flow of steps S60 to S90 may be repeated until the user's question is resolved.

[0061] 17 shows an operational flow of key point selection by the learning support system 1. In response to the explanation 41 displayed on the user terminal 100 in step S50 of the above-mentioned operational flow (see FIG. 2), the user may select, on the user terminal 100, any one of a plurality of key points 60 listed in the explanation 41 (see FIG. 14B). This process is executed in step S61. As a result, a request for further explanation of the selected key point from among the plurality of key points 60 is transmitted from the user terminal 100 to the learning support device 200.

[0062] In step S501, the transmitting / receiving unit 210 and the generating unit 220 generate a further explanation of the selected main point. First, the transmitting / receiving unit 210 instructs the generating AI 300 to explain the selected main point. For example, after inputting a plurality of main points 60 to the generating AI, an explanation of the selected main point can be requested by inputting "Please explain the third main point in more detail."

[0063] In step S71, the generation AI 300 generates an explanation 65 for the selected main point 75, and returns the generated explanation 65 to the generation unit 220.

[0064] Then, the generation unit 220 receives the explanation 65 generated from the generation AI 300 and sets it as the explanation 43 for the selected key point. According to this, the key point 75 selected by the user from the key points 60 of the question 10 and the answer 20 is input to the generation AI 300 to generate an explanation 65 for the key point 75 selected by the user, and an explanation 43 for the user is generated based on the explanation 65, so that the learning support device can deepen the user's understanding by providing an explanation focusing on the key point 75 selected by the user.

[0065] Steps S700 and S90 are similar to steps S400 and S50, respectively, and the details of these steps are omitted.

[0066] FIG. 18 shows an operation flow of automatic grading by the learning support system 1. Here, steps S10, S100, S400 to S700, and S90 are the same as those described above. This flow starts when the user selects "Grade" on the screen of the user terminal 100 at the start of the operation (see FIG. 3). At this time, a message 1201 "Please grade" is transmitted from the user terminal 100 to the learning support device 200. In response to this, after the completion of step S100, the learning support device 200 transmits a message to the user terminal 100 prompting the user to transmit the answer sheet 80. As a result, messages 1202 "Of course" and "Can I see your answer sheet?" are displayed on the screen of the user terminal 100 as shown in FIG. 19.

[0067] In step S21, the user inputs an answer 80 into the user terminal 100 and instructs it to be sent. An example of the answer 80 is shown in Fig. 20. The answer 80 is an answer created by the user to the question 10. The answer 80 is sent from the user terminal 100 to the learning support device 200.

[0068] In step S201, the transmitting / receiving unit 210 transmits and receives the answer sheet 80. First, the transmitting / receiving unit 210 receives the answer sheet 80 from the user terminal 100. If the answer sheet 80 is input as image information, the answer sheet 80 may be converted into text information as in step S130. Then, the transmitting / receiving unit 210 transmits the answer sheet 80 to the generation AI 300 and requests grading of the answer sheet 80 by transmitting the message "Please grade."

[0069] In step S31, the generation AI 300 receives the answer 80 from the learning support device 200, grades it, and transmits it to the learning support device 200.

[0070] In step S301, the answer is graded. First, the generation unit 220 receives from the generation AI 300 the graded result 90 generated by the generation AI 300 based on the question 10, the answer 20, and the answer 80. Next, the generation unit 220 requests the generation AI 300 to extract a plurality of key points 60. In step S40, the generation AI 300 extracts the multiple key points 60 and returns them to the learning support device 200. Thereafter, the generation unit 220 receives the multiple key points 60 returned from the generation AI 300. Then, the generation unit 220 generates an explanation 45 based on the graded result 90 and the multiple key points 60.

[0071] 21 shows an example of the screen display of the user terminal 100 in step S50. In this example, the answer submitted by the user in step S21 is displayed from the top as message 1203 on the user terminal 100, and message 1204 "Your answer is not wrong," which is the marking result 90 generated by the generation AI in step S30, and message 1205 "Make sure you fully understand the intent of the question...," which is part of the multiple key points 60 generated by the generation AI in step 40, are displayed as explanations 45.

[0072] This completes the grading of the answer. According to this, by inputting the user's answer 80 to the generation AI 300 and having the generation AI 300 grade the answer, the labor of grading can be reduced and grading can be done without relying on a grader. In addition, by inputting the user's additional question 71 regarding the grading result 90 of the generation AI 300 to the generation AI 300, and having the generation AI 300 generate an answer 52 to the additional question 71 based on the problem 10 and the answer 20, and generating an explanation 44 for the user based on the answer 52, the user's question regarding the grading result 90 can be answered.

[0073] As described above, according to the learning support system 1 of this embodiment, the learning support device 200 inputs not only the question 10 input from the user terminal 100 but also the answer 20 to the question into the generation AI 300, and then inputs a question 30 from the user into the generation AI 300, which generates an answer 50 to the question 30 based on the question 10 and the answer 20, and generates an explanation 40 for the user based on the answer 50, thereby making it possible to answer the user's question, i.e., any doubts about the question and the answer.

[0074] In addition, the learning support device 200 of this embodiment is a device that supports a user's learning by generating an explanation for the answer to a question, and is provided with a transceiver unit 210 that receives a question 10 and an answer 20 to the question 10 input by the user from the user terminal 100, transmits the question 10 and the answer 20 to the generation AI 300, and after transmitting the question 10 and the answer 20, receives a question 30 input by the user from the user terminal 100 and transmits the question 30 to the generation AI 300, and a generation unit 220 that receives an answer 50 to the question 30 from the generation AI 300 and generates an explanation 40 for the user based on the answer 50. According to this, not only the question 10 but also the answer 20 to the question 10 is input to the generation AI 300, and then a question 30 from the user is input to the generation AI 300, which then generates an answer 50 to the question 30 based on the question 10 and the answer 20, and generates an explanation 40 for the user based on the answer 50, thereby answering the user's question 30, i.e., the user's confusion (doubt) about the question 10 and the answer 20.

[0075] In addition, the learning support system 1 according to the present embodiment is provided as a system including a learning support device 200, a user terminal 100, and a generation AI 300. With this, a highly accurate explanation can be generated in response to a user's question 30, thereby improving the user's learning effect.

[0076] In addition, the learning support method of this embodiment is a learning support method that supports a user's learning by generating an explanation 40 for an answer 20 to a question 10, and includes a step of receiving a question 10 and an answer 20 to the question 10 input by the user from the user terminal 100 and transmitting the question 10 and the answer 20 to the generation AI 300, a step of receiving a question 30 input by the user from the user terminal 100 after transmitting the question 10 and the answer 20 to the generation AI 300, and a step of receiving an answer 50 to the question 30 from the generation AI 300 and generating an explanation 40 for the user based on the answer 50. According to this, not only the question 10 but also the answer 20 to the question 10 is input to the generation AI 300, and then a question 30 from the user is input to the generation AI 300, which then generates an answer 50 to the question 30 based on the question 10 and the answer 20, and generates an explanation 40 for the user based on the answer 50, thereby answering the user's question 30, i.e., the user's confusion (doubt) about the question 10 and the answer 20.

[0077] In addition, the learning support program according to the present embodiment provides a program for executing the following in order to generate an explanation for the answer to the question: a means for receiving a question 10 and an answer 20 to the question 10 input by the user from the user terminal 100, and transmitting the question 10 and the answer 20 to the generation AI 300; a means for receiving a question 30 input by the user from the user terminal 100 after transmitting the question 10 and the answer 20, and a means for receiving an answer 50 to the question 30 from the generation AI 300, and generating an explanation 40 for the user based on the answer 50. According to this, not only the question 10 but also the answer 20 to the question 10 is input to the generation AI 300, and then the question 30 from the user is input to the generation AI 300, and the generation AI 300 generates an answer 50 to the question 30 based on the question 10 and the answer 20, and generates an explanation 40 for the user based on the answer 50, thereby answering the user's question 30, i.e., the user's unclear (doubt) about the question 10 and the answer 20.

[0078] Moreover, according to the learning support system 1 of this embodiment, the learning support device 200 inputs not only the problem 10 input from the user terminal 100 but also the answer 20 to the problem to the generation AI 300, and then inputs the question 30 from the user to the generation AI 300, and the generation AI 300 generates an answer 50 to the question 30 based on the problem 10 and the answer 20, and generates an explanation 40 for the user based on the answer 50, thereby stabilizing the correct answer rate, which fluctuated between about 50% and 84% in the conventional technology, to 98%. This makes it possible to find a clue to a solution in the world of generation AI, where hallucination is an issue.

[0079] Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, where the blocks may represent (1) stages of a process in which operations are performed or (2) sections of an apparatus responsible for performing the operations. Particular stages and sections may be implemented by dedicated circuitry, programmable circuitry provided with computer readable instructions stored on a computer readable medium, and / or a processor provided with computer readable instructions stored on a computer readable medium. Dedicated circuitry may include digital and / or analog hardware circuitry and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuitry may include reconfigurable hardware circuitry including logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, memory elements such as flip-flops, registers, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like.

[0080] A computer readable medium may include any tangible device capable of storing instructions that are executed by a suitable device, such that a computer readable medium having instructions stored thereon comprises an article of manufacture that includes instructions that can be executed to create means for performing the operations specified in the flowchart or block diagram. Examples of computer readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer readable media may include floppy disks, diskettes, hard disks, random access memories (RAMs), read-only memories (ROMs), erasable programmable read-only memories (EPROMs or flash memories), electrically erasable programmable read-only memories (EEPROMs), static random access memories (SRAMs), compact disk read-only memories (CD-ROMs), digital versatile disks (DVDs), Blu-ray disks, memory sticks, integrated circuit cards, etc.

[0081] The computer readable instructions may include either assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0082] Computer readable instructions may be provided to a processor or programmable circuitry of a programmable data processing apparatus, such as a general purpose computer, special purpose computer, or other computer, either locally or over a wide area network (WAN) such as a local area network (LAN), the Internet, etc., to execute the computer readable instructions to create means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0083] 22 illustrates an example of a computer 1200 in which aspects of the present invention may be embodied in whole or in part. Programs installed on the computer 1200 may cause the computer 1200 to function as or perform operations associated with an apparatus or one or more sections of the apparatus according to an embodiment of the present invention, and / or to perform a process or steps of the process according to an embodiment of the present invention. Such programs may be executed by the CPU 1212 to cause the computer 1200 to perform specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0084] The computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, a graphic controller 1216, and a display device 1218, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a hard disk drive 1224, a DVD-ROM drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The computer also includes legacy input / output units such as a ROM 1230 and a keyboard 1242, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0085] The CPU 1212 operates according to a program stored in the ROM 1230 and the RAM 1214, thereby controlling each unit. The graphic controller 1216 retrieves image data generated by the CPU 1212 into a frame buffer or the like provided in the RAM 1214 or into the graphic controller 1216 itself, and causes the image data to be displayed on the display device 1218.

[0086] The communication interface 1222 communicates with other electronic devices via a network. The hard disk drive 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD-ROM drive 1226 reads programs or data from the DVD-ROM 1201 and provides the programs or data to the hard disk drive 1224 via the RAM 1214. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0087] The ROM 1230 stores therein a boot program or the like executed by the computer 1200 upon activation and / or a program that depends on the hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0088] The programs are provided by a computer-readable medium such as a DVD-ROM 1201 or an IC card. The programs are read from the computer-readable medium, installed in the hard disk drive 1224, the RAM 1214, or the ROM 1230, which are also examples of computer-readable media, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be constructed by realizing information manipulation or processing according to the use of the computer 1200.

[0089] For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 may execute a communication program loaded in the RAM 1214 and instruct the communication interface 1222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer processing area provided in the RAM 1214, the hard disk drive 1224, the DVD-ROM 1201, or a recording medium such as an IC card, and transmits the read transmission data to a network, or writes reception data received from the network to a reception buffer processing area or the like provided on the recording medium.

[0090] Furthermore, the CPU 1212 may cause all or a necessary portion of a file or database stored in an external recording medium such as a hard disk drive 1224, a DVD-ROM drive 1226 (DVD-ROM 1201), an IC card, etc. to be read into the RAM 1214, and perform various types of processing on the data on the RAM 1214. The CPU 1212 then writes back the processed data to the external recording medium.

[0091] Various types of information, such as various types of programs, data, tables, and databases, may be stored in the recording medium and undergo information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequence of the program, and write back the results to the RAM 1214. The CPU 1212 may also search for information in a file, database, etc. in the recording medium. For example, when a plurality of entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored in the recording medium, the CPU 1212 may search for an entry that matches a condition, in which the attribute value of the first attribute is specified, from among the plurality of entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0092] The above-described programs or software modules may be stored in a computer-readable medium on the computer 1200 or in the vicinity of the computer 1200. In addition, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable medium, thereby providing the programs to the computer 1200 via the network.

[0093] Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It is clear to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the description of the claims that such modifications and improvements can also be included in the technical scope of the present invention.

[0094] It should be noted that the order of execution of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and may be realized in any order unless the output of a previous process is used in a later process. Even if the operational flow in the claims, specifications, and drawings is explained using "first," "next," etc. for convenience, it does not mean that it is essential to perform the process in this order. [Explanation of symbols]

[0095] 1...Learning support system, 10...Problem, 20...Answer, 30...Question, 40, 41, 42, 43, 44, 45...Explanation, 50, 51, 52...Answer, 60, 61...Key points, 65...Explanation, 70, 71...Additional questions, 75...Selected key points, 80...Answer, 90...Result, 100...User terminal, 200...Learning support device, 210...Transmitter / receiver, 220...Generator, 230...Output unit, 400...OCR device, 500...Network, 1001, 1002, 1003, 1004, 1005, 1101 , 1102, 1103, 1104, 1105, 1201, 1202, 103, 1204, 1205...message, 1200...computer, 1210...host controller, 1212...CPU, 1216...graphics controller, 1218...display device, 1220...input / output controller, 1222...communication interface, 1224...hard disk drive, 1226...DVD-ROM drive, 1240...input / output chip, 1242...keyboard

Claims

1. A learning support device that supports a user's learning by generating an explanation for an answer to a question, A transceiver unit that receives a problem and an answer to the problem input by a user from a user terminal, transmits the problem and the answer to a generation AI, and after transmitting the problem and the answer, further receives a question input by the user from the user terminal and transmits the question to the generation AI; A generation unit that receives an answer to the question from the generation AI and generates an explanation for the user based on the answer; A learning support device comprising:

2. The transceiver unit further receives an additional question input by the user from the user terminal, and transmits the additional question to the generation AI. The learning support device according to claim 1 , wherein the generation unit receives an answer to the additional question from the generation AI and generates an explanation for the user based on the answer.

3. The learning support device according to claim 1 , further comprising an output unit that outputs the commentary to the user terminal.

4. The transmission / reception unit receives an answer entered by the user from the user terminal, transmits the answer to the generation AI for grading, The learning support device according to claim 1 , wherein the generation unit receives a grading result of the answer sheet from the generation AI.

5. The transmission / reception unit further receives a question regarding the scoring result input by the user from the user terminal, and transmits the question to the generation AI; The learning support device according to claim 4 , wherein the generation unit receives an answer to the question from the generation AI and generates an explanation for the user based on the answer.

6. The learning support device according to claim 1 , wherein the generating AI is a generating AI connected to the learning support device via a network.

7. The learning support device according to claim 1 , wherein the transmitting / receiving unit receives at least one of the problem, the answer, or the question as image information.

8. The learning support device according to claim 6 , wherein the transmission / reception unit recognizes characters contained in at least one of the problem, the answer, or the question received as image information, and transmits the characters as character information to the generation AI.

9. The learning support device according to claim 1 , wherein the generation unit further causes the generation AI to extract a plurality of key points from the answer and add the plurality of key points to the explanation.

10. The learning support device of claim 1, wherein the generation unit further causes the generation AI to extract multiple key points from the answer, provides the multiple key points to the user terminal, transmits key points selected by the user to the generation AI, receives an answer to the key points from the generation AI, and generates an explanation for the user based on the answer.

11. A learning support device according to any one of claims 1 to 10; The user terminal; The generated AI; A system comprising:

12. A learning support method for supporting a user's learning by generating an explanation for an answer to a question, comprising: receiving a question and an answer input by a user from a user terminal, and transmitting the question and the answer to a generation AI; After transmitting the problem and the answer, further comprising receiving a question input by the user from the user terminal and transmitting the question to the generating AI; receiving an answer to the question from the generating AI and generating an explanation for the user based on the answer; A learning support method that includes the following:

13. To generate an explanation for the answer to the problem, A means for receiving a question and an answer input by a user from a user terminal and transmitting the question and the answer to a generation AI; After transmitting the problem and the answer, a means for receiving a question input by the user from the user terminal and transmitting the question to the generating AI; A means for receiving an answer to the question from the generating AI and generating an explanation for the user based on the answer; A program that executes the following.

Images