Question reception system and question reception method

Abstract

To provide a question receiving system and a question receiving method for providing answers to questions in a state suitable for a learner. [Solution] The system has a memory unit that stores teaching material data, an artificial intelligence unit that generates an answer to the question based on the teaching material data when it receives a question about the teaching material data from an information processing terminal of a learner who is studying using the teaching material data, and an answer unit that reflects the characteristics of the learner in the answer generated by the artificial intelligence unit and outputs it to the information processing terminal.

Description

[Technical field]

[0001] The present disclosure relates to a technology for supporting learning by using a computer system. [Background technology]

[0002] Patent Document 1 discloses a learning support system having a learning support device that supports a user's learning by generating an explanation for an answer to a problem. The learning support device has a transmitting / receiving unit that receives a question input by a user for solving a problem from a user terminal and transmits the received question to a generation AI, and a generating unit that receives an answer from the generation AI and generates an explanation based on the answer. The explanation is composed of an answer to the question and multiple key points. Patent Document 1 describes that the multiple key points are knowledge necessary for understanding the problem and the answer. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7456589 Summary of the Invention [Problem to be solved by the invention]

[0004] In the learning support system disclosed in Patent Document 1, a user can obtain the knowledge necessary to understand the problem and the answer in addition to the answer to the question. However, depending on the user, there may be a surplus or deficiency of the knowledge necessary to understand the problem and the answer. For example, a user with a high learning level may feel that it is enough to obtain the answer and that the knowledge necessary to understand the problem and the answer is unnecessary. On the other hand, for a user with a low learning level, the knowledge contained in the explanation may be insufficient for understanding. A uniformly created explanation may not be suitable for all users.

[0005] One object of the present disclosure is to provide a question receiving system and a question receiving method that provide answers to questions in a manner suitable for a learner. [Means for solving the problem]

[0006] A question reception system according to one aspect included in the present disclosure includes a memory unit that stores teaching material data, an artificial intelligence unit that, when it receives a question about the teaching material data from an information processing terminal of a learner who is studying using the teaching material data, generates an answer to the question based on the teaching material data, and an answer unit that reflects characteristics of the learner in the answer generated by the artificial intelligence unit and transmits the answer to the information processing terminal. Effect of the Invention

[0007] According to one aspect of the present disclosure, answers suited to the characteristics of a learner can be provided instantly. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing an example of a configuration of a question receiving system according to a first embodiment. [Diagram 2] 1 is a block diagram showing a hardware configuration of a question receiving system. [Diagram 3] 2 is a table showing an example of learning record data stored in a storage unit shown in FIG. 1. [Figure 4] 4 is a flowchart showing an example of an operation procedure of the question receiving system according to the first embodiment. [Diagram 5] 5 is a flowchart showing an example of a procedure for a response providing process shown in FIG. 4. [Figure 6] 5 is a flowchart showing an example of a procedure of the weakness overcoming learning process shown in FIG. 4. [Figure 7] 5 is a flowchart showing an example of a procedure of the data collection process shown in FIG. 4. [Figure 8] 4 is a flowchart showing an example of a procedure of an additional learning process executed by a learning unit shown in FIG. [Figure 9] 10 is a flowchart showing another example of the procedure of the additional learning process executed by the learning unit shown in FIG. [Figure 10] FIG. 11 is a block diagram showing an example of the configuration of a question receiving system according to a second embodiment. [Figure 11] 10 is a flowchart showing an example of an operation procedure of the question receiving system according to the second embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] The question receiving system of this embodiment will be described below with reference to the drawings.

[0010] <First embodiment> The question receiving system of this embodiment is a computer system that provides students with lecture content consisting of video and audio by a virtual person (hereinafter referred to as a "virtual lecturer") who resembles a lecturer. In this embodiment, the computer system is used, for example, by a learner to study a subject for a qualification exam with the aim of passing the exam. The configuration of the question receiving system of the present embodiment will be described with reference to the drawings. Fig. 1 is a block diagram showing an example of the configuration of the question receiving system according to the first embodiment.

[0011] As shown in Fig. 1, question reception system 10 has instant response unit 11, AI (artificial intelligence) unit 12, learning unit 13, setting unit 14, and storage unit 15. In storage unit 15, prepared data required to execute the service and information registered by executing the service are recorded. The processes of instant response unit 11, AI unit 12, learning unit 13, and setting unit 14 are defined by software programs, and are realized by a processor executing the software programs. Details of each unit, data, and information will be described later.

[0012] FIG. 2 is a block diagram showing a hardware configuration of the question receiving system. 2, the question receiving system 10 includes a server 20 and an information processing terminal 30, such as a personal computer or a smartphone, that can be connected to the server 20 via a communication network such as the Internet. The information processing terminal 30 is an information processing device operated by a learner 90 who is taking lecture content.

[0013] The information processing terminal 30 has a camera 31, a microphone 32, a speaker 33, a display 34, a memory (not shown), and a processor (not shown). The memory stores a browser 35 which is a browsing application software program. The processor executes the browser 35 stored in the memory. A learner 90 connects to the server 20 using the browser 35 on the information processing terminal 30, and uses a service provided by the server 20. The service is a service that provides content related to learning. The service is realized by the various units shown in FIG. 1.

[0014] As shown in FIG. 2, the server 20 has, as hardware, a processing device 21, a main memory 22, a storage device 23, a communication device 24, an input device 25, and a display device 26, which are connected to a bus 27.

[0015] The storage device 23 stores data in a writable and readable manner. The storage unit 15 shown in FIG. 1 is realized by the storage device 23. The storage device 23 is, for example, a hard disk drive (HDD) or a solid state drive (SSD). The processing device 21 is a processor that reads data stored in the storage device 23 into the main memory 22 and executes processing of a software program using the main memory 22. The processing device 21 is, for example, a central processing unit (CPU). The immediate response unit 11, the AI ​​unit 12, the learning unit 13, and the setting unit 14 shown in FIG. 1 are realized by the processing device 21. The communication device 24 transmits information processed by the processing device 21 via a communication network including wired or wireless or both, and also transmits information received via the communication network to the processing device 21. The received information is used for software processing by the processing device 21. The input device 25 is a device that accepts information input by an operator using a keyboard, a mouse, or the like, and the input information is used for software processing by the processing device 21. The display device 26 is a device that displays image or text information on a display screen in accordance with software processing by the processing device 21. The input device 25 and the display device 26 are provided for use not by the learners 90 but mainly by an administrator (not shown).

[0016] The data stored in the storage unit 15 shown in FIG. 1 will be described. The storage unit 15 stores teaching material data, learning record data, learning assistance data, and answer models. The teaching material data includes lecture content, data on the textbook used in the lecture, and commentary content, which is content that explains the subject matter for each of the multiple subjects described in the textbook. The teaching material data may also include a confirmation test for confirming the multiple subjects described in the textbook, and answers to the multiple questions included in the confirmation test. Furthermore, the teaching material data may also include, for the content described in the textbook, a problem exercise that is more difficult than the confirmation test, answers to the multiple questions included in the problem exercise, and commentary content, which is content that explains the answers to the multiple questions.

[0017] Fig. 3 is a table showing an example of learning record data stored in the storage unit shown in Fig. 1. In the table, question and answer data, evaluation, learning level, areas of strength / weakness, learning process, and test-taking experience are recorded in correspondence with a learner ID, which is an identifier different for each learner.

[0018] The question and answer data is data that combines questions previously asked by the learner 90 corresponding to the learner ID and answers generated by the AI ​​unit 12. Two specific examples of combinations of questions and answers will be described for a case in which the learner's qualifications for taking the exam for a licensed real estate agent.

[0019] (Question 1) Question subject: <Textbook> Textbook "Real Estate Business Law", <Question number or page number, etc.> Pages 114-116 Question: "In the textbook, when it comes to business guarantees and repayment guarantees, it always says to notify the licensee, but who is the licensee?"

[0020] (Answer 1) "To operate a real estate business, you need a license. The explanation of who holds the license can be found on pages 98-101 of the textbook on the Real Estate Business Law. To put it simply, as shown in the diagram on page 99 of the textbook, if the office is in only one prefecture, the prefectural governor is the license holder, and if the office is in two or more prefectures, the Minister of Land, Infrastructure, Transport and Tourism is the license holder."

[0021] (Question 2) · Question target: <Textbook> "Real Estate Business Law Textbook 1", <Question number or page number, etc.> Page 118 Question: "I would like to ask about the difference between the recovery of business guarantees and repayment guarantees. In the case of business guarantees, if the business guarantee is exceeded due to the closure of a branch office, "public notice is required." In the case of repayment guarantees, if the amount of the contribution is exceeded due to the closure of some offices, "public notice is not required." What is the reason for the difference between "public notice required" and "not required?"

[0022] (Answer 2) "For example, let's say Company A has a head office and one branch office, and has deposited 15 million yen as a business guarantee. In this case, the limit on the amount of refunds that customers can receive is 15 million yen. If Company A were to close the branch office and immediately get back the business guarantee (5 million yen), the limit on the amount of refunds that customers can receive would become 10 million yen. In order to ensure that the limit on the amount of refunds that customers can receive is not immediately reduced even if Company A closes a branch office, and to make customers aware of this, a notice is required to specify a period of at least six months for customers to claim their rights. What the notice means is that 'Those who have the right to a refund should exercise their right promptly. If they do not do so promptly, there is a possibility that they will not be able to receive a refund from the business guarantee deposit.' On the other hand, suppose that Company B also has a head office and one branch office, and has paid 900,000 yen as a repayment guarantee contribution. In this case, the limit on the amount of refund that a customer can receive is 15 million yen, just like Company A. The reason why the limit on the amount of refund is 15 million yen even though only 900,000 yen has been paid is because of the repayment guarantee contributions paid by other members. For example, if there are 1,000 members (real estate agents) in a guarantee association and each company pays a repayment guarantee contribution of 900,000 yen, the guarantee association will have a total of 900 million yen deposited. Even if Company B closes its branch office and the repayment guarantee contribution (300,000 yen) is immediately reclaimed, it will not have a significant impact on the total amount of 900 million yen. Therefore, if Company B simply closes its branch office and remains a member of the guarantee association, it can be immediately reclaimed without any public notice.

[0023] Fig. 3 shows a case where the text of each of the questions and answers is recorded in a table, but the recording location of the question and answer data is not limited to the table shown in Fig. 3. For example, the setting unit 14 may assign an identifier to each of the text data of the question and answer, record the assigned identifier in the learning record data, and save the text data of the question and answer in another storage area in the storage unit 15. As described above, the text of the question may include not only the content of the question, but also information on the subject of the question.

[0024] The evaluation column of the table shown in Fig. 3 records the evaluation of the answer by the learner 90. The evaluation is, for example, a five-level evaluation from rank 1 to rank 5. Rank 5 is the highest evaluation and rank 1 is the lowest rank. Specific examples of ranks 5 to 1 are as follows. Rank 5: Very easy to understand Rank 4: Fairly easy to understand Rank 3: Normal Rank 2: A little confusing Rank 1: Very confusing

[0025] 3, for example, in the case of a learner with a learner ID of Gs2, two questions were asked in the learning process, and of the two answers, one answer was evaluated as rank 5 and the other answer was evaluated as rank 4. In this embodiment, a case will be described in which the evaluation is on a five-point scale, but the evaluation rank division is not limited to five.

[0026] The learning level column records the learning level of the learner 90. Although Fig. 3 shows three learning levels, high, medium, and low, the division of learning levels is not limited to three. The division of learning levels may be two, or four or more. The strong and weak areas of the learner 90 are described in the strong and weak areas of the learner's subjects. In this embodiment, there are five subjects: T, J, S, K, and F. Referring to FIG. 3, for example, it is shown that the learner 90 with the learner ID Gs1 is strong in subjects T and J, but weak in subject S. The strong and weak areas are not limited to subjects, and may be a learning range that occupies a part of one subject. Hereinafter, information on strong and weak areas is referred to as strengths and weaknesses information. The learning progress indicates the range of the entire lecture content that is being viewed by the learner 90. For example, if the entire lecture content has 30 frames, it is divided into three parts: the first half from 1 to 10, the middle half from 11 to 20, and the second half from 21 to 30. In the test-taking experience column, if the learner 90 has never taken the actual test, "no" is recorded, and if the learner 90 has taken the actual test at least once, "yes" is recorded. The learning support data includes information on virtual instructors as data to support the teaching material data. The virtual instructors respond to questions from learners in place of real instructors. The virtual instructors are created to suit the preferences of the learners. The virtual instructor information is associated with the learner's ID and registered in the learning support data.

[0027] The configurations of the immediate response section 11, the AI ​​section 12, the learning section 13 and the setting section 14 shown in FIG. 1 will be briefly described. The instantaneous response unit 11 inputs questions received from the information processing terminal 30 of the learner 90 to the AI ​​unit 12. The instantaneous response unit 11 reflects the characteristics of the learner 90 in the answers acquired from the AI ​​unit 12 and transmits them to the information processing terminal 30. Learner characteristics are a concept that comprehensively represents the individuality and qualities of each learner, and include elements such as emotional aspects, learning progress, learning level, and strong / weak subjects. The AI ​​unit 12 generates an answer to the question using the answer model. The learning unit 13 updates the answer model using the learning data. The setting unit 14 records an evaluation of the answer in the learning record data stored by the memory unit 15. The function of each part will be explained along with the operation of question receiving system 10, and detailed explanations thereof will be omitted here.

[0028] Next, an operation of the question receiving system 10 of this embodiment will be described. Fig. 4 is a flowchart showing an example of an operation procedure of the question receiving system according to the first embodiment.

[0029] In step S101, the server 20 accepts a question from the information processing terminal 30 of the learner 90. The data format of the question is not limited to text, but may be voice, still image, or moving image. The question format is not limited to text, but may be a voice dialogue format using the voice of the learner 90, or a face-to-face conference format using a face image and voice. When the question format is a voice dialogue format, the information processing terminal 30 transmits voice data of the learner 90 collected by the microphone 32 to the server 20. When the question format is a face-to-face conference format, the information processing terminal 30 transmits image data of the face of the learner 90 captured by the camera 31 and voice data of the learner 90 collected by the microphone 32 to the server 20. The image data may be still image data or moving image data.

[0030] In step S102, the server 20 performs an answer providing process. The answer providing process will be described in detail with reference to FIG. 5. In step S103, the server 20 performs a weakness overcoming learning process. The weakness overcoming learning process will be described in detail with reference to FIG. 6. In step S104, the server 20 performs a data collection process. The data collection process will be described in detail with reference to FIG. 7.

[0031] FIG. 5 is a flowchart illustrating an example of a procedure of the answer providing process illustrated in FIG. In step S201, when the immediate response unit 11 receives selection information for selecting a virtual instructor from the learner 90 via the information processing terminal 30, the immediate response unit 11 selects a virtual instructor from the learning assistance data according to the selection information. The immediate response unit 11 obtains information on the selected virtual instructor from the learning assistance data. The selection information is, for example, the learner ID. In step S202, the instantaneous response unit 11 inputs a question to the AI ​​unit 12. If the question format is text via e-mail, the instantaneous response unit 11 inputs text data to the AI ​​unit 12. If the question format is voice dialogue, the instantaneous response unit 11 inputs voice data to the AI ​​unit 12. If the question format is face-to-face conference, image data of the learner's face and voice data are input to the AI ​​unit 12.

[0032] Regarding step S202, of the two specific examples of questions described above, the case of question 2 will be described. In step S101, the email received from the information processing terminal 30 contains the following question content in addition to the description of the question subject. "thank you always. I would like to ask about the difference between the recovery of business guarantee deposits and settlement operation guarantee deposits. In the business guarantee, it is stated that "public notice is required" if the business guarantee is exceeded due to the closure of a branch office, and in the repayment business guarantee, it is stated that "public notice is not required" if the amount of the contribution is exceeded due to the closure of some offices. What is the reason for the difference between "public notice" and "not required"? In this case, the immediate response unit 11 inputs the above question content to the AI ​​unit 12, excluding the part "Thank you for your continued support," which is not directly related to the question.

[0033] In step S203, when the AI ​​unit 12 receives the question from the immediate answer unit 11, it analyzes the emotion of the learner 90 from the question. When the question format is voice dialogue, the AI ​​unit 12 judges whether the learner is in a good mood, for example, from the volume and / or frequency of the learner's voice. When a person is in a bad mood, their voice tends to become quieter and their voice frequency tends to be lower. When the volume of the learner's voice is lower than a predetermined volume reference value, the AI ​​unit 12 judges that the learner is in a bad mood. When the frequency of the learner's voice is lower than a predetermined frequency reference value, the AI ​​unit 12 judges that the learner is in a bad mood. The AI ​​unit 12 may also judge the learner's mood based on the speed at which the learner speaks. When a person is in a bad mood, their speed of speech tends to increase, so when the speed of the learner's speech is faster than a predetermined reference speed, the AI ​​unit 12 judges that the learner is in a bad mood. A case in which the learner is in a bad mood is, for example, when the final exam is approaching. When the question format is a face-to-face meeting, the AI ​​unit 12 judges whether the learner is highly motivated to learn based on the size of the contour of the learner's face. When a learner is highly motivated to learn, he or she tends to lean forward, so the contour of the image of the face captured by the camera of the information processing terminal 30 becomes larger. Therefore, when the size of the contour of the learner's face is larger than a predetermined reference size, the AI ​​unit 12 judges that the learner is highly motivated. The image of the learner's face may be a still image or a moving image. The AI ​​unit 12 outputs the result of the sentiment analysis to the immediate answer unit 11. In addition, the AI ​​unit 12 generates an answer to the question using the answer model.

[0034] In step S204, the immediate response unit 11 obtains an answer from the AI ​​unit 12. The immediate response unit 11 obtains a result of emotion analysis from the AI ​​unit 12. If the result of the emotion analysis indicates that the learner is in a bad mood, such as that the learner has low motivation for learning, the immediate response unit 11 requests the AI ​​unit 12 to express the answer in a way that is in line with the learner's emotions. Specifically, the immediate response unit 11 inputs to the AI ​​unit 12, together with the "analysis result" and "answer" received from the AI ​​unit 12, a request that the "answer" be expressed in a way that does not upset the learner. For example, the immediate response unit 11 inputs to the AI ​​unit 12, together with the answer, a request that "the learner who will receive the answer is in a bad mood, so please express the answer in a way that does not upset the learner." The AI ​​unit 12 creates an answer with an expression corresponding to the learner's emotion based on the generated answer. The immediate answering unit 11 may request an external general-purpose generating AI to make the answer to the learner an expression that is in tune with the learner's emotion, instead of the AI ​​unit 12.

[0035] Here, a specific example of a method for creating an answer in response to a learner's emotions when the learner is in a bad mood, such as when the learner has low motivation to learn, will be described. In order to increase the motivation of a learner who has low motivation to learn, several effective answering methods can be considered. As specific examples of effective answering methods, four methods (1) to (4) will be described below. The AI ​​unit 12 applies one or more of methods (1) to (4) to the generated answer. If (1) to (4) are prioritized, (1) is the most important.

[0036] (1) Show empathy for the learners. By showing understanding of the learners' concerns and questions and using phrases such as "I understand how you feel," the learners will feel that their situation is understood and will be more likely to open up. (2) Encourage learners to set specific goals. Ask students, "What do you want to achieve through this class?" and help them clarify their own goals. Having a clear goal increases their motivation to learn. Also, setting small, achievable goals allows students to gain experience of success, which leads to self-confidence. (3) Emphasizing the practicality and / or relevance of the learning content to learners. By explaining to learners "How will this knowledge be useful in the future?" with concrete examples, you can make them feel the significance of learning. For example, presenting a concrete scenario such as "This formula is very important in real business situations" can arouse interest. (4) Give learners positive feedback. Praising learners for the questions they asked and the efforts they made will help them feel more confident. It is important to evaluate the learner's thoughts and actions by saying things like, "That's a very good point of view."

[0037] Among the specific examples of the two questions mentioned above, for example, when the above (4) is applied to Answer 1 to Question 1, the AI ​​unit 12 creates an answer by adding a message "That's a very good point of view" before Answer 1. Specifically, the AI ​​unit 12 creates an answer saying, "That's a very good point of view. To operate a real estate business, you need a license. The explanation of the license holder is on pages 98 to 101 of the textbook on the Real Estate Business Law. Simply put, as shown in the diagram on page 99 of the textbook, if the office is in only one prefecture, the governor of that prefecture is the license holder, and if the office is in two or more prefectures, it is the Minister of Land, Infrastructure, Transport and Tourism."

[0038] In step S205, the immediate response section 11 judges whether or not the learning level of the learner 90 is high. If the result of the determination in step S205 is that the learning level of the learner is high, a strengths and weaknesses determination of the learner is performed (step S206). If it is determined in step S206 that the learning subject of the question belongs to the learner's field of expertise, the immediate answering unit 11 provides the answer to the information processing terminal 30 (step S207). Specifically, the immediate answering unit 11 causes the virtual instructor selected by the learner 90 in step S201 to read out the answer, causes an image of the virtual instructor to be displayed on the display 34 via the browser 35 of the information processing terminal 30, and causes the speaker 33 to output the answer as voice.

[0039] On the other hand, if the result of the judgment in step S205 is that the learning level of the learner is not high, the immediate answering unit 11 proceeds to the process of step S208. If the result of the judgment in step S206 is that the learning subject of the question belongs to the learner's weak field, the immediate answering unit 11 proceeds to the process of step S208. In step S208, the immediate answering unit 11 acquires explanation content of basic matters from the teaching material data, and provides the acquired explanation content to the information processing terminal 30. Specifically, the immediate answering unit 11 makes the virtual instructor selected by the learner 90 in step S201 read out the explanation, displays the image of the virtual instructor on the display 34 via the browser 35 of the information processing terminal 30, and outputs the explanation by voice from the speaker 33. After the process of step S208, the immediate answering unit 11 makes the virtual instructor output the answer as described above (step S207).

[0040] In this way, if the result of the determination in step S205 is that the learning level is high and the result of the determination in step S206 is that the subject is a strong field, the instant answer unit 11 may transmit the answer to the information processing terminal 30 as content to be provided to the learner in step S207. On the other hand, if the result of the determination in step S205 is that the learning level is not high or the result of the determination in step S206 is that the subject is a weak field, the instant answer unit 11 transmits explanation content in addition to the answer to the information processing terminal 30 as content to be provided to the learner.

[0041] The server 20 does not have to perform all of the processes of steps S201, S203, S205, and S206 shown in Fig. 5. It is sufficient to perform at least one of these processes. For example, if the immediate response unit 11 does not receive selection information for selecting a virtual instructor from the information processing terminal 30, it does not have to perform the process of step S201. Also, if the result of the determination in step S205 is that the learning level is high and the determination in step S206 is not performed, the immediate response unit 11 may proceed to the process of step S207.

[0042] The following describes how the above-described question receiving system 10 can solve the problems of the related art. Problems 1 to 5 will be described as the problems of the related art. (Issue 1: It takes a long time to answer a question after it has been received) When an instructor accepts questions from learners via email and creates answers to those questions and replies to the learners via email, the answers may not be sent until the day after the question was received or later. One reason for this is that there is a limit to the number of instructors who can respond to questions from many learners. In particular, questions tend to be concentrated just before the actual exam, and it is difficult for instructors to reply to all questions by the day after the question was received. On the other hand, if learners receive answers to their questions quickly, their doubts are resolved immediately, and their motivation to study is maintained. On the other hand, the longer the response takes, the less motivated the learners are to study. For this reason, it is necessary to provide answers to questions to learners as soon as possible.

[0043] (This embodiment for problem 1: immediate response by AI) In the question receiving system 10 of this embodiment, the AI ​​unit 12 automatically generates answers to questions, and the instantaneous answering unit 11 outputs the answers generated by the AI ​​unit 12 to the learner's information processing terminal 30. Since the AI ​​unit 12 of the server 20 generates answers to questions based on teaching material data instead of an actual instructor, answers can be provided to the learner quickly regardless of the time the question was received.

[0044] In this embodiment, if an answer to a question that is the same as the question received from the learner has been generated in the past, the previously generated answer may be used. This method will be specifically described. Assume that question answer data and evaluation information are recorded in the learning record data for answers given in the past to the same question as the newly received question. In this case, the immediate answering unit 11 outputs answers that have been given in the past to the same question and have an evaluation equal to or higher than a predetermined reference value to the information processing terminal 30 of the learner. The reference value is, for example, rank 5. Since the answers generated in the past can be utilized, the answer can be provided to the learner quickly. In addition, since the answer has an evaluation of rank 5, a highly evaluated answer can be provided to the learner. However, it is considered that there are few answers with rank 5 depending on the learning range. Therefore, the reference value may be rank 4. The reference value may be changed according to the learning range that is the subject of the question.

[0045] (Task 2: Learners cannot choose who to answer) When learners receive answers from instructors who match their preferences, they are more motivated to learn and tend to ask more questions. The number of instructors who teach a single exam is limited. Since people tend to have good and bad compatibility, learners may not necessarily get along with the instructor who answers their questions.

[0046] (This embodiment for problem 2: Answer by a virtual instructor that matches the learner's preferences) Many people have had the experience of studying hard in a subject taught by a teacher they liked during their school days. It is not always possible for a learner to meet a teacher who matches their preferences in the case of a real teacher, but this is highly likely to be possible in the case of a virtual teacher. The question receiving system 10 of this embodiment allows a learner to obtain answers from a virtual teacher who matches their preferences.

[0047] A learner inputs his / her preferences for each of a plurality of conditions to the server 20 via the information processing terminal 30. The setting unit 14 creates a virtual instructor that matches the learner's preferences according to the instructions input for each of the plurality of conditions. The setting unit 14 stores information about the created virtual instructor together with the learner's ID in the storage unit 15. The plurality of conditions may be, for example, the virtual instructor's appearance, fashion, voice, and personality.

[0048] The appearance is information that represents the appearance of the virtual instructor. For example, the appearance of the virtual instructor is set to an appearance selected by the learner from a plurality of types of appearances prepared in advance. The fashion is information that represents the clothes of the virtual instructor. For example, the fashion is set to an outfit selected by the learner from a plurality of types of fashions prepared in advance. The voice is information that represents the voice uttered by the virtual teacher. For example, the voice selected by the learner from a plurality of voices prepared in advance is set for the virtual teacher. The personality is information that represents the personality of the virtual teacher. For example, the virtual teacher is set to have a personality selected by the learner from a plurality of personalities prepared in advance.

[0049] This allows a virtual teacher to be set with the learner's preferred appearance, fashion, voice and personality. The learner can obtain answers from the virtual teacher he or she created. While the virtual teacher is presenting an answer, the learner may change the settings for each of a number of conditions. In this case, the learner can update to a more ideal virtual teacher.

[0050] (Challenge 3: Not being able to respond to a learner's question while taking into account their feelings) Since learners are human, sometimes they feel good and sometimes they feel bad. Naturally, the mental state of a learner varies from time to time. In particular, many learners become mentally unstable just before the actual exam. Therefore, when an instructor receives a question just before the actual exam, it is desirable for the instructor to guess the learner's emotions and respond appropriately to those emotions. When an instructor receives a question from a learner by email, the instructor replies with an answer to the question by email. In this case, it is difficult for the instructor to guess the learner's emotions from the content of the email text every time a question is received and respond while taking those emotions into consideration.

[0051] (This embodiment for problem 3: sentiment analysis) The question receiving system 10 of this embodiment infers the emotion from the learner's question and responds appropriately to the inferred emotion. Furthermore, the question receiving system 10 of this embodiment is not limited to the case where the question format is text, but also supports voice dialogue or face-to-face conference. The AI ​​unit 12 analyzes the emotion of the questioner according to the question format and generates an answer that is in line with the emotion of the analysis result. The question format is, for example, text, voice dialogue, or face-to-face conference.

[0052] When the question format is text, the AI ​​unit 12 infers the learner's emotions from the words used. When the question format is voice dialogue, the AI ​​unit 12 infers the learner's emotions from the learner's voice state and the words used in the conversation. In this case, the AI ​​unit 12 can obtain information on the learner's voice strength, speaking speed, and / or intonation when the question is asked, and can therefore infer emotions more accurately than when the question format is text. When the question format is face-to-face conference, the AI ​​unit 12 analyzes facial expressions toward the learner and infers the learner's emotions from the results of the facial expression analysis and the words used. In this case, the AI ​​unit 12 can obtain information on the learner's facial expressions in addition to the learner's voice when the question is asked, and can therefore infer emotions more accurately. The question receiving system 10 of this embodiment can provide an answer that corresponds more to the learner's emotions when the question is asked.

[0053] (Challenge 4: Questions that are difficult to express in writing are difficult to answer via email alone.) Students ask questions about a variety of subjects, including textbooks and lectures. Some questions are about what is written in the textbook, while others are about what is explained orally by the lecturer in the lecture. Consider the case where a student asks a question about something written in a textbook by email. In this case, the student must write "'...' written on page XX, line XX of the textbook" as the subject of the question in the message field of the email, followed by the content of the question. The student must transcribe the matters written in the textbook as the premise of the content of the question. Let us also consider the case where a student asks a question by email about the contents of a lecture that was explained orally by the instructor. In this case, the student must write in the message field of the email, "During the lecture of the XXXth class, '...' the instructor said at △△ minutes after the start of the lecture" as the subject of the question, followed by the content of the question. The student must convert what the instructor said orally into text as a prerequisite for the content of the question. In this way, if a learner were to ask questions about all of the learning materials by e-mail, this would place a heavy burden on the learner.

[0054] (This embodiment for problem 4: multimodal question reception) When a learner asks a question, various appropriate patterns can be considered depending on the subject, the content of the question, the level of the question, and the learning level of the questioner, such as a question best suited to text via e-mail, a question best suited to voice dialogue, or a question best suited to a face-to-face meeting. For example, when a learner asks a question about something written in a mathematics textbook, a face-to-face meeting is best. Asking a question about mathematics content via e-mail places a considerable burden on the learner. Therefore, the question receiving system 10 of the present embodiment is configured to be able to handle questions from learners in any of three question formats: text, voice dialogue, and face-to-face conference. Learners can select the format that places the least burden on them and is easiest for them to ask questions from the three question formats.

[0055] (Task 5: Different learners evaluate the same answer differently) Even if a learner gives the same answer to the same question, the evaluation of the answer will differ depending on the learner. One reason is that there are differences in academic ability among learners. If the same answer is provided to all learners, learners whose answers do not match their learning level will not be satisfied with the answer. Therefore, it is desirable to provide answers that match the learner's learning level. Another reason is that strengths and weaknesses differ depending on the learner. Even if a learner's learning level is low, if the answer is related to the learner's strengths, the learner is likely to be satisfied with the answer. On the other hand, even if a learner's learning level is high, if the answer is related to the learner's weaknesses, the learner is less likely to be satisfied with the answer. Therefore, it is desirable to provide answers that match the learner's strengths and weaknesses.

[0056] (This embodiment for problem 5: generating answers that match the learner's learning level) The question receiving system 10 of this embodiment generates answers according to the learning level of the learner. The learning level of each learner is recorded in the learning record data as described with reference to FIG. 3. An example of a method for recording the learning level of each learner will be described. For each course, a test is administered within the curriculum to all learners taking that course, and the test scores of each learner are recorded in the learning record data. When a learner has a low learning level, they often do not understand basic knowledge. Therefore, when a learner asks a question, it is best to provide them with information on basic matters so that they can confirm the knowledge that is the premise of the answer before answering the question. In contrast, when a learner asks a question with a high learning level, it is best to answer the question concisely without providing them with information on basic matters. This is because if a learner with a high learning level is prompted to confirm basic matters before answering, there is a high possibility that they will be dissatisfied and will want the question answered more concisely. Therefore, in this embodiment, the way of answering is changed depending on the learning level of the learner, taking into consideration the above-mentioned learner characteristics. For example, the learning level of each learner is classified into either high or low rank, and the style of answering is changed according to the learning level of the learner. When providing information on basic matters to the learner, the basic matters may be provided together with the answer.

[0057] (This embodiment for problem 5: generating answers that match the learner's strengths / weaknesses) Many people have areas of study that they are good at and areas that they are not good at. Even people with excellent grades always have areas that they are not good at. There are only a few people who have no areas that they are not good at. The question receiving system 10 of this embodiment generates an answer depending on whether the question belongs to the learner's strong or weak field. Information on the strong and weak fields of each learner is recorded in the learning record data as described with reference to FIG. 3. An example of a method for recording information on the strong and weak fields of each learner will be described. A questionnaire for filling out the strong and weak fields of each learner who applies for a course is distributed to all learners who apply for a course, and the questionnaire results of each learner are recorded in the learning record data. As another method, the AI ​​unit 12 may determine the strong or weak field of the learner based on the results of a test administered to the learner, and record the determination result in the learning record data. For example, if the test results of a certain learning subject are significantly worse than those of other learning subjects, the AI ​​unit 12 determines that the learning subject with the poor results is a weak field. In this embodiment, when a question falls within a learner's weak area, in addition to the answer to the question, basic information that assists the answer is provided to the learner.

[0058] Next, a description will be given of the weakness overcoming learning process shown in Fig. 4. Fig. 6 is a flowchart showing an example of the procedure of the weakness overcoming learning process shown in Fig. 4. In step S301, the AI ​​unit 12 judges the proficiency of the learner 90 based on the question of the learner 90. There are three levels of proficiency: A, B, and C. The relationship between these three levels of proficiency is as follows: <B<Cである。

[0059] The proficiency level A is a case where the learner 90 does not yet have basic knowledge of the learning range of the question subject. When the AI ​​unit 12 determines that the question is about a basic matter of the learning subject, it determines the proficiency level of the learner 90 as A. Proficiency level B is when the learner 90 has basic ability but no applied ability in the learning range of the question. When the AI ​​unit 12 determines from the question that the learner 90 understands basic matters but does not understand applied matters, it determines the learner 90's proficiency level as B. Proficiency level C is when the learner 90 has considerable ability in the target learning range. When the AI ​​unit 12 determines from the question that the learner 90 has both basic ability and applied ability, and further determines that the learner 90 can laterally expand the knowledge of the target learning range to other fields based on the basic ability and applied ability, the AI ​​unit 12 determines the learner 90's proficiency level as C. Note that in this embodiment, a case will be described in which the learner's proficiency level in the learning range is classified into three levels, A, B, and C, but the number of levels is not limited to three.

[0060] If the AI ​​unit 12 judges in step S301 that the proficiency level of the learner 90 is A, the immediate response unit 11 provides the information processing terminal 30 with explanatory content in the field to be studied (step S302). In step S303, the immediate response unit 11 conducts a confirmation test on the learner 90.

[0061] If the AI ​​unit 12 judges the learner 90's proficiency level to be B as a result of the judgment in step S301, the instantaneous answering unit 11 provides practice problems in the field to be studied to the information processing terminal 30, and prompts the learner 90 to carry out the practice problems (step S304). When the instantaneous answering unit 11 receives the answers to the practice problems from the information processing terminal 30, it compares the correct answers with the answers of the learner 90, and extracts the questions that were answered incorrectly from the practice problems. In step S305, the instantaneous answering unit 11 provides the information processing terminal 30 with explanation content for the questions that were answered incorrectly.

[0062] The question receiving system 10 of the present embodiment can solve a problem in the related art, which will be referred to as problem 6. (Task 6: Answering questions but not providing learning guidance to students) Since instructors have to answer questions from many students, they are overwhelmed with answering the questions. Therefore, even if instructors notice weak areas of students from the content of the students' questions, it is difficult for them to provide learning guidance. Many people have difficulty finding the motivation to tackle their weak areas, and it is difficult for them to overcome them on their own. If weak areas are left unattended, academic ability will not improve no matter how much time passes. Therefore, it is desirable to have the students study to overcome their weak areas when answering their questions.

[0063] (This embodiment for issue 6: Proposing a learning plan for each learner to overcome their weaknesses) The question receiving system 10 of this embodiment judges the learner's level of proficiency in the learning subject from the content of the question, proposes a study plan to the learner for overcoming the weak point according to the level of proficiency, and allows the learner to study for overcoming the weak point. Since the study plan for overcoming the weak point is proposed to the learner at the timing when the learner receives the answer to the question, the learner can smoothly work on overcoming the weak point according to the study plan. In this embodiment, the immediate response unit 11 proposes the following study plans to each of the learners at proficiency levels A and B, and has them study immediately according to the study plans. For proficiency level A, the learning plan involves having students immediately watch a lecture video on a weak area in order to review their basic skills, and then having them take a simple test to help them solidify their knowledge. For learners at proficiency level B, if they have basic skills but no application skills, they will not be able to solve problems equivalent to the actual test. Therefore, the learning plan for proficiency level B is to have learners first solve multiple problems, and then have them watch lectures on how to solve the problems they were unable to solve.

[0064] Next, a description will be given of the data collection process shown in Fig. 4. Fig. 7 is a flowchart showing an example of the procedure of the data collection process shown in Fig. 4. In step S401, when the setting unit 14 receives an evaluation of the answer from the information processing terminal 30, the setting unit 14 accepts the evaluation. In step S402, the setting unit 14 accumulates question and answer data that combines the question and the answer in the learning record data. In addition, the immediate answering unit 11 records the received information on the evaluation result in the learning record data. In this way, the evaluation of the answer is accumulated in the learning record data.

[0065] Next, a description will be given of the additional learning process by the learning unit 13. First, a case where the learning unit 13 performs fine tuning will be described. Fig. 8 is a flowchart showing an example of the procedure of the additional learning process executed by the learning unit shown in Fig. 1. In step S501, the learning unit 13 refers to the learning record data and extracts question and answer data with answers that have a rating of 5. In step S502, the learning unit 13 adds the extracted question and answer data to the learning data of the answer model. In step S503, the learning unit 13 performs fine tuning of the answer model using the learning data.

[0066] Next, a case will be described in which the learning unit 13 performs context learning. Fig. 9 is a flowchart showing another example of the procedure of the additional learning process executed by the learning unit shown in Fig. 1 . In step S601, the learning unit 13 refers to the learning record data and extracts question and answer data with answers that have a rating of 5. In step S602, the learning unit 13 adds the extracted question and answer data to the learning data of the answer model. In step S603, the learning unit 13 updates the prompt with the learning data.

[0067] The question receiving system 10 of the present embodiment can solve a problem in the related art, which will be referred to as problem 7. (Challenge 7: Uneven quality of answers) For example, during periods when many questions are concentrated, such as immediately before the actual exam, in addition to the instructor, people who have passed the actual exam may join the answering staff to help answer the questions. In this case, differences in knowledge and experience between the instructor and the answering staff can cause variations in the quality of the instructor's answers and the answering staff's answers.

[0068] (This embodiment for problem 7: generating answers of uniform quality) In the question receiving system 10 of this embodiment, the learning unit 13 updates an answer model that generates answers from questions by using question and answer data, which is a combination of an answer and a question that has a rating equal to or higher than a predetermined reference value among past answers, as learning data. Therefore, improvement in the quality of answers is maintained. Since the AI ​​unit 12 generates answers using the answer model, the quality of the generated answers is uniform. The reference value is, for example, rank 5 on a 5-point scale.

[0069] The learning unit 13 updates the answer model using answers rated at rank 5 among past answers. This modifies the algorithm for generating answers from questions, resulting in more optimal answers. To continue improving the quality of answers, the learner is asked to rate answers newly generated by the AI ​​unit 12 on a 5-point scale. The learning unit 13 then continues to add answers rated at rank 5 as learning data. This maintains improvement in the quality of answers.

[0070] (Main configuration and effects of the system of this embodiment) The question receiving system 10 of this embodiment includes a memory unit 15 that stores teaching material data, an AI unit 12 that generates an answer to the question based on the teaching material data when it receives a question about the teaching material data from the information processing terminal 30 of a learner 90 who is studying using the teaching material data, and an instantaneous answer unit 11 that reflects the characteristics of the learner 90 in the answer generated by the AI ​​unit 12 and outputs the answer to the information processing terminal 30.

[0071] According to this embodiment, an answer suited to the characteristics of the learner 90 can be provided immediately.

[0072] <Second embodiment> This embodiment allows learners of the same learning level or learning process to share question and answer data. In this embodiment, the same components as those described in the first embodiment are given the same reference numerals, and detailed description thereof will be omitted. The configuration of the question receiving system of this embodiment will be described with reference to Fig. 10. Fig. 10 is a block diagram showing an example of the configuration of the question receiving system according to the second embodiment.

[0073] As shown in FIG. 10, the question receiving system 10 of this embodiment has a question sharing unit 16 in addition to the instant answer unit 11, AI unit 12, learning unit 13, setting unit 14, and memory unit 15 shown in FIG.

[0074] Next, an operation of the question receiving system 10 of this embodiment will be described. Fig. 11 is a flowchart showing an example of an operation procedure of the question receiving system according to the second embodiment. In step S701, the question sharing unit 16 extracts, from the learning record data, question and answer data evaluated as rank 5. In step S702, the question sharing unit 16 refers to the learning record data and determines the learning process of the learner. In step S703, the question sharing unit 16 refers to the learning record data and determines the learning level of the learner. In step S704, based on the learning process and learning level of the learner, the question and answer data to be shared by the learner is selected from the learning record data.

[0075] The question receiving system 10 of the present embodiment can solve a problem in the past. The problem in the past will be referred to as problem 8. (Issue 8: Learners cannot share questions with other students) When people start studying for a qualification exam, they tend to have similar doubts or questions about the same area of ​​study. If multiple students can share answers to the doubts or questions that many students have, the learning efficiency of each student will improve. On the other hand, if students were to share answers to all questions with each other, the number of accumulated questions would be so huge that students would have to search through the huge number of questions to find questions that are relevant to their studies, which would take time. Also, if students thought that all the information in the accumulated "questions and answers" was useful and tried to look through all of the "questions and answers," they would end up looking through information that was not necessary, resulting in a waste of time. Therefore, it is desirable to provide information shared among students in a way that is tailored to the characteristics of each learner.

[0076] (This embodiment for assignment 8: Students with the same learning process share questions) The question receiving system 10 of the present embodiment provides a learner with question and answer data of other learners who are in the same learning process as the learner. The learner can share frequently asked questions or doubts and their answers with other learners according to the progress of his / her learning. Usually, the content of questions changes during the course of learning, even for the same learner. Here is a concrete example. When a learner starts studying for a qualification exam using a computer system, he or she asks many questions, such as how to use the study materials and not understanding the basic concepts of the subject to be studied. After that, the learner completes all the classes of the course and begins to understand the overall picture of the exam subjects. At this stage, the content of questions changes from the overall basic learning matters to the details. Then, at the final stage of the qualification exam study materials, the learner's main study is practicing past exam questions. At this stage, the content of questions changes to how to solve past exam questions or how to study before the actual exam. In this way, the content of learners' questions changes during the course of learning, so it is desirable for learners to share questions and answers from other learners who are at the same level of the study process with each other. Therefore, in this embodiment, as a rule, information on questions and answers from other learners at the same learning process is shared among learners at the same learning process. However, learners who have taken exams do not show the above-mentioned phenomenon of change in the content of questions. Therefore, as an exception, questions from learners who have taken exams are shared with other learners regardless of their learning process. In this embodiment, the learning process is divided into three parts, the first half, the middle part, and the second half, but the number of parts into which the learning process is divided is not limited to three.

[0077] (This embodiment for assignment 8: Students at the same learning level share questions) The question receiving system 10 of the present embodiment provides a learner with question and answer data of other learners who have a similar learning level to the learner. A learner can share frequently asked questions or doubts and their answers that are appropriate for his or her own learning level with other learners. The content of learners' questions varies depending on the learner's learning level. Learners with a high learning level tend to ask high-quality questions. Learners with a low learning level feel inferior when they read high-quality questions, thinking that their learning level is still low. On the other hand, learners with low academic ability tend to ask low-quality questions. Low-quality questions are often not helpful to learners with a high learning level. For this reason, it is desirable for learners with similar learning levels to share information about questions and answers. Therefore, in this embodiment, learning levels are divided into three ranks, high, medium, and low, and questions and their answers are shared among learners of the same rank. The learning levels of each learner are ranked, for example, according to the results of tests administered in the learning curriculum, and are registered in the learning record data. In this embodiment, the learning levels are divided into three ranks. However, the number of ranks of the learning levels is not limited to three.

[0078] <Additional Notes> The above-described embodiments are illustrative examples of the present invention, and are not intended to limit the scope of the present invention to these embodiments. Those skilled in the art can implement the present invention in various other forms without departing from the scope of the present invention.

[0079] The above-described embodiment includes the following features. However, the features included in the embodiment are not limited to the following features.

[0080] (Item 1) A storage unit for storing teaching material data; an artificial intelligence unit that, when receiving a question about the teaching material data from an information processing terminal of a learner who is studying using the teaching material data, generates an answer to the question based on the teaching material data; a response unit that reflects characteristics of the learner in the response generated by the artificial intelligence unit and outputs the response to the information processing terminal; A question reception system having the above configuration. This makes it possible to instantly provide answers suited to the learner's characteristics.

[0081] (Item 2) the storage unit stores information on evaluations made by other learners different from the learner with respect to answers given in the past to the same question as the question received from the information processing terminal; The answering section: outputting, to the information processing terminal, answers among the previously given answers whose evaluation is equal to or exceeds a predetermined reference value; Item 1. A question reception system. This allows for instantaneous provision of answers that have been highly rated in the past to the same question.

[0082] (Item 3) the storage unit stores information on a virtual instructor, which is a virtual person imitating an instructor and reflects the learner's preferences; the answering unit causes the virtual instructor to output the answer to the information processing terminal; A question reception system according to item 1 or 2. This allows learners to get answers to their questions from a virtual instructor of their choice, which increases their motivation to learn.

[0083] (Item 4) The storage unit stores information on a learning level as the characteristic of the learner, The answering section: selecting content corresponding to the learning level as the answer to be output to the information processing terminal; 4. A question reception system according to any one of items 1 to 3. This allows the learner to easily understand the answer since the answer is suited to his / her own learning level.

[0084] (Item 5) The storage unit stores strengths and weaknesses information, which is information on the learner's strengths and weaknesses, for a learning subject; The answering section: selecting content corresponding to the strengths and weaknesses information as the answer to be output to the information processing terminal; 4. A question reception system according to any one of items 1 to 3. This allows the learner to obtain answers that are tailored to his or her strengths and weaknesses, and thus allows the learner to understand the content of the answers.

[0085] (Item 6) The storage unit stores a learning plan corresponding to each of a plurality of proficiency levels for a learning subject, The artificial intelligence unit determines the proficiency level of the learner from the plurality of proficiency levels based on the question, When outputting the answer to the information processing terminal, the answering unit outputs the learning plan corresponding to the proficiency level determined by the artificial intelligence unit to the information processing terminal. 6. A question reception system according to any one of items 1 to 5. This allows learners to not only get answers to their questions, but also obtain a study plan that suits their own learning level, thereby improving their learning proficiency.

[0086] (Item 7) A learning unit is provided for updating an answer model, which is a model for generating an answer from a question, based on learning data; The artificial intelligence unit generates the answer to the question using the answer model; the storage unit stores question and answer data, which is a combination of questions previously received and answers to the questions, and information on evaluations of the answers included in the question and answer data; The learning unit is updating the answer model using, as the learning data, the question and answer data including answers whose evaluation is equal to or higher than a predetermined reference value, among the question and answer data stored by the storage unit; 7. A question receiving system according to any one of items 1 to 6. This allows the answer model to be updated based on answers that have been highly evaluated in the past, improving the quality of answers generated from questions, and allowing learners to obtain higher quality answers.

[0087] (Item 8) The artificial intelligence unit is when receiving the question from the learner, the question including data in at least one data format of text, audio, still image, and video, generating the answer corresponding to the question based on the teaching material data; 8. A question reception system according to any one of items 1 to 7. This allows the learner to ask questions in a variety of data formats.

[0088] (Item 9) The artificial intelligence unit is receiving the question from the learner, the question including data in at least one data format of text, audio, still image, and video image, analyzing the learner's emotion from the question; The answering section: causing the artificial intelligence unit to create an answer corresponding to the result of the analysis as the characteristic of the learner based on the answer; 9. A question reception system according to any one of items 1 to 8. This allows learners to get answers that are in tune with their own feelings.

[0089] (Item 10) the storage unit stores, for each of the plurality of learners, learning record data in which the learning process of the learner and question and answer data which is a combination of the questions and the answers of the learners are recorded; The answering section: When transmitting the answer to the information processing terminal of the learner, determining the learning process of the learner by referring to the learning record data; reading out the question and answer data of other learners who are in the same learning process as the determined learning process from the learning record data; transmitting the read question and answer data to the information processing terminal; 10. A question reception system according to any one of items 1 to 9. This allows learners to share questions and their answers with other learners who are in the same learning process as themselves.

[0090] the storage unit stores, for each of the plurality of learners, learning record data in which a learning level of the learner and question answer data which is a combination of the question and the answer are recorded; The answering section: When transmitting the answer to the information processing terminal of the learner, the learning level of the learner is determined by referring to the learning record data; reading out the question and answer data of other learners having the same learning level as the determined learning level from the learning record data; transmitting the read question and answer data to the information processing terminal; 10. A question reception system according to any one of items 1 to 9. This allows learners to share questions and their answers with other learners at the same learning level as themselves. [Explanation of symbols]

[0091] 10 question reception system, 11 real-time answer section, 12 AI (artificial intelligence) section, 13 learning section, 14 setting section, 15 memory section, 16 question sharing section, 20 server, 21 processing section, 22 main memory, 23 storage device, 24 communication device, 25 input device, 26 display device, 27 bus, 30 information processing terminal, 31 camera, 32 microphone, 33 speaker, 34 display, 35 browser.

Claims

1. A memory unit for storing teaching material data for a course; an artificial intelligence unit which, when receiving a question about the teaching material data from an information processing terminal of a learner who is taking the course via a network and studying using the teaching material data, generates an answer to the question based on the teaching material data; a response unit that reflects characteristics including a learning level and a learning process of the learner in the response generated by the artificial intelligence unit and transmits the response to the information processing terminal; having the storage unit stores, for each of the plurality of learners, learning record data in which the learning level and learning process of the learner and question and answer data which is a combination of the questions and the answers of the learners are recorded; The answering section: When transmitting the answer to the information processing terminal of the learner, referring to the learning record data, a learning level and a learning process of the learner are determined; reading out the question and answer data of another learner who has the same learning level and the same learning process as the determined learning level from the learning record data; transmitting the read question and answer data to the information processing terminal; Question reception system.

2. the storage unit stores information on evaluations made by other learners different from the learner with respect to answers given in the past to the same question as the question received from the information processing terminal; The answering section: outputting, to the information processing terminal, answers among the previously given answers whose evaluation is equal to or exceeds a predetermined reference value; The question receiving system according to claim 1.

3. the storage unit stores information on a virtual instructor, which is a virtual person imitating an instructor and reflects the learner's preferences; the answering unit causes the virtual instructor to output the answer to the information processing terminal; The question receiving system according to claim 1.

4. The storage unit stores a learning plan corresponding to each of a plurality of proficiency levels for a learning subject, The artificial intelligence unit determines the proficiency level of the learner from the plurality of proficiency levels based on the question, When outputting the answer to the information processing terminal, the answering unit outputs the learning plan corresponding to the proficiency level determined by the artificial intelligence unit to the information processing terminal. The question receiving system according to claim 1 .

5. A learning unit is provided for updating an answer model, which is a model for generating answers from questions, based on learning data; The artificial intelligence unit generates the answer to the question using the answer model; the storage unit stores question and answer data, which is a combination of questions previously received and answers to the questions, and information on evaluations of the answers included in the question and answer data; The learning unit is updating the answer model using, as the learning data, the question and answer data including answers whose evaluation is equal to or higher than a predetermined reference value among the question and answer data stored in the storage unit; The question receiving system according to claim 1.

6. The artificial intelligence unit is when receiving the question from the learner, the question including data in at least one data format of text, audio, still image, and video, generating the answer corresponding to the question based on the teaching material data; The question receiving system according to claim 1 .

7. A question receiving method executed by an information processing device, comprising: storing teaching material data for a course and learning record data in which the learning levels and learning processes of a plurality of learners who study using the teaching material data, as well as question and answer data which are combinations of questions and answers, of the learners are recorded; when a question about the teaching material data is received from an information processing terminal of a learner taking the course via a network, an answer to the question is generated based on the teaching material data; reflecting characteristics including the learning level and learning process of the learner in the generated answer and transmitting the answer to the information processing terminal; When transmitting the answer to the information processing terminal of the learner, determining the learning level and learning process of the learner by referring to the learning record data; reading out the question and answer data of another learner who has the same learning level and the same learning process as the determined learning level from the learning record data; transmitting the read question and answer data to the information processing terminal; How to receive questions.

Images