System, program, and information processing method

Abstract

To support learning of a user.SOLUTION: A system 1 according to an embodiment of the present disclosure comprises: a consultation-content acquisition unit 100a which acquires consultation content regarding learning that is input to a terminal device 3 of a user; a praise information acquisition unit 100b which acquires praise information that praises the user in relation to the consultation content; a response information acquisition unit 100c which acquires response information indicating a response to the consultation content; an output unit 104 which can output the praise information and the response information; a praise condition determination unit (determination unit 106) which determines whether or not predetermined conditions regarding output of the praise information are satisfied; and a praise restriction unit (restriction unit 108) which restricts at least one of the output of the praise information by the output unit 104 and the acquisition of the praise information by the praise information acquisition unit 100b on the basis of a determination result by the praise condition determination unit (determination unit 106).SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a system, a program, and an information processing method. [Background technology]

[0002] Conventionally, there are known techniques for computers to answer user questions. For example, Patent Document 1 describes an information processing device that can answer a plurality of patterns of fact-type questions. According to Patent Document 1, the information processing device can flexibly answer various types of fact-type questions.

[0003] However, the technology described in Patent Document 1 cannot fully support the user's learning. For example, there is room for further consideration regarding responses to the user's inquiries. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-85873 Summary of the Invention [Problem to be solved by the invention]

[0005] The present disclosure aims to provide a system, a program, and an information processing method that can support a user's learning. [Means for solving the problem]

[0006] A system according to one aspect of the present disclosure includes a consultation content acquisition unit that acquires consultation content related to learning input to a user's terminal device, a praise information acquisition unit that acquires praise information praising the user in relation to the consultation content, an answer information acquisition unit that acquires answer information indicating an answer to the consultation content, an output unit that can output praise information and answer information, a praise condition determination unit that determines whether a predetermined condition regarding the output of praise information is satisfied, and a praise restriction unit that restricts at least one of the output of praise information by the output unit and the acquisition of praise information by the praise information acquisition unit based on the determination result by the praise condition determination unit.

[0007] A system according to another aspect of the present disclosure includes a consultation content acquisition unit that acquires consultation content related to learning input to a user's terminal device; a first response information acquisition unit that acquires first response information indicating a first response to the consultation content, where the first response information is acquired by inputting a first instruction including the consultation content to a first model that is compatible with natural language processing; a second response information acquisition unit that acquires second response information indicating a second response to the consultation content, where the second response information is acquired by inputting a second instruction including the consultation content to a second model that has learned one or more educational content that is restricted from learning by the first model; and an output unit that is capable of outputting the first response information and the second response information.

[0008] A program according to another aspect of the present disclosure causes a computer to function as a consultation content receiving means for receiving input of consultation content related to learning, a praise information acquiring means for acquiring praise information praising the user in relation to the consultation content, a response information acquiring means for acquiring response information indicating an answer to the consultation content, and an output means capable of outputting the praise information and the answer information, wherein the output of the praise information or acquisition by the praise information acquiring means is restricted based on the result of a determination as to whether or not a predetermined condition regarding the output of the praise information is satisfied.

[0009] An information processing method according to another aspect of the present disclosure has a computer execute a consultation content acquisition step of acquiring consultation content related to learning input to a user's terminal device, a praise information acquisition step of acquiring praise information praising the user in relation to the consultation content, an answer information acquisition step of acquiring answer information indicating an answer to the consultation content, a transmission step of sending the praise information and the answer information to the terminal device, a determination step of determining whether or not predetermined conditions regarding the output of praise information in the terminal device are satisfied, and a restriction step of restricting at least one of performing the praise information acquisition step, sending the praise information in the transmission step, and outputting the praise information in the terminal device based on the determination result in the determination step. [Effects of the Invention]

[0010] According to the present disclosure, it is possible to support a user's learning. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram illustrating an example of an overview of a system 1. [Figure 2] FIG. 2 is a diagram illustrating an example of a functional configuration of the system 1. [Figure 3] 10 is a flowchart showing an example of the operation of the information processing device 2. [Figure 4] FIG. 10 is a diagram showing an example of a display screen of the terminal device 3. [Figure 5] FIG. 10 is a diagram showing an example of a display screen of the terminal device 3. [Figure 6] FIG. 2 is a diagram illustrating an example of hardware of an information processing device 2. [Figure 7] FIG. 10 is a diagram showing another example of a display screen of the terminal device 3. DETAILED DESCRIPTION OF THE INVENTION

[0012] <1. Overview> Generally, praising a learner is important to increase their motivation. However, excessive praise may hinder the original purpose of resolving questions. One of the purposes of the present disclosure is to maintain a balance between the timing of praise and what to praise, thereby achieving both increased motivation and smooth question resolution for the learner. In the explanation of this disclosure, the learner is assumed to be between elementary school and junior high school age, but the application of this disclosure is not limited to this. In the following explanation, the learner will be referred to as the "user."

[0013] 1 is a diagram showing an overview of a system 1 according to an embodiment. A user inputs a message, for example, "I don't understand division," to his / her terminal device 3. The terminal device 3 transmits the message to the information processing device 2 (S1). In response to receiving the message, the information processing device 2 determines whether to praise the user (S2).

[0014] If the information processing device 2 determines to praise the user, the information processing device 2 transmits a message praising the user, such as "Division is difficult, but you're doing a great job," to the terminal device 3 (S3). The information processing device 2 further transmits to the terminal device 3 a message saying "This video explains division in an easy-to-understand way," along with a web link or the like of video data explaining how to calculate division (S4).

[0015] On the other hand, if the information processing device 2 determines not to praise the user, the information processing device 2 performs the process described in S4 without performing the process described in S3 (i.e., without sending a message praising the user to the terminal device 3).

[0016] That is, the information processing device 2 constantly responds to the user's consultation content (see S4), while controlling whether to praise the user based on a predetermined determination (see S2). In this way, the information processing device 2 can maintain a balance between praising and not praising, and increase the user's motivation to study.

[0017] The detailed configuration and operation of the system 1 including the information processing device 2 will be described below.

[0018] <2. Functional configuration> The functional configuration of the system 1 will be described with reference to Figure 2. The system 1 includes an information processing device 2, a terminal device 3, an NLP (Natural Language Processing) server device 5a, a teaching material presentation server device 5b, and communication networks 6a and 6b. The information processing device 2 and the terminal device 3 are configured to be able to communicate with each other via the communication network 6a. The information processing device 2, the NLP server device 5a, and the teaching material presentation server device 5b are configured to be able to communicate with each other via the communication network 6b. Note that the communication networks 6a and 6b may be networks connected to each other. Hereinafter, when there is no need to particularly distinguish between the communication networks 6a and 6b, they will be collectively referred to as the "communication network 6."

[0019] [NLP server device 5a] The NLP server device 5a is a device that stores a model suitable for natural language processing (hereinafter referred to as an "NLP model"). The NLP server device 5a acquires predetermined information and outputs the result of inputting the predetermined information into the NLP model. For example, the NLP server device 5a acquires text data input by a user to the terminal device 3 and outputs the text data obtained by inputting the text data into the NLP model.

[0020] In one embodiment, the NLP server device 5a generates and outputs text data that praises the user in relation to the consultation content of the user in response to the consultation content of the user.

[0021] The NLP server device 5a may generate a praising phrase based on the content of the user's consultation, for example. Furthermore, the NLP server device 5a may generate text data praising the user in relation to the content of the consultation, for example, by the following processes (1) to (3). (1) Based on the content of the consultation, the subject or unit the user is trying to study (for example, "arithmetic" or "division") is identified. (2) Extract the characteristics of the identified subject or unit (e.g., "difficult," "many people have difficulty with it," etc.) (3) The results of (1) and (2) and a phrase that praises the user (for example, "You're doing a great job") are combined according to a predetermined rule. For example, in the example described in Figure 1, in response to the consultation content of "I don't understand division," the NLP server device 5a generates text data saying "Division is difficult, but you're doing well," and sends it as a message.

[0022] In one embodiment, the NLP model includes a large language model (LLM). In this case, the NLP server device 5a acquires an instruction (which may also be called a prompt) including the user's consultation content, inputs the instruction into the NLP model, which is a large language model, and outputs the result. Examples of the NLP model include ChatGPT, GPT-4, and BERT.

[0023] [Learning material presentation server device 5b] The teaching material presentation server device 5b is a device that stores a model (hereinafter referred to as a "teaching material presentation model") that has learned one or more teaching material contents. The teaching material presentation server device 5b acquires predetermined information and outputs the result of inputting the predetermined information into the teaching material presentation model. For example, the teaching material presentation server device 5b acquires text data that a user inputs into the terminal device 3 and outputs teaching material content determined by inputting the text data into the teaching material presentation model.

[0024] The learning material content includes content to support the user's learning. The learning material content is, for example, text data or video data that explains a specific unit of a specific subject, or success stories of senior learners. The learning material content may be any of text data, image data, video data, audio data, etc.

[0025] In one embodiment, the teaching material presentation model can refer to master information for determining (or searching) the teaching material content to be presented to the user from one or more teaching material contents. The master information may include search index information generated based on one or more teaching material contents. That is, the teaching material presentation model may refer to the search index information to determine the teaching material content to be presented to the user from one or more teaching material contents. An example of the teaching material presentation model is Microsoft® Azure® AI Search.

[0026] The search index information may include, for example, information associating the identification information of the learning material content with the contents of the text and / or images contained in the learning material content. In other words, the search index information can be said to include information indicating which of one or more learning material contents contains what content.

[0027] In one embodiment, the teaching material presentation model may learn data in which tags indicating the target audience and / or content of one or more teaching material contents are associated with each of the teaching material contents. The tags may be, for example, at least one of the subject, unit, medium (e.g., video data or text data), target grade, and difficulty level. In other words, the teaching material presentation model may learn which users and which consultation contents each of the one or more teaching material contents is suitable for. Furthermore, in one embodiment, the teaching material presentation model may learn information obtained by vectorizing and indexing text data, image data, audio data, etc. included in the teaching material contents.

[0028] In one embodiment, the learning material presentation server device 5b outputs learning material content that is estimated to be useful for solving the user's consultation. The learning material presentation server device 5b may determine the learning material content to be output, for example, by the following processes (1) and (2). (1) Based on the content of the consultation, the subject or unit the user is trying to study (for example, "arithmetic" or "division") is identified. (2) Determine the teaching material content associated with tags that are highly relevant to the identified subject or unit. For example, in the example described in FIG. 1, in response to the inquiry about "I don't understand division," the teaching material presentation server device 5b transmits to the terminal device 3 a web link to video data that explains how to calculate division.

[0029] In one embodiment, the teaching material presentation model includes a large-scale language model. In this case, the teaching material presentation server device 5b acquires an instruction including the content of the user's consultation, and outputs the result of inputting the instruction into the teaching material presentation model, which is a large-scale language model.

[0030] In the present disclosure, "the learning material presentation model learning the learning material content" may be, for example, at least one of the following (1) to (4). (1) The teaching material presentation model can refer to one or more teaching material contents in order to determine the teaching material contents to be presented to the user. (2) The teaching material presentation model can refer to index information generated based on one or more teaching material contents in order to determine the teaching material contents to be presented to the user. (3) The teaching material presentation model stores the relationship between one or more teaching material contents and tags, etc., associated with the teaching material contents. (4) The teaching material presentation model learns the actual content of the text data, etc., contained in the teaching material content, for example, by self-supervised learning.

[0031] Note that the teaching material presentation model in the present disclosure is not limited to a machine learning model, but may store, for example, in table or list format, the relationship between one or more teaching material contents and tags, etc., associated with the teaching material contents. In other words, "the teaching material presentation model learning the teaching material contents" is not limited to, for example, updating the weighting of the teaching material presentation model including a neural network based on the teaching material contents.

[0032] In one embodiment, the above-mentioned NLP model is limited in its learning of educational material content. The restriction on the learning of educational material content by the NLP model may mean that the NLP model is limited in its reference to educational material content, that the NLP model does not learn educational material content, or that the NLP model learns a smaller number or amount of educational material content compared to the educational material presentation model. In other words, the NLP model is a model specialized in praising the user in relation to the consultation content (rather than presenting educational material content), and the educational material presentation server device 5b is a model specialized in presenting educational material content that is estimated to be useful for resolving the consultation content.

[0033] [Information processing device 2] The information processing device 2 is a server device in the case where the terminal device 3 is a client terminal device. In one embodiment, the information processing device 2 is a web server device.

[0034] The information processing device 2 includes a control unit 10, a storage unit 12, a network interface unit 14, and a bus 16. The control unit 10, the storage unit 12, and the network interface unit 14 are electrically connected via the bus 16.

[0035] (Control unit 10) The control unit 10 functions as an acquisition unit 100, a determination unit 102, an output unit 104, a judgment unit 106, and a restriction unit 108 by executing various programs stored in the storage unit 12, which will be described later.

[0036] -Acquisition part 100- The acquisition unit 100 includes a consultation content acquisition unit 100a, a praise information acquisition unit 100b, and a response information acquisition unit 100c.

[0037] ~Consultation content acquisition unit 100a~ The consultation content acquisition unit 100a acquires consultation content related to learning input to the user's terminal device 3. The consultation content may be input as any of text data, image data, video data, and audio data.

[0038] ~Praise information acquisition unit 100b~ The praise information acquisition unit 100b acquires praise information that praises the user in relation to the consultation content acquired by the consultation content acquisition unit 100a. In one embodiment, the praise information acquisition unit 100b acquires praise information based on a list in which phrases corresponding to one or more consultation contents and / or keywords included in the consultation content are associated with the consultation contents and / or keywords. For example, the list associates the keywords "fractions," "decimals," and "turtle and crane calculation" with phrases such as "Fractions can be difficult, but it's impressive that you persevered," "Decimal points are difficult. Thanks for asking the question," and "Tortoise and crane calculation is a high-level problem. It would be amazing if you could master it!" In this case, for example, if the consultation content includes the keyword "fractions," the praise information acquisition unit 100b acquires the phrase "Fractions can be difficult, but it's impressive that you persevered," as praise information.

[0039] The consultation content may be a specific question about a particular subject and / or unit, or a general question or consultation about learning (e.g., "I can't concentrate," "I don't know how to study English," etc.).

[0040] In the present disclosure, "praising the user in relation to the consultation content" may mean praising, approving, or encouraging the user to work on the consultation content (including past work and future work). "Praising the user in relation to the consultation content" may also mean motivating the user to work on the consultation content.

[0041] In one embodiment, the praise information acquisition unit 100b acquires praise information by inputting a first instruction based on the consultation content acquired by the consultation content acquisition unit 100a as a prompt to the NLP model. In one embodiment, the first instruction further includes an instruction to motivate the user in addition to the consultation content. For example, the first instruction is, "The user's consultation content is XX. Please create a message that motivates the user while mentioning the consultation content."

[0042] ~Answer information acquisition part 100c~ The answer information acquiring unit 100c acquires answer information indicating answers to the consultation contents acquired by the consultation content acquiring unit 100a. In one embodiment, the answer information acquiring unit 100c acquires answer information based on a list in which answers corresponding to one or more consultation contents and / or keywords included in the consultation contents are associated with the consultation contents and / or keywords. For example, the list associates text data explaining how to solve fraction problems, text data explaining how to solve decimal problems, and text data explaining how to solve turtle and crane problems with each of the consultation contents, such as "fractions," "decimals," and "turtle and crane problems." In this case, if the consultation content includes the keyword "fraction," for example, the answer information acquiring unit 100c acquires text data explaining how to solve fraction problems as answer information.

[0043] In one embodiment, the answer information acquisition unit 100c acquires answer information by inputting a second instruction including the consultation content acquired by the consultation content acquisition unit 100a to the teaching material presentation model that has learned one or more teaching material contents. In this case, the answer information may include at least one of the one or more teaching material contents. Furthermore, the teaching material content included in the answer information may include at least one of image data and video data. For example, if the consultation content includes the keyword "fraction," the answer information may include video data that the teaching material presentation model has learned, which explains how to solve a fraction problem.

[0044] In one embodiment, the answer information includes a policy for resolving the consultation content acquired by the consultation content acquisition unit 100a. Furthermore, if a correct answer exists for the consultation content, the answer information may be restricted from including the answer. That is, the answer information acquisition unit 100c may acquire answer information that does not include a direct answer to the consultation content but includes advice for the user to solve the consultation content on their own. For example, if the consultation content includes text data such as "What is the answer to 3 divided by 5?", the answer information acquisition unit 100c may acquire answer information that includes educational content explaining how to perform division so that the answer is a decimal point, rather than the answer itself, 0.6.

[0045] In one embodiment, the second instruction further includes, in addition to the consultation content, an instruction to restrict the answer information from including an answer. For example, the second instruction is, "The user's consultation content is XX. Please output hints to help the user find the answer by themselves, without presenting a direct answer to the user's consultation content."

[0046] In the present disclosure, "obtaining information" includes making the information processable in the control unit 10. "Obtaining information" may mean receiving the information from another device, reading the information from the storage unit 12, or obtaining the information as a result of predetermined processing.

[0047] -Decision Unit 102- When a first keyword is included in the consultation content acquired by the consultation content acquisition unit 100a, the determination unit 102 determines a second keyword having a similar meaning to the first keyword. The second keyword is associated with at least one of one or more learning material contents. In other words, the determination unit 102 can be said to rephrase a first keyword that is not necessarily associated with a learning material content into a second keyword that is associated with the learning material content.

[0048] In this case, the answer information acquiring unit 100c acquires answer information including the learning material content associated with the second keyword. For example, if the consultation content includes any one of "division," "divide," "divide," and "÷" as the first keyword, the determining unit 102 determines "division," which has a similar meaning to any of these, as the second keyword, and the answer information acquiring unit 100c acquires answer information including the learning material content associated with the second keyword "division" (for example, video data explaining the basic calculation method of division).

[0049] -Output section 104- The output unit 104 is configured to be able to output the praise information acquired by the praise information acquisition unit 100b and the answer information acquired by the answer information acquisition unit 100c.

[0050] In one embodiment, the output unit 104 outputs the praise information and the answer information in a list. Outputting the praise information and the answer information in a list includes, for example, consecutively displaying a message corresponding to the praise information and a message corresponding to the answer information (see FIG. 4 described later). That is, the output unit 104 outputs the praise information and the answer information in a manner that allows the user to recognize the praise and the answer to the consultation content as a single unit.

[0051] In the present disclosure, "outputting information" may mean either making the information recognizable to a user or transmitting the information to another device. Making information recognizable to a user includes, for example, displaying the information on a display device and outputting the information as audio data through a speaker.

[0052] -Judgment section 106- The determination unit 106 determines whether or not a predetermined condition (hereinafter referred to as a "praise condition") related to the output of the praise information acquired by the praise information acquisition unit 100b is satisfied. The praise condition may be, for example, at least one of the following (1) to (3).

[0053] (1) The number of times that the output unit 104 outputs praise information within a predetermined period is equal to or less than a predetermined threshold. In other words, the number of times the user has been praised within the predetermined period has not reached the upper limit. For example, if the upper limit for the number of times that praise information is output per day (i.e., the number of times the user can be praised) is 10, it can be said that the praise condition is met when the number of times that praise information is output is 0 to 10, and that the praise condition is not met when the number of times is 11 or more.

[0054] (2) A predetermined period of time has passed since the output unit 104 most recently output the praise information. In other words, the user is not praised too frequently. For example, if the frequency at which the praise information is output is once every 10 minutes at most, it can be said that the praise condition is not satisfied before 10 minutes have passed since the praise information was output, but the praise condition is satisfied after 10 minutes have passed.

[0055] (3) The consultation content satisfies a predetermined condition. In this case, the predetermined condition may be, for example, that the consultation content corresponds to the user's appropriate learning level, and that the number of characters in the consultation content is equal to or greater than a predetermined threshold. Whether the consultation content corresponds to the user's appropriate learning level may be determined based on the target grade corresponding to the consultation content and the user's grade included in the user information. For example, if the consultation content from a sixth-grade user is clearly below the standard level for a sixth-grade user, such as "What is 1 + 2?", the determination unit 106 may determine that the consultation content does not correspond to the user's appropriate learning level.

[0056] -Restricted section 108- The limiting unit 108 limits praise for the user when the determining unit 106 determines that the praise condition is not satisfied. Specifically, when the determining unit 106 determines that the praise condition is not satisfied, the limiting unit 108 limits at least one of (1) the output unit 104 from outputting praise information and (2) the praise information acquiring unit 100b from acquiring praise information. On the other hand, when the determining unit 106 determines that the praise condition is satisfied, the limiting unit 108 does not impose any of the above restrictions (1) and (2).

[0057] The limiting unit 108 may limit the output of praise information by the output unit 104 in any of the following cases (1) to (3). (1) Controlling the output unit 104 so that it does not output praise information. (2) Reducing the amount of praise information output by output unit 104. For example, when the output of praise information is not restricted, a message of about 100 characters is output as praise information, and when the output of praise information is restricted, a message of about 30 characters is output as praise information. In addition, when the output of praise information is not restricted, image data and stamps are output as praise information in addition to text data, and when the output of praise information is restricted, only text data is output. (3) Reducing the probability that the output unit 104 outputs praise information. For example, when the output of praise information is not restricted, the output unit 104 outputs praise information with a 100% probability, and when the output of praise information is restricted, the output unit 104 outputs praise information with a 30% probability.

[0058] (Storage unit 12) The storage unit 12 stores various programs executed by the control unit 10. The storage unit 12 further stores a teaching material content information DB 120, a keyword information DB 122, and a user information DB .

[0059] -Teaching material content information DB120- The educational content information DB 120 stores information related to educational content. The educational content information DB 120 stores data indicating the actual content of the educational content (e.g., text data, image data, video data, etc.) and tags of the educational content (e.g., subject, unit, medium, target grade, difficulty level, etc.) in association with the identification information of the educational content.

[0060] -Keyword Information DB122- The keyword information DB 122 stores information regarding the correspondence between first keywords and second keywords, and information regarding the correspondence between second keywords and educational content. The keyword information DB 122 may further store information regarding the relationship between the first keywords and / or second keywords and the school year in which units related to the first keywords and / or second keywords are taught. For example, the keyword information DB 122 may store the keyword "division" in association with the school year "third grade of elementary school," which is the school year in which division begins to be taught.

[0061] -User Information DB124- The user information DB 124 stores user information, which includes at least some of the user's information such as identification information, grade, weak subjects or units, and goals.

[0062] (Network Interface Unit 14) The network interface unit 14 realizes communication with other devices or systems via the communication network 6 .

[0063] [Terminal device 3] The terminal device 3 is a device used by a user to use the system 1. The terminal device 3 is configured to be able to communicate with the information processing device 2 via a communication network 6. The terminal device 3 is, for example, a personal computer, a smartphone, a tablet terminal, etc. The terminal device 3 includes an input device (for example, a mouse, a keyboard, a touch panel, a camera, a microphone, etc.) and an output device (for example, a display, a speaker, etc.). In one embodiment, the terminal device 3 communicates with the information processing device 2 by executing dedicated application software.

[0064] [Communication Network 6] The communication network 6a realizes communication between the information processing device 2 and the terminal device 3. The communication network 6b realizes communication between the information processing device 2, the NLP server device 5a, and the teaching material presentation server device 5b. The communication network 6 realizes communication based on, for example, the TCP / IP protocol.

[0065] <3.Operation> 3-5, an example of the operation of the information processing device 2 will be described. Fig. 3 is a flowchart showing an example of the operation of the information processing device 2. In this example, the information processing device 2 will be described as acquiring praise information from an NLP server device 5a that stores an NLP model, which is a large-scale language model, and acquiring answer information from a learning material presentation server device 5b that stores a learning material presentation model, which is a large-scale language model different from the NLP model.

[0066] First, the information processing device 2 acquires the consultation content input to the terminal device 3 used by the user (S100). In this example, it is assumed that the information processing device 2 acquires the consultation content including text data such as "I don't know how to divide 5 by 8."

[0067] Next, the information processing device 2 executes, in parallel, a step group (S10) relating to outputting praise information and a step group (S20) relating to outputting answer information.

[0068] [Steps related to outputting praise information (S10)] In the step group related to the output of praise information, the information processing device 2 first determines whether the praise condition is satisfied (S102). If it is determined that the praise condition is not satisfied (S102 NO), the information processing device 2 ends the step group related to the output of praise information. In this case, the information processing device 2 does not acquire or output praise information.

[0069] On the other hand, if it is determined that the praise condition is satisfied (S102 YES), the information processing device 2 determines a first instruction based on the consultation content acquired in S100 (S104). In this example, the first instruction is text data saying, "The user's consultation content is 'I don't know how to divide 5 by 8.' Please create a message that motivates the user while referring to the consultation content."

[0070] The information processing device 2 transmits the first instruction determined in S104 to the NLP server device 5a and acquires the response as praise information (S106). In this example, the information processing device 2 acquires praise information including text data such as "You're working hard on division right now. Division is difficult, but it's great that you're trying so hard!" as a response to the first instruction from the NLP server device 5a.

[0071] The information processing device 2 transmits the praise information acquired in S106 to the terminal device 3 (S108).

[0072] [Steps for outputting response information (S20)] In the step group related to outputting answer information, the information processing device 2 first determines a second keyword having a similar meaning to the first keyword based on the first keyword included in the consultation content (S200). In this example, since the consultation content includes text data of "÷", the information processing device 2 refers to the keyword information DB 122 and determines "division" corresponding to the first keyword "÷" as the second keyword.

[0073] The information processing device 2 determines a second instruction based on the consultation content acquired in S100 and the second keyword determined in S200 (S202). In this example, the second instruction is text data that reads, "The user's consultation content is 'I don't know how to divide 5 by 8.' Please output hints to help the user arrive at the answer by themselves, without presenting a direct answer to the user's consultation content. Also, please present educational content related to 'division.'"

[0074] The information processing device 2 transmits the second instruction determined in S202 to the learning material presentation server device 5b and acquires the response as answer information (S204). In this example, the information processing device 2 acquires, as a response to the second instruction from the learning material presentation server device 5b, answer information including text data saying "I've looked for a recommended explanation that might solve the problem!" and a link to play learning material content about the calculation method for "division."

[0075] The information processing device 2 transmits the answer information acquired in S204 to the terminal device 3 (S206).

[0076] 4 is a diagram showing an example of a display screen of the terminal device 3 when the praise condition is satisfied (i.e., when S102 is YES). The example display screen of FIG. 4 displays an icon d100, an icon d102, an icon d104, a message m100, a message m102, a message m104, a text box d116, and a send button d118.

[0077] The icon d100 corresponds to the user, while the icons d102 and d104 correspond to virtual characters that provide advice to the user.

[0078] The message m100 indicates the content of the user's inquiry, and in this example, it displays "I don't know how to divide 5 by 8" (see S100). The message m100 is displayed in association with the icon d100.

[0079] Message m102 indicates praise information received by terminal device 3 from information processing device 2, and in this example, it displays "You're working hard on division right now. Division is difficult, but it's great that you're trying so hard!" (See S108). Message m102 is displayed in association with icon d102.

[0080] The message m104 indicates the answer information that the terminal device 3 received from the information processing device 2, and together with text data d105 saying, "I've looked for some recommended explanations that may solve your problem!", the educational material content d106, the additional consultation button d112, and the additional consultation button d114 are displayed (see S206). The message m104 is displayed in association with the icon d104.

[0081] The educational content d106 includes a title d108 and a play button d110. The title d108 indicates the title of the educational content, and in this example is displayed as "[Explanation] How to calculate division that results in a decimal." The play button d110 is a button that the user can press to play video data that is the educational content.

[0082] The additional consultation button d112 and the additional consultation button d114 are buttons that, when pressed by the user, allow further consultation corresponding to the pressed button. For example, the additional consultation button d112 displays "How to enter a decimal point," and when the user presses this button, further answer information can be obtained with "How to enter a decimal point" as the additional consultation content. Furthermore, the additional consultation button d114 displays "Other explanations," and when the user presses this button, answer information including other educational content related to "division" can be obtained.

[0083] The text box d116 is an element that allows the user to freely input new or additional consultation content. The send button d118 is a button that the user can press to obtain further answer information as the text data entered in the text box d116 as new or additional consultation content.

[0084] 5 is a diagram showing an example of a display screen of the terminal device 3 when the praise condition is not satisfied (i.e., when S102 is NO). In the example of the display screen of FIG. 5, the icon d102 and the message m102 indicating the praise information are not displayed, unlike the example of the display screen of FIG. 4.

[0085] <4. Effects> A system 1 according to one embodiment of the present disclosure includes a consultation content acquisition unit 100a that acquires consultation content related to learning input to a user's terminal device 3, a praise information acquisition unit 100b that acquires praise information praising the user in relation to the consultation content, a response information acquisition unit 100c that acquires response information indicating a response to the consultation content, an output unit 104 that outputs the praise information and the response information, a judgment unit 106 that judges whether or not predetermined conditions regarding the output of the praise information are satisfied, and a restriction unit 108 that restricts at least one of the output of praise information by the output unit 104 and the acquisition of praise information by the praise information acquisition unit 100b based on the judgment result by the judgment unit 106.

[0086] With this configuration, the system 1 can strike a balance between giving praise and not giving praise, and can efficiently increase the user's motivation to study.

[0087] In one embodiment, the predetermined condition includes a condition regarding the number of times the output unit 104 outputs praise information per unit period.

[0088] Praising a user too much in a short period of time can easily cause the negative effects of praising, as described above in <1. Overview>. This configuration limits how much praise a user can receive in a short period of time, thereby more efficiently increasing the user's motivation to study.

[0089] In one embodiment, the praise information acquiring unit 100b acquires the praise information by inputting a first instruction including the consultation content to an NLP model suitable for natural language processing.

[0090] This configuration allows the system 1 to praise the user in relatively human-like sentences rather than in formulaic sentences, thereby more efficiently increasing the user's motivation to study.

[0091] In one embodiment, the answer information acquisition unit 100c acquires answer information by inputting a second instruction including the consultation content to a learning material presentation model that has learned one or more learning material contents. Also, in one embodiment, learning of one or more learning material contents by the NLP model is restricted. Also, in one embodiment, the answer information includes at least one of the one or more learning material contents.

[0092] Responses to consultation content require higher reliability than praising the user in relation to the consultation content. In this regard, a typical NLP model may suffer from so-called hallucination, which may result in providing erroneous information to the user. With this configuration, the response information is provided by a learning material presentation model that has learned predetermined learning material content, allowing the system 1 to provide more reliable responses to the user.

[0093] In one embodiment, the consultation content includes a first keyword, and the system 1 further includes a determination unit 102 that determines a second keyword having a similar meaning to the first keyword, where the second keyword may be associated with at least one of one or more educational content items, and the response information includes educational content items associated with the second keyword from among the one or more educational content items.

[0094] In particular, users with little learning experience are likely to find themselves in a situation where they don't know what they don't understand or how to ask for help. With this configuration, the first keywords entered by the user are rephrased as second keywords before the learning material content is determined, making it possible to present appropriate learning material content for a wide range of user inputs. As a result, it is possible to more efficiently support the user's learning.

[0095] In one embodiment, the one or more instructional content items include at least one of an image and a video.

[0096] This configuration allows the system 1 to provide educational content that is easier for users to understand.

[0097] In one embodiment, the answer information may include a policy for resolving the consultation content. Furthermore, if there is a correct answer to the consultation content, the answer information may be restricted from including the answer.

[0098] Providing a direct answer to a question can hinder a user's learning and reduce their motivation to learn. With this configuration, the system 1 can facilitate learning while cultivating the user's ability to think for themselves.

[0099] The above-described effects are merely examples and do not limit the scope of application of the present disclosure.

[0100] <5. Hardware Configuration> 6, an example of a hardware configuration in which each device included in the above-described system 1 is realized by a computer 70 will be described. Note that the functions of each device can also be realized by dividing them into multiple devices.

[0101] As shown in FIG. 6, the computer 70 includes a processor 700 , a storage device 702 , an input I / F 704 , a data I / F 706 , a communication I / F 708 , and a display device 710 .

[0102] The processor 700 controls various processes in the computer 70 by executing programs stored in the storage device 702. For example, each functional unit included in the control unit 10 of the information processing device 2 can be realized by the processor 700 executing the programs stored in the storage device 702.

[0103] The storage device 702 is a storage medium such as a RAM (Random Access Memory), etc. The RAM temporarily stores the program code of the program executed by the processor 700 and data required when the program is executed.

[0104] The storage device 702 may also be a non-volatile storage medium such as a hard disk drive (HDD) or flash memory. The storage device 702 stores an operating system and various programs for implementing the above-described configurations. The storage medium storing the various programs may be a non-transitory computer-readable medium. The storage device 702 may also store tables that register various types of information and a DB that manages the tables. Such programs and data are loaded into the storage device 702 as needed and referenced by the processor 700.

[0105] The input I / F 704 is a device for receiving input from a user. Specific examples of the input I / F 704 include a camera, a button, a microphone, a keyboard, a mouse, a touch panel, various sensors, and a wearable device. The input I / F 704 may be connected to the computer 70 via an interface such as a USB (Universal Serial Bus).

[0106] The data I / F 706 is a device for inputting data from outside the computer 70. A specific example of the data I / F 706 is a drive device for reading data stored in various storage media. The data I / F 706 may be provided outside the computer 70. In this case, the data I / F 706 is connected to the computer 70 via an interface such as a USB.

[0107] The communication I / F 708 is a device for performing data communication with devices external to the computer 70 via the communication network 6, either wired or wirelessly. The communication I / F 708 may be provided external to the computer 70. In this case, the communication I / F 708 is connected to the computer 70 via an interface such as a USB.

[0108] The display device 710 is a device for displaying various types of information. Specific examples of the display device 710 include a liquid crystal display, an organic EL (Electro-Luminescence) display, and a display of a wearable device. The display device 710 may be provided outside the computer 70. In this case, the display device 710 is connected to the computer 70 via, for example, a display cable. Furthermore, when a touch panel is adopted as the input I / F 704, the display device 710 can be configured as an integral part of the input I / F 704.

[0109] Furthermore, the components of each device included in the system 1 described in the above embodiment are assumed to realize predetermined processing in cooperation with other hardware when a program stored in the storage device 702 is executed by the processor 700. In other words, these components are envisioned as both software or firmware and the corresponding hardware, and in both of these concepts, they are also referred to as "functions," "means," "parts," "processing circuits," "units," or "modules," and can be interpreted as such.

[0110] <6. Variations> The matters described in the above embodiment can be changed as appropriate within a range that does not cause inconsistencies.

[0111] An information processing device 2 according to another aspect of the present disclosure includes a consultation content acquisition unit 100a that acquires consultation content related to learning input to a user's terminal device 3, a first response information acquisition unit that acquires first response information indicating a first response to the consultation content, a second response information acquisition unit that acquires second response information indicating a second response to the consultation content, and an output unit 104 that outputs the first response information and the second response information. The first response information is acquired by inputting a first instruction including the consultation content to an NLP model. The second response information is acquired by inputting a second instruction including the consultation content to a learning material presentation model. In the above embodiment, an example has been described in which the information processing device 2 includes the determination unit 106 and the restriction unit 108. However, the information processing device 2 does not necessarily have to include the determination unit 106 and the restriction unit 108.

[0112] Fig. 7 is a diagram showing an example of a display screen of the terminal device 3 that displays the first answer information and the second answer information. The example display screen of Fig. 7 displays icons d200, d202, d204, messages m200, m202, m204, number of remaining questions d210, text box d212, and send button d214. Of these, icons d200, d202, d204, text box d212, and send button d214 may be similar to icons d100, d102, d104, text box d116, and send button d118 described with reference to the example display screen of Fig. 5, and therefore description thereof will be omitted below.

[0113] The message m200 indicates the content of the user's consultation, and in this example, it displays "I can't maintain my concentration." In the above embodiment, an example was described in which the content of the consultation mainly relates to a specific subject or unit, but in this way, the content of the consultation may be a general one related to learning.

[0114] Message m202 shows an example of first response information obtained by inputting a first instruction including the consultation content to the NLP model, and displays the following message: "It's hard to concentrate for a long period of time. It's important to decide on a period of time to concentrate and set aside time for breaks. For example, it might be a good idea to study at a rhythm of studying for 50 minutes and then taking a 10-minute break!"

[0115] Message m204 shows an example of second answer information acquired by inputting a second instruction including the consultation content to the teaching material presentation model, and displays a testimonial display button d206 and a testimonial display button d208 together with text data saying, "Let's take a look at the success story of a senior who had difficulty concentrating!" The testimonial display button d206 displays "Mr. A passed XX junior high school," and the testimonial display button d208 displays "Mr. B passed XX junior high school." The testimonial display button d206 and the testimonial display button d208 are buttons that, when pressed by the user, can display Mr. A's success story and Mr. B's success story, respectively. In the above embodiment, an example has been described in which the teaching material content is mainly related to how to solve problems in a specific subject or unit, but such success stories are also an example of teaching material content.

[0116] The remaining number of questions d210 indicates the number of times the user can ask new or additional questions within a predetermined period. In this example, the remaining number of questions d210 displays "Number of remaining questions today: 9 / 10 this month: 39 / 40." This indicates that the user can ask another 9 new or additional questions within the same day, and another 39 new or additional questions within the same month. In other words, if the user asks 11 or more questions within the same day, the output of the first answer information and the second answer information is restricted.

[0117] To abstract this, system 1 may further include an answer condition determination unit that determines whether or not predetermined conditions (which may also be called "answer conditions") regarding the output of first answer information and second answer information are satisfied, and an answer restriction unit that, based on the determination result by the answer condition determination unit, restricts at least one of the output unit 104 from outputting the first answer information, the output unit 104 from outputting the second answer information, the first answer information acquisition unit from acquiring the first answer information, and the second answer information acquisition unit from acquiring the second answer information.

[0118] As in this example, when the consultation content is general learning-related, it is important for the user to take action in line with the advice. Therefore, by setting a limit on the number of consultations within a specified period depending on the type of consultation content, it is possible to adequately listen to the user's consultation while preventing the user from continuing to consult beyond an appropriate level and encouraging them to take action.

[0119] In the above embodiment, an example has been described in which the information processing device 2 communicates with the NLP server device 5a and the learning material presentation server device 5b to acquire praise information and response information, but this is not limiting. For example, the information processing device 2 may store an NLP model and a learning material presentation model in the storage unit 12 and use them to acquire praise information and response information.

[0120] In the above embodiment, an example in which the information processing device 2 executes a series of processes according to the present disclosure has been described, but this is not limiting. For example, the control unit of the terminal device 3 may function as at least a part of the acquisition unit 100, the determination unit 102, the output unit 104, the judgment unit 106, and the restriction unit 108 described in the above embodiment. Furthermore, a storage unit of the terminal device 3 may store an NLP model and a learning material presentation model, and the terminal device 3 may use these to acquire praise information and response information. That is, each function of the system 1 may be implemented in the information processing device 2, may be implemented in the terminal device 3, or may be implemented in both the information processing device 2 and the terminal device 3.

[0121] In the above embodiment, the NLP server device 5a has been described as generating and outputting text data, but this is not limiting. Specifically, the NLP server device 5a may generate and output image data, video data, audio data, etc. that praise the user in relation to the consultation content.

[0122] In the above embodiment, an example has been described in which the NLP model and the teaching material presentation model are both large-scale language models, but this is not limiting. The NLP model and the teaching material presentation model may be classification models based on supervised learning, using the relationship between consultation content and responses thereto as learning data. The classification model may be any of a model based on a support vector machine (SVM), a decision tree, a k-nearest neighbor method, or a logistic regression, or a model including a neural network. The SVM may be either a linear SVM or a nonlinear SVM. The neural network may be any of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), etc.

[0123] In the above embodiment, the first instruction and the second instruction are described as typically including the entire consultation content, but are not limited to this. Specifically, the first instruction and the second instruction may include a part of the consultation content. Including a part of the consultation content may mean, for example, including some of the consultation content when there are multiple consultation contents, including specific keywords included in the consultation content, etc.

[0124] In the above embodiment (particularly, in FIGS. 5-6), an example has been described in which, when the consultation content includes text data of "÷", the information processing device 2 determines "division" corresponding to the first keyword of "÷" as the second keyword. However, this is not limiting. The first keyword is not limited to specific text data, and may be specified as a predetermined abstract expression (e.g., a regular expression). For example, when the consultation content includes a portion matching a predetermined regular expression, the information processing device 2 may acquire answer information including educational material content associated with the keyword corresponding to the predetermined regular expression. More specifically, when the consultation content includes text data of "Y=aX+b", the information processing device 2 may acquire answer information including educational material content associated with the "linear function" by determining that "Y=aX+b" matches a regular expression corresponding to a linear function.

[0125] Furthermore, when the consultation content includes multiple first keywords, the information processing device 2 may select some of the first keywords based on the priorities set for each of the multiple first keywords. In this case, the information processing device 2 may acquire answer information including educational content associated with second keywords corresponding to the selected first keywords. For example, when the consultation content includes text data such as "I don't understand the graph of Y=aX+b," the information processing device 2 may extract the first keywords "linear function" and "graph" from the text data. Furthermore, when the priority set for "graph" is higher than the priority set for "linear function," the information processing device 2 may acquire answer information including educational content associated with second keywords corresponding to "graph" (e.g., "how to draw a graph"). Furthermore, when the consultation content includes multiple first keywords, the information processing device 2 may select some of the second keywords based on the priorities set for second keywords corresponding to each of the multiple first keywords.

[0126] Furthermore, when the consultation content includes multiple first keywords, the information processing device 2 may determine the educational material content based on the second keywords corresponding to each of the multiple first keywords. For example, when the consultation content includes text data such as "I don't understand 5÷8×12," the information processing device 2 may acquire answer information including educational material content associated with the second keyword "division" corresponding to "÷" and educational material content associated with the second keyword "multiplication" corresponding to "×."

[0127] In the above embodiment (particularly, FIGS. 5-6), an example has been described in which the information processing device 2 presents educational content in a single response to the user's consultation content, but this is not limiting. Specifically, the information processing device 2 may present a plurality of educational content candidates and a message for digging deeper into the consultation content in response to the user's consultation content. The information processing device 2 may further acquire information regarding the user's selection of at least some of the plurality of educational content candidates, and present educational content corresponding to the selected candidate. In other words, the information processing device 2 may be configured to present educational content that is effective in resolving the consultation content based on interactions with the user.

[0128] 7. EMBODIMENTS OF THE PRESENT DISCLOSURE The present disclosure includes, for example, the following embodiments: Note that terms used in the above embodiments are shown in parentheses.

[0129] [Appendix 1] A system 1 according to one embodiment of the present disclosure includes a consultation content acquisition unit 100a that acquires consultation content related to learning input to a user's terminal device 3, a praise information acquisition unit 100b that acquires praise information praising the user in relation to the consultation content, a response information acquisition unit 100c that acquires response information indicating a response to the consultation content, an output unit 104 that can output praise information and response information, a praise condition determination unit (determination unit 106) that determines whether or not predetermined conditions regarding the output of praise information are satisfied, and a praise restriction unit (restriction unit 108) that restricts at least one of the output of praise information by the output unit 104 and the acquisition of praise information by the praise information acquisition unit 100b based on the determination result by the praise condition determination unit (determination unit 106).

[0130] [Appendix 2] In the system 1 described in Supplementary Note 1, the predetermined condition may include a condition regarding the number of times the output unit 104 outputs praise information per unit period.

[0131] [Appendix 3] In the system 1 described in Appendix 1 or Appendix 2, the praise information acquisition unit 100b may acquire praise information by inputting a first instruction including at least a part of the consultation content to a first model (NLP model) that is compatible with natural language processing.

[0132] [Appendix 4] In the system 1 described in Appendix 3, the answer information acquisition unit 100c may acquire answer information by inputting a second instruction including at least a part of the consultation content to a second model (teaching material presentation model) that has learned one or more teaching material contents.

[0133] [Appendix 5] In the system 1 described in Supplementary Note 4, one or more pieces of educational material content may be restricted from being learned by the first model (NLP model).

[0134] [Appendix 6] In the system 1 described in Supplementary Note 4, the answer information may include at least one of one or more educational content items.

[0135] [Appendix 7] In the system 1 described in Appendix 6, the consultation content may include a first keyword, and the system 1 may further include a determination unit 102 that determines a second keyword having a similar meaning to the first keyword, where the second keyword may be associated with at least one of one or more educational content items, and the response information may include educational content associated with the second keyword from among the one or more educational content items.

[0136] [Appendix 8] In the system 1 according to any one of Supplementary Notes 4 to 7, the one or more educational content may include at least one of an image and a video.

[0137] [Appendix 9] In the system 1 according to any one of Supplementary Note 1 to Supplementary Note 8, the response information may include a policy for resolving the consultation content.

[0138] [Appendix 10] In the system 1 described in Supplementary Note 9, when there is an answer that is a correct answer to the consultation content, the answer information may be restricted from including the answer.

[0139] [Appendix 11] A system 1 according to another aspect of the present disclosure includes a consultation content acquisition unit 100a that acquires consultation content related to learning input to a user's terminal device 3; a first response information acquisition unit that acquires first response information indicating a first response to the consultation content, where the first response information is acquired by inputting a first instruction including the consultation content to a first model (NLP model) that is compatible with natural language processing; a second response information acquisition unit that acquires second response information indicating a second response to the consultation content, where the second response information is acquired by inputting a second instruction including the consultation content to a second model (teaching material presentation model) that has learned one or more teaching material contents whose learning by the first model (NLP model) is restricted; and an output unit 104 that can output the first response information and the second response information.

[0140] [Appendix 12] In the system 1 described in Appendix 11, at least one of the first answer information and the second answer information may include a policy for resolving the consultation content, and the system may further include an answer condition determination unit that determines whether or not a predetermined condition regarding the output of the first answer information and the second answer information is satisfied, and an answer restriction unit that, based on the determination result by the answer condition determination unit, restricts at least one of the output unit 104 from outputting the first answer information, the output unit 104 from outputting the second answer information, the first answer information acquisition unit from acquiring the first answer information, and the second answer information acquisition unit from acquiring the second answer information.

[0141] [Appendix 13] A program according to another aspect of the present disclosure causes a computer 70 to function as a consultation content receiving means for receiving input of consultation content related to learning, a praise information acquiring means for acquiring praise information praising the user in relation to the consultation content, a response information acquiring means for acquiring response information indicating an answer to the consultation content, and an output means capable of outputting praise information and response information, wherein the output of the praise information or acquisition by the praise information acquiring means is restricted based on the determination result of whether or not a predetermined condition regarding the output of the praise information is satisfied.

[0142] [Appendix 14] An information processing method according to another aspect of the present disclosure causes a computer 70 to execute a consultation content acquisition step for acquiring consultation content related to learning input to a user's terminal device 3, a praise information acquisition step for acquiring praise information praising the user in relation to the consultation content, an answer information acquisition step for acquiring answer information indicating an answer to the consultation content, a transmission step for transmitting the praise information and the answer information to the terminal device 3, a determination step for determining whether or not predetermined conditions regarding the output of praise information in the terminal device 3 are satisfied, and a restriction step for restricting at least one of performing the praise information acquisition step, transmitting the praise information in the transmission step, and outputting the praise information in the terminal device 3 based on the determination result in the determination step. [Explanation of symbols]

[0143] 1...system, 2...information processing device, 3...terminal device, 10...control unit, 12...storage unit, 70...computer, 100...acquisition unit, 100a...consultation content acquisition unit, 100b...praise information acquisition unit, 100c...answer information acquisition unit, 102...determination unit, 104...output unit, 106...determination unit, 108...restriction unit

Claims

1. a consultation content acquisition unit that acquires consultation content related to learning input to a user's terminal device; a praise information acquisition unit that acquires praise information that praises the user in relation to the consultation content; an answer information acquisition unit that acquires answer information indicating an answer to the consultation content; an output unit capable of outputting the praise information and the answer information; a praise condition determination unit that determines whether a predetermined condition regarding the output of the praise information is satisfied; Based on the judgment result by the praise condition judgment unit, the output unit outputs the praise information; the praise information acquisition unit acquires the praise information; A praise limiting unit that limits at least one of the above. A system comprising:

2. The system according to claim 1 , wherein the predetermined condition includes a condition regarding the number of times the output unit outputs the praise information per unit period.

3. The system according to claim 1 , wherein the praise information acquisition unit acquires the praise information by inputting a first instruction including at least a part of the consultation content to a first model suitable for natural language processing.

4. The system according to claim 3 , wherein the answer information acquisition unit acquires the answer information by inputting a second instruction including at least a part of the consultation content to a second model that has learned one or more educational content.

5. The system of claim 4 , wherein the one or more educational content elements are restricted from being learned by the first model.

6. The system according to claim 4 , wherein the answer information includes at least one of the one or more educational content items.

7. The consultation content includes a first keyword, a determination unit that determines a second keyword having a similar meaning to the first keyword, the second keyword being associated with at least one of the one or more educational content; The system according to claim 6 , wherein the answer information includes a teaching material content associated with the second keyword among the one or more teaching material contents.

8. The system of claim 4 , wherein the one or more educational content items include at least one of an image and a video.

9. The system according to claim 1 , wherein the response information includes a policy for resolving the consultation content.

10. The system according to claim 9 , wherein, in the case where an answer that is a correct answer to the consultation content exists, the answer information is restricted from including the answer.

11. a consultation content acquisition unit that acquires consultation content related to learning input to a user's terminal device; a first answer information acquisition unit that acquires first answer information indicating a first answer to the consultation content, the first answer information being acquired by inputting a first instruction including the consultation content to a first model that is compatible with natural language processing; a second answer information acquisition unit that acquires second answer information indicating a second answer to the consultation content, the second answer information being acquired by inputting a second instruction including the consultation content to a second model that has learned one or more educational content items that are restricted from learning by the first model; an output unit capable of outputting the first answer information and the second answer information; A system comprising:

12. At least one of the first response information and the second response information includes a policy for resolving the consultation content, an answer condition determination unit that determines whether a predetermined condition regarding output of the first answer information and the second answer information is satisfied; Based on the determination result by the answer condition determination unit, the output unit outputs the first answer information; the output unit outputs the second answer information; a first response information acquisition unit acquiring the first response information; a second response information acquisition unit acquiring the second response information; an answer limiting unit that limits at least one of the above; The system of claim 11 further comprising:

13. Computer, a consultation content receiving means for receiving input of consultation content regarding learning; a praise information acquisition means for acquiring praise information that praises the user in relation to the consultation content; answer information acquisition means for acquiring answer information indicating an answer to the consultation content; an output means capable of outputting the praise information and the answer information, wherein the output of the praise information or acquisition by the praise information acquisition means is restricted based on a determination result as to whether or not a predetermined condition related to the output of the praise information is satisfied; A program that functions as a

14. On the computer, a consultation content acquisition step of acquiring a consultation content related to learning input to the user's terminal device; a praise information acquisition step of acquiring praise information that praises the user in relation to the consultation content; an answer information acquisition step of acquiring answer information indicating an answer to the consultation content; a transmitting step of transmitting the praise information and the answer information to the terminal device; a determination step of determining whether a predetermined condition regarding the output of the praise information in the terminal device is satisfied; Based on the determination result in the determining step, performing the praise information acquisition step; transmitting the praise information in the transmitting step; The praise information is output on the terminal device; a limiting step of limiting at least one of An information processing method for executing the above.

Images