Learning material generation system, learning material generation method, and learning material generation program

Abstract

To provide a learning material generation system, a learning material generation method, and a learning material generation program configured to improve the efficiency in preparing a learning material.SOLUTION: A learning material generation system includes: a query acquisition unit which acquires a query D1 including a request to generate a learning material composed of combinations of questions and answers and a generation theme thereof; and a learning material generation unit which refers, when the query D1 acquired by the query acquisition unit is executed, to a database 7 in which a large-scale language model 71 is stored in advance, to generate a learning material based on the generation theme. The query acquisition unit may acquire a query D1 including a request to generate a learning material and a plurality of datasets D2 in which a generation theme is paired with contents of questions. The learning material generation unit may generate a plurality of learning materials corresponding to the contents on the basis of the plurality of datasets D2.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present invention relates to a learning material generation system, a learning material generation method, and a learning material generation program for generating learning materials for education using a large-scale language model. [Background technology]

[0002] Currently, there is a lot of research being done on automatic text generation using AI (artificial intelligence). In particular, by using a natural language processing model that has been trained on a large amount of text data, it is possible to, for example, classify input text, analyze emotions from input text, summarize input text, and generate responses to input questions.

[0003] Patent Document 1 discloses a system that uses a natural language processing model to generate a question in natural language and an answer (QA) to that question. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent Publication No. 2023-2475 Summary of the Invention [Problem to be solved by the invention]

[0005] The generation system disclosed in Patent Document 1 uses a natural language processing model to generate a natural language question using a first phrase expressing a cause or effect, extracts candidate second phrases from candidate text, and selects the candidate second phrase with the highest probability as having a causal relationship with the first phrase, thereby generating a question and answer combination. However, the generation system disclosed in Patent Document 1 does not disclose the generation of learning materials consisting of a combination of questions and answers, for example, for the purpose of education in a specific field.

[0006] The present invention has been devised in consideration of the above-mentioned problems, and its object is to provide a learning material generation system, a learning material generation method, and a learning material generation program that can improve the efficiency of creating learning materials. [Means for solving the problem]

[0007] The learning material generation system in the first invention is characterized by comprising a query acquisition unit that acquires a query including a request for generating learning material consisting of a combination of questions and answers and a generation theme, and a learning material generation unit that, when the query acquired by the query acquisition unit is executed, generates the learning material based on the generation theme by referring to a database in which a large-scale language model is pre-stored.

[0008] The learning material generation system of the second invention is characterized in that, in the first invention, the query acquisition unit acquires the query including a request for generating the learning material and a plurality of data sets each of which is a set of the generation theme and a table of contents of the questions, and the learning material generation unit generates a plurality of the learning materials corresponding to the table of contents based on the plurality of data sets acquired by the query acquisition unit.

[0009] The learning material generation system of the third invention is characterized in that, in the second invention, the query acquisition unit acquires the query including the data set in which at least one of the generation theme and the table of contents is extracted from existing learning material data.

[0010] The learning material generation system in the fourth invention is characterized in that, in any of the first to third inventions, the query acquisition unit acquires the query further including a generation request for the generation theme and its classification theme, and when the query acquired by the query acquisition unit is executed, the learning material generation unit generates the learning material based on the generation theme newly acquired based on the classification theme by referring to a database in which a large-scale language model is pre-stored.

[0011] The learning material generation system in the fifth invention, in any of the first to third inventions, further includes a query conversion unit that converts the generation theme included in the query acquired by the query acquisition unit into one of the related generation themes by referring to a database in which the generation theme is pre-linked to one or more related generation themes related to the generation theme, and the learning material generation unit generates the learning material based on the related generation theme converted by the query conversion unit.

[0012] The learning material generation method of the sixth invention is characterized by having a query acquisition step of acquiring a query including a request for generating learning material consisting of a combination of questions and answers and a generation theme, and a learning material generation step of executing the query acquired by the query acquisition step, and generating the learning material based on the generation theme by referring to a database in which a large-scale language model is pre-stored.

[0013] The learning material generation program in the seventh invention is characterized in that it causes a computer to execute a query acquisition step of acquiring a query including a request for generating learning material consisting of a combination of questions and answers and a generation theme, and a learning material generation step of executing the query acquired by the query acquisition step, and generating the learning material based on the generation theme by referring to a database in which a large-scale language model is pre-stored. Effect of the Invention

[0014] According to the first to fifth inventions, a learning material generating unit is provided that generates learning materials based on a generation theme included in a query acquired by referring to a database in which a large-scale language model is stored in advance. Therefore, learning materials related to the generation theme can be automatically generated by the large-scale language model. This can improve the efficiency of creating learning materials.

[0015] In particular, according to the second invention, the query acquisition unit acquires a query including a request for generating learning materials and a plurality of data sets each including a generation theme and a table of contents, and the learning material generation unit generates a plurality of learning materials based on the acquired plurality of data sets. Therefore, the learning materials related to the generation theme can be automatically generated according to the table of contents by the large-scale language model. This can improve the efficiency of creating a problem set including a plurality of learning materials.

[0016] In particular, according to the third invention, the query acquisition unit acquires a query including a data set in which at least one of the generated theme and the table of contents is extracted from existing learning material data. Therefore, the work related to creating a query can be omitted. This can further improve the efficiency of creating learning materials. In addition, learning materials can be generated based on existing learning materials. This can improve the quality of learning materials.

[0017] In particular, according to the fourth invention, the learning material generation unit generates learning materials based on a newly acquired generation theme based on a classification theme after referring to a database in which a large-scale language model is previously stored. Therefore, a generation theme related to a classification theme can be automatically generated by a large-scale language model. This can further improve the efficiency of creating learning materials. In addition, since it is not necessary to select a generation theme for each learning material, even a user with little specialized knowledge of learning materials can automatically generate learning materials. This can improve the workability of creating learning materials.

[0018] In particular, according to the fifth aspect of the present invention, a query conversion unit is further provided for converting a generation theme included in the acquired query into one related generation theme. Therefore, it is possible to automatically generate learning materials with different contents from the same generation theme using a large-scale language model. This makes it possible to improve the convenience of the learning materials to be created.

[0019] In particular, according to the sixth aspect of the present invention, the method includes a learning material generating step of generating learning materials based on a generation theme included in a query acquired by referring to a database in which a large-scale language model is previously stored. Therefore, learning materials related to the generation theme can be automatically generated by the large-scale language model. This can improve the efficiency of creating learning materials.

[0020] In particular, according to the seventh aspect of the present invention, a learning material generating step is executed by a computer to generate learning materials based on a generation theme included in a query acquired by referring to a database in which a large-scale language model is previously stored. Therefore, learning materials related to the generation theme can be automatically generated by the large-scale language model. This can improve the efficiency of creating learning materials. [Brief description of the drawings]

[0021] [Figure 1] FIG. 1 is a schematic diagram showing an example of a learning material generation system in the first embodiment. [Diagram 2] 2(a) and 2(b) are schematic diagrams showing an example of the configuration of a learning material generation system in the first embodiment. [Diagram 3] FIG. 3 is a schematic diagram showing an example of a detailed configuration of the learning material generation system in the first embodiment. [Figure 4] FIG. 4 is a flowchart showing an example of the operation of the learning material generation system in the first embodiment. [Diagram 5] FIG. 5(a) is a schematic diagram showing an example of the operation of the learning material generation system in the first embodiment, and FIG. 5(b) is a schematic diagram showing a modified example of the operation of the learning material generation system in the first embodiment. [Figure 6] FIG. 6 is a schematic diagram showing an example of the operation of the learning material generation system in the second embodiment. [Figure 7] FIG. 7 is a schematic diagram showing an example of the configuration of a learning material generation system in the third embodiment. [Figure 8]FIG. 8 is a flowchart showing an example of the operation of the learning material generation system in the third embodiment. [Figure 9] FIG. 9 is a schematic diagram showing an example of the operation of the learning material generation system in the third embodiment. [Figure 10] FIG. 10 is a schematic diagram showing an example of a database used for the operation of the learning material generation system in the third embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0022] Hereinafter, an example of a learning material generation system 100, a learning material generation method, and a learning material generation program according to an embodiment of the present invention will be described in detail with reference to the drawings. Note that the configurations in each drawing are shown diagrammatically for the purpose of explanation, and the size of each component, the size comparison between components, etc. may differ from those shown in the drawings.

[0023] (First embodiment: learning material generation system 100) An example of the configuration of a learning material generation system 100 in this embodiment will be described with reference to FIGS.

[0024] 1, the learning material generation system 100 includes a user terminal 1, a server 2, and a communication network 9. The learning material generation system 100 receives an input from a user U via the user terminal 1, and acquires a query to be executed on a database that stores a pre-stored large-scale language model. The learning material generation system 100 then executes the acquired query, thereby automatically generating learning materials based on the large-scale language model.

[0025] The user U refers to a user who presents learning materials generated by using the learning material generation system 100 to the answering user who is the subject of education. The user U can improve the efficiency of educational activities for the answering user by providing the answering user with automatically generated learning materials. The user U may also be the answering user, for example. In other words, the user U can improve the efficiency of self-study by answering the learning materials generated by using the learning material generation system 100 by himself.

[0026] The learning material refers to a test consisting of a combination of questions and answers that tests the knowledge of the answering user, and includes question formats such as descriptive questions, multiple choice questions, and combination questions. The learning material also includes any teaching material that is output to the answering user as visual or auditory information. Examples of learning materials include learning material data generated by the learning material generation system 100, images and videos displayed on a display based on the learning material data, three-dimensional images and three-dimensional videos displayed via a holographic display based on the learning material data, printed materials printed based on the learning material data, and sounds played via audio equipment based on the learning material data.

[0027] In this embodiment, a configuration will be described in which a database that stores a large-scale language model is stored in the server 2, and the learning material generation system 100 generates learning materials in the server 2, but this is not limiting. The learning material generation system 100 may store a database that stores a large-scale language model in the user terminal 1, and generate learning materials in the user terminal 1, in which case the server 2 may not be provided.

[0028] <User device 1> The user terminal 1 is a terminal that controls the automatic generation of learning materials. The user terminal 1 is a terminal that is operated by a user U. The user terminal 1 is communicatively connected to a server 2 via a communication network 9.

[0029] 2(a), the user terminal 1 includes a housing 10, a CPU (Central Processing Unit) 101, a ROM (Read Only Memory) 102, a RAM (Random Access Memory) 103, a storage unit 104, and I / Fs 105 to 107. The components 101 to 107 are connected by an internal bus 110. As the user terminal 1, for example, a known electronic device such as a laptop (notebook) PC, a desktop PC, a tablet terminal, or a smartphone is used.

[0030] The CPU 101 controls the entire user terminal 1. The ROM 102 stores operation code for the CPU 101. The RAM 103 is a working area used when the CPU 101 is operating. The storage unit 104 stores various information such as backups of data stored in the ROM, databases, and learning target data. As the storage unit 104, for example, a data storage device such as an HDD (Hard Disk Drive) or an SSD (Solid State Drive) is used. For example, the user terminal 1 may have a GPU (Graphics Processing Unit) (not shown).

[0031] The I / F 105 is an interface for transmitting and receiving various information to and from the server 2 as necessary via the communication network 9. The I / F 106 is an interface for transmitting and receiving information to and from the input unit 108. For example, a keyboard or a mouse is used as the input unit 108, and the user U inputs various information via the input unit 108. The I / F 107 is an interface for transmitting and receiving various information to and from the display unit 109. The display unit 109 displays various information stored in the storage unit 104, evaluation results, etc. A display is used as the display unit 109, and in the case of a touch panel type, for example, it is provided integrally with the input unit 108.

[0032] 3, the user terminal 1 includes a communication unit 11, a storage unit 12, a query acquisition unit 13, a query execution unit 14, and a learning material output unit 15. Each component of the user terminal 1 is realized by a CPU 101 using a RAM 103 as a working area to execute a program stored in a ROM 102, a storage unit 104, etc.

[0033] <Communications Division 11> The communication unit 11 transmits information to, for example, the server 2. The communication unit 11 transmits information acquired, generated, or stored by, for example, each component of the user terminal 1 to the server 2 via the communication network 9. The communication unit 11 receives information acquired, generated, or stored by, for example, the server 2 via the communication network 9.

[0034] <Storage section 12> The storage unit 12 stores, for example, information acquired or generated by each component of the user terminal 1 in a database stored in the storage unit 104 as necessary. The storage unit 12 retrieves, for example, various pieces of information stored in the database stored in the storage unit 104 as necessary.

[0035] <Query Acquisition Unit 13> The query acquisition unit 13 acquires a query (query data) requesting the large-scale language model to generate learning materials. The query acquisition unit 13 acquires the query requesting the large-scale language model to generate learning materials, for example, by a method of accepting an input from a user U via the input unit 108.

[0036] <Query execution unit 14> The query execution unit 14 executes a query acquired or generated by each component of the learning material generation system 100. The query execution unit 14 executes the query acquired by the query acquisition unit 13, for example, on a database in which a large-scale language model is stored in advance.

[0037] <Learning material output section 15> The learning material output unit 15 outputs the learning material generated by each component of the learning material generation system 100. The learning material output unit 15 receives the learning material generated by a learning material generation unit 23 (described later) of the server 2 via the communication network 9 from the server 2, and outputs the learning material.

[0038] The learning material output unit 15 may output the learning material so that it is displayed on the display unit 109. The learning material output unit 15 may output the learning material in which the characteristics of the learning material have been converted into a format that the user U can understand, for example, by using a display format previously stored in the storage unit 104 or the like.

[0039] <Server 2> The server 2 stores, for example, a database in which a large-scale language model is stored in advance. The server 2 is communicatively connected to the user terminal 1 via, for example, a communication network 9. The server 2 generates, stores, and transmits / receives information in response to a processing request received from, for example, the user terminal 1 via the communication network 9.

[0040] 2(b), the server 2 includes a housing 20, a CPU 201, a ROM 202, a RAM 203, a storage unit 204, and an I / F 205. The components 201 to 205 are connected by an internal bus 210. As the server 2, for example, a known electronic device such as a laptop (notebook) PC or a desktop PC is used.

[0041] The CPU 201 controls the entire server 2. The ROM 202 stores the operation code of the CPU 201. The RAM 203 is a working area used when the CPU 201 is operating. The storage unit 204 stores various information such as backups of data stored in the ROM, databases, and learning target data. As the storage unit 204, for example, a data storage device such as an HDD or an SSD is used. For example, the server 2 may have a GPU (not shown). The I / F 205 is an interface for transmitting and receiving various information to and from the user terminal 1 as necessary via the communication network 9.

[0042] <Server communication unit 21> The server communication unit 21 transmits information to, for example, the user terminal 1. The server communication unit 21 transmits, for example, information acquired, generated, or stored by each component of the server 2 to the user terminal 1 via the communication network 9. The server communication unit 21 receives, for example, information acquired, generated, or stored by the user terminal 1 via the communication network 9.

[0043] <Server storage unit 22> The server storage unit 22 stores, for example, information acquired or generated by each component of the server 2 in a database stored in the storage unit 204 as necessary. The server storage unit 22 retrieves, for example, various pieces of information stored in the database stored in the storage unit 204 as necessary.

[0044] <Learning material generation unit 23> The learning material generation unit 23 generates learning materials by referring to a database in which a large-scale language model is stored, for example, in response to a learning material generation request from the user terminal 1. The learning material generation unit 23 generates learning materials in response to the request content of a query executed by the query execution unit 14, for example.

[0045] <Communication Network 9> The communication network 9 is, for example, an Internet network to which the user terminal 1 and the server 2 are connected via a communication circuit. The communication network 9 may be configured as a so-called optical fiber communication network. The communication network 9 may be realized by known communication technologies such as a wireless communication network in addition to a wired communication network.

[0046] (First embodiment: an example of the operation of the learning material generation system 100) Next, an example of the operation of the learning material generation system 100 will be described as a learning material generation method in this embodiment with reference to Fig. 4 and Fig. 5. The learning material generation system 100 is executed via a learning material generation program installed in the user terminal 1 and the server 2, for example.

[0047] The operation of the learning material generation system 100 includes, for example, a query acquisition step S11, a learning material generation step S12, and a learning material output step S13, as shown in Fig. 4. Note that the operation of the learning material generation system 100 may include performing the query acquisition step S11 multiple times, and may include performing the learning material generation step S12 multiple times.

[0048] First, various information associated with the operation of the learning material generation system 100 in this embodiment will be described. The various information handled by the learning material generation system 100 includes, for example, a query D1 and generated data D71, as shown in Fig. 5(a). The learning material generation system 100 stores a database 7 in advance.

[0049] <Query D1> The query D1 is information including a processing request for a database 7 described later in which a large-scale language model 71 described later is stored. The query D1 includes, for example, learning material generation request information D11 and generation theme information D12. The learning material generation request information D11 and the generation theme information D12 are, for example, linked to each other.

[0050] The query D1 is, for example, a prompt including a processing instruction for the large-scale language model 71, and is composed of a tag specifying a role and a natural language specifying the instruction content. <system>You are an excellent Japanese history teacher. <user>Please create one difficult question for the History Proficiency Test in the following format. This is a string that includes the combination of [Question][Choices] [Answer][Explanation]. By executing query D1 that includes this combination, it is possible to generate learning materials that include questions, choices, answers, and explanations about Japanese history, for example.

[0051] The instructions may also include instructions to generate a problem set consisting of multiple problems, and may also include the title of the problem set, the structure of each chapter in the problem set, the goal or objective of each chapter in the problem set, keywords for each chapter in the problem set, the number of questions in each chapter, and the output format (such as HTML format).

[0052] <Learning material generation request information D11> The learning material generation request information D11 is information that specifies a request to generate learning material among processing requests. The learning material generation request information D11 constitutes, for example, a part of the character string of the query D1. For example, the learning material generation request information D11 corresponds to "Please create a question" in the above-mentioned example prompt sentence.

[0053] <Generated theme information D12> The generation theme information D12 is information that specifies a theme related to a request to generate learning materials. The generation theme information D12 is information that specifies a theme of learning materials requested to be generated by, for example, the learning material generation request information D11. The generation theme information D12, for example, constitutes a part of the character string of the query D1. The generation theme information D12 is composed of one or more words that specify, for example, the subject, the name of the qualification or examination, the field, the era, the person, the question format, the answer format (presence or absence of options, presence or absence of explanation, etc.), the number of questions, the difficulty level, and the educational classification such as primary education, secondary education, and higher education in the school system corresponding to the learning guidelines, in order to specify the content of the learning materials to be generated. The generation theme information D12 corresponds to, for example, "History Proficiency Test", "Difficult", "The following format", "One", "[Question] [Options] [Answer] [Explanation]" in the above-mentioned prompt example sentence.

[0054] The generated theme information D12 may be, for example, one or more words that specify the final goal of the study. In this case, the generated theme information D12 may be a character string such as "acquire basic knowledge for taking a qualification exam", "cover common questions in qualification exams", or "deepen understanding of subjects that are difficult to study through repetitive study".

[0055] The generation theme information D12 may use, for example, one or more words input by the user U via the input unit 108. Also, the learning material generation request information D11 may use, for example, a syntax stored in advance in the user terminal 1. That is, the learning material generation system 100 can obtain the query D1 and generate learning materials simply by the user U inputting one or more words. In this case, even a user U with little expert knowledge of the query D1 can automatically generate learning materials. This can improve the workability of creating learning materials.

[0056] <Generated data D71> The generated data D71 indicates data generated based on the query D1. The generated data D71 includes one or more pieces of data indicating the contents of the learning material, and includes, for example, learning material data D711.

[0057] The learning material data D711 indicates the contents of the learning material related to the generation theme included in the generation theme information D12, and is composed of a combination of questions and answers. The number of characters of the questions and answers in the learning material data D711 may be determined arbitrarily by the large-scale language model 71. The learning material data D711 may further include an explanation for the answer. In this case, the explanation may be generated by the large-scale language model 71 together with the answer.

[0058] An example of the learning material data D711 corresponding to the generation theme information D12 is as shown in Table 1.

[0059] [Table 1]

[0060] When the generated theme includes the word "history," as in Classification 1, the learning material data D711 may be a question-and-answer style learning material consisting of a combination of a question related to the generated theme "history," such as "Who carried out the Taiko land survey?", and the answer to that question, "Toyotomi Hideyoshi."

[0061] As for the learning material data D711, when the generated theme includes the word "Azuchi-Momoyama period," i.e., is a sub-concept of "history," as in Classification 2, the learning material may be a question-and-answer style learning material consisting of a combination of a question similar to the question related to the generated theme "history," "Who carried out the Taiko land survey?", and the answer to that question, "Toyotomi Hideyoshi."

[0062] As in category 3, when the generation theme includes the word "Toyotomi Hideyoshi," the learning material data D711 may be a question-and-answer type learning material consisting of a combination of a question "Who carried out the Taiko land survey?" and the answer "Toyotomi Hideyoshi," which is generated with the generation theme as the answer.

[0063] The learning material data D711 may be a question-and-answer style learning material consisting of a combination of a question "Who carried out the Taiko land survey?" and the answer "Toyotomi Hideyoshi," which is generated by referring to an external database such as a curriculum guideline when the generated theme includes the word "social studies for junior high school students," as in category 4.

[0064] When the generated theme includes the words "Azuchi-Momoyama period" and "question and answer type question," as in category 5, the learning material data D711 may be a question and answer type learning material consisting of a combination of a question "Who carried out the Taiko land survey?" related to the generated theme "Azuchi-Momoyama period" and the answer to that question "Toyotomi Hideyoshi," which is generated based on the premise that the question format is a question and answer type question.

[0065] When the generated theme includes the word "history" and the word "basic," as in category 6, the learning material data D711 may be a question-and-answer style learning material consisting of a combination of a question "Who carried out the Taiko land survey?" and the answer to that question, "Toyotomi Hideyoshi," which is generated by referring to an external database such as a curriculum guideline, as well as a database in which the generated theme is linked to difficulty levels such as basic / applied, easy / difficult, etc.

[0066] When the generated theme includes the words "history" and "application" as in Category 7, the learning material data D711 may be a question-and-answer style learning material consisting of a combination of a question "What is the name of the principle of peasant control established in the Taiko land survey?" and the answer to that question "The principle of one land, one farmer," which is generated by referring to a database, etc. similar to that explained in Category 6.

[0067] When the generated theme includes the words "Azuchi-Momoyama period" and "multiple choice question," as in category 8, the learning material data D711 may be a multiple choice learning material consisting of a combination of a question related to the generated theme "Azuchi-Momoyama period" such as "Who carried out the Taiko land survey? 1. Oda Nobunaga 2. Toyotomi Hideyoshi 3. Tokugawa Ieyasu" and the answer to the question, "2," which is generated based on the premise that the question format is a multiple choice question.

[0068] As per classification 9, when the generated theme includes the word "Azuchi-Momoyama period" and the word "combination question," the learning material data D711 may be a combination-type learning material consisting of a question regarding the generated theme "Azuchi-Momoyama period," "Which did Toyotomi Hideyoshi carry out? 1. Taiko land survey 2. Sword hunt 3. Rakuichi Rakuza," and the answer to that question, "1 and 2," which is generated based on the premise of the question format being a combination question.

[0069] <Database 7> The database 7 is a collection of data stored in advance in the learning material generation system 100. The database 7 is stored in advance in, for example, the storage unit 204 of the server 2. The database 7 stores a large-scale language model 71 in advance.

[0070] <Large-scale language model 71> The large-scale language model 71 is a type of natural language processing model used for automatically generating learning materials by the learning material generation system 100. The large-scale language model 71 is a known large-scale language model (LLM) that is machine-learned in advance using a large amount of text data.

[0071] As the large-scale language model 71, specifically, GPT-3, GPT-3.5 or GPT-4 related to "GPT (Generative Pre-trained Transformer) (registered trademark)", "BERT (Bidirectional Encoder Representations from Transformers)", "LaMDA (Language Model for Dialogue Applications)", "PaLM (Scaling Language Modeling with Pathways)", "LLaMA (Large Language Model Meta AI)", etc. may be used.

[0072] Next, the operation of the learning material generation system 100 in this embodiment will be described in detail.

[0073] <Advance preparation> Before operating the learning material generation system 100 , the user U confirms that the database 7 in which the large-scale language model 71 is stored is saved in the server 2 .

[0074] <Query acquisition step S11> In a query acquisition step S11, the query acquisition unit 13 accepts an input from the user U via the input unit 108, and acquires a query D1 including learning material generation request information D11 and generation theme information D12.

[0075] <Learning material generation step S12> In the learning material generation step S12, the query execution unit 14 executes the query D1 (a generation request based on the learning material generation request information D11) acquired in the query acquisition step S11 against the database 7. When the query acquisition unit 13 acquires the query D1, the query execution unit 14 may automatically execute the acquired query D1, or may execute the query D1 according to an input from the user U. The query execution unit 14 may be separately executed before the learning material generation step S12 as a query execution step distinct from the learning material generation step S12.

[0076] When the query D1 is executed on the database 7, the learning material generation unit 23 generates generation data D71 including learning material data D711 based on the generation theme included in the generation theme information D12 after referring to the database 7. In this case, the large-scale language model 71 can automatically generate learning materials (learning material data D711) related to the generation theme (generation theme information D12). This can improve the efficiency of creating learning materials. Furthermore, as long as the query D1 can be acquired and executed, the user U can have the learning material generation system 100 generate the generation data D71 without having to prepare existing learning materials. This can improve the user U's workability in creating learning materials.

[0077] <Learning material output step S13> In the learning material output step S13, when the user terminal 1 receives the generated data D71 generated by the learning material generation unit 23 via the communication network 9, the learning material output unit 15 outputs it to the user U via the display unit 109 or the like.

[0078] After performing each of the above steps, the operation of the learning material generation system 100 in this embodiment ends. Note that the learning material generation system 100 may perform each of the above steps repeatedly, for example.

[0079] (First embodiment: Modified example of operation of learning material generation system 100) <Query D1> The query D1 may further include table of contents information D13, for example, as shown in Fig. 5(b) The query D1 includes one or more pieces of table of contents information D13.

[0080] The table of contents information D13 is information that specifies the table of contents of questions included in the learning materials to be generated. Here, the table of contents specifies the number of questions, order, chapters (including chapters, sections, paragraphs, etc.), number of questions per chapter, title of each chapter, etc. of each learning material generated by the learning material generation system 100.

[0081] For example, one piece of table of contents information D13 is linked to one piece of generation theme information D12 to form one data set D2. At this time, each piece of generation data D71 generated based on a generation theme included in each piece of generation theme information D12 is assigned a table of contents according to each piece of table of contents information D13 linked to each piece of generation theme information D12.

[0082] Specifically, when the table of contents information D13 includes information specifying the number of questions in the study material as "2", two pieces of generated data D71 are generated in accordance with the number of questions "2" specified by the table of contents information D13, based on the generation theme included in the generation theme information D12. Here, even if the query D1 includes only one data set D2, multiple pieces of generated data D71 may be generated in accordance with the number of questions specified by the table of contents information D13.

[0083] When the table of contents information D13 includes information specifying the order of the learning materials "1" and "2", two pieces of generation data D71 are generated based on the generation themes included in the generation theme information D12, arranged according to the order specified by the table of contents information D13. For example, when the query D1 includes a data set D2a in which table of contents information D13a specifying the order "1" is linked to generation theme information D12a specifying the generation theme "Theme A", and a data set D2b in which table of contents information D13a specifying the order "2" is linked to generation theme information D12a specifying the generation theme "Theme B", generation data D71 is generated, which includes learning material data D711 consisting of a combination of questions and answers for "Question 1" related to "Theme A" and learning material data D712 consisting of a combination of questions and answers for "Question 2" related to "Theme B".

[0084] When the table of contents information D13 includes information specifying the chapters of the learning material, "Chapter 1" and "Chapter 2", the generated data D71 is generated after being arranged according to the chapters specified by the table of contents information D13 based on the generation theme included in the generation theme information D12, as in the case where the table of contents information D13 includes information specifying the order described above. When the table of contents information D13 includes information specifying the combinations of the chapters of the learning material and the number of questions, "Chapter 1, 2 questions" and "Chapter 2, 3 questions", the generated data D71 is generated after being arranged according to the combinations of the chapters and the number of questions specified by the table of contents information D13 based on the generation theme included in the generation theme information D12. When the table of contents information D13 includes information specifying the titles of the chapters of the learning material, the titles may be included as part of each learning material data D712 and output together with the questions.

[0085] Next, the operation of the learning material generation system 100 in this embodiment will be described in detail.

[0086] <Query acquisition step S11> In a query acquisition step S11, the query acquisition unit 13 accepts input from a user U, for example, via the input unit 108, and acquires a query D1 including learning material generation request information D11 and multiple data sets D2 each of which is a set of generation theme information D12 and table of contents information D13.

[0087] The query acquisition unit 13 may acquire a query D1 including a data set D2 in which at least one of the generated theme information D12 and the table of contents information D13 is extracted from existing learning material data, instead of or in addition to the method of accepting input from the user U.

[0088] The query acquisition unit 13 may use a known program or software capable of extracting phrases using, for example, TF-IDF (Term Frequency - Inverse Document Frequency), RAKE (Rapid Automatic Keyword Extractor), YAKE (Yet Another Keyword Extractor), etc. to acquire information extracted from existing learning material data as at least one of the generated theme information D12 and the table of contents information D13. Specifically, all or a part of the existing learning material data may be given as a context, and nouns and unique expressions (such as expressions with a low frequency of occurrence) may be extracted from the context and acquired as the generated theme information D12. In addition, examples of combinations of chapters and the number of questions in the existing learning material data, such as "Chapter 1, 2 Questions" and "Chapter 2, 3 Questions," may be extracted and acquired as the table of contents information D13. In this case, the work of the user U involved in creating the query D1 can be omitted. This can further improve the efficiency of creating learning materials. In addition, the learning materials to be generated are generated based on existing learning materials that have higher quality as learning materials than sentences unrelated to the learning materials. This can improve the quality of the learning materials. The number of characters in the questions and answers in the learning material data D711 generated based on these data sets D2 may be determined by the large-scale language model 71 based on the number of characters in the context of the existing learning material data provided as the extraction range.

[0089] <Learning material generation step S12> In the learning material generation step S12, when the query D1 acquired in the query acquisition step S11 is executed on the database 7, the learning material generation unit 23 generates generation data D71 including multiple learning material data D711, D712 corresponding to the table of contents information D13 based on the generation theme information D12 and the table of contents information D13 included in the multiple data sets D2 with reference to the database 7. In this case, the large-scale language model 71 can automatically generate multiple learning materials (multiple learning material data D711, D712) related to the generation theme (generation theme information D12) according to the table of contents (table of contents information D13). This can improve the efficiency of creating a problem set including multiple learning materials.

[0090] According to this embodiment, the large-scale language model 71 includes a learning material generating unit 23 that generates learning materials based on a generation theme included in a query D1 acquired by referring to a database 7 in which the large-scale language model 71 is previously stored. Therefore, the large-scale language model 71 can automatically generate learning materials related to the generation theme. This can improve the efficiency of creating learning materials.

[0091] According to this embodiment, the query acquisition unit 13 acquires a query D1 including a plurality of data sets D2 each including a request for generating learning materials, a generation theme, and a table of contents, and the learning material generation unit 23 generates a plurality of learning materials based on the acquired plurality of data sets D2. Therefore, the large-scale language model 71 can automatically generate learning materials related to the generation theme according to the table of contents. This can improve the efficiency of creating a problem set including a plurality of learning materials.

[0092] According to this embodiment, the query acquisition unit 13 acquires a query D1 including a data set D2 in which at least one of a generation theme and a table of contents is extracted from existing learning material data. Therefore, the work related to the creation of the query D1 can be omitted. This can further improve the efficiency of creating learning materials. In addition, learning materials based on existing learning materials can be generated. This can improve the quality of learning materials.

[0093] According to this embodiment, the large-scale language model 71 has a learning material generating step S12 for generating learning materials based on a generation theme included in a query D1 acquired by referring to a database 7 previously stored in the large-scale language model 71. Therefore, the large-scale language model 71 can automatically generate learning materials related to the generation theme. This can improve the efficiency of creating learning materials.

[0094] According to this embodiment, a learning material generating step S12 is executed by a computer to generate learning materials based on a generation theme included in a query D1 acquired by referring to a database 7 in which a large-scale language model 71 is previously stored. Therefore, learning materials related to the generation theme can be automatically generated by the large-scale language model 71. This can improve the efficiency of creating learning materials.

[0095] (Second embodiment: an example of the operation of the learning material generation system 100) An example of the operation of the learning material generation system 100 in this embodiment will be described with reference to Fig. 6. This embodiment differs from the first embodiment in that the learning material generation system 100 generates intermediate acquisition data D8. Note that the description of the same configuration as that described above will be omitted.

[0096] First, a description will be given of various information associated with the operation of the learning material generation system 100 in this embodiment. The various information handled by the learning material generation system 100 further includes, for example, generation theme generation request information D14, classification theme information D15, and intermediate acquisition data D8, as shown in FIG.

[0097] <Query D1> The query D1 may further include, for example, creation theme generation request information D14 and classification theme information D15. The creation theme generation request information D14 and the classification theme information D15 are, for example, linked to each other.

[0098] The query D1 may further include intermediately acquired data D8 that is newly acquired based on the theme generation request information D14 and the classification theme information D15.

[0099] <Generation theme generation request information D14> The theme generation request information D14 is information that specifies a request to generate a theme for a learning material among the processing requests. The theme generation request information D14 constitutes, for example, a part of the character string of the query D1, similar to the learning material generation request information D11.

[0100] <Classification Theme Information D15> The categorization theme information D15 is information that specifies a theme related to a request for generating a theme for a learning material. The categorization theme information D15 includes information similar to the generation theme information D12, and is information that specifies the theme of the learning material requested to be generated by, for example, the learning material generation request information D11. Like the generation theme information D12, the categorization theme information D15 is, for example, a part of the character string of the query D1, and is composed of one or more words.

[0101] The classification theme included in the classification theme information D15 may be, for example, a content corresponding to a superordinate concept of the generated theme, a content corresponding to a subordinate concept, or a content corresponding to an equivalent concept.

[0102] The classification theme information D15 may use, for example, one or more words input by the user U via the input unit 108. The generation theme generation request information D14 may use, for example, a syntax stored in advance in the user terminal 1. That is, the learning material generation system 100 can obtain a query D1 simply by the user U inputting one or more words, and can newly obtain intermediate acquisition data D8 as a generation theme for the learning material.

[0103] <Interim Data D8> The intermediately acquired data D8 indicates data generated before the generation data D71, among data newly acquired based on the query D1. The intermediately acquired data D8 may acquire existing article texts and article URLs on the web newly acquired based on the query D1 together with the data to be generated, or may acquire them instead of the data to be generated. At least a part of the acquired article texts and article URLs may be used as part or all of the commentary included in the learning material data D711. The intermediately acquired data D8 includes generation theme information D81.

[0104] <Generated theme information D81> The generation theme information D81 is information that specifies a theme related to a request to generate a learning material, and is similar to the generation theme information D12. The generation theme information D81 is, for example, information that specifies a theme of a learning material requested to be generated by the learning material generation request information D11. The generation theme information D81, for example, constitutes a part of the character string of the query D1, and is composed of one or more words.

[0105] The creation theme information D81 indicates a creation theme of the learning material related to the classification theme included in the classification theme information D15, and is composed of, for example, one or more words. An example of the creation theme information D81 corresponding to the classification theme information D15 is as shown in [Table 2].

[0106] [Table 2]

[0107] When the classification theme includes the word "Azuchi-Momoyama period" as in Class 10, the generation theme information D81 may include the generation theme "history" which is a superordinate concept of the classification theme.

[0108] When the classification theme includes the word "Azuchi-Momoyama period" as in Class 11, the generating theme information D81 may include a generating theme "Toyotomi Hideyoshi" which is a subordinate concept of the classification theme.

[0109] When the classification theme includes the word "Azuchi-Momoyama period" as in Class 12, the generating theme information D81 may include a generating theme "Azuchi-Momoyama period" which is equivalent to the same concept as the classification theme.

[0110] When the classification theme including the difficulty level includes the word "Azuchi-Momoyama period basics" as in classification 13, the generated theme information D81 may include a generated theme "Toyotomi Hideyoshi basics" that does not change the difficulty level portion.

[0111] When the classification theme including the question format includes the words "Azuchi-Momoyama period multiple-choice questions" as in classification 14, the generated theme information D81 may include a generated theme "Toyotomi Hideyoshi multiple-choice questions" that does not change the difficulty portion.

[0112] <Database 7a> The database 7a is stored in advance in the server 2. The database 7a may be the same database as the database 7, or may be a similar database different from the database 7. The database 7a stores a large-scale language model 71a in advance.

[0113] <Large-scale language model 71a> The large-scale language model 71 a may be the same large-scale language model as the large-scale language model 71 , or may be a similar large-scale language model different from the large-scale language model 71 .

[0114] Next, the operation of the learning material generation system 100 in this embodiment will be described in detail.

[0115] <Query acquisition step S11> In a query acquisition step S11, the query acquisition unit 13 acquires a query D1 including learning material generation request information D11, generation theme generation request information D14, and classification theme information D15.

[0116] <Learning material generation step S12> In the learning material generation step S12, the query execution unit 14 executes the query D1 (a generation request based on the generation theme generation request information D14) acquired in the query acquisition step S11 to the database 7a in which the large-scale language model 71a is stored in advance.

[0117] When the query D1 is executed on the database 7a, the learning material generation unit 23 refers to the database 7a and newly acquires intermediate acquisition data D8 including generated theme information D81 based on the classification theme included in the classification theme information D15. Here, the intermediate acquisition data D8 may be information generated by the large-scale language model 71a based on the classification theme, or may be information (including the above-mentioned existing article text on the web and article URLs) acquired as a result of the learning material generation system 100 executing a web search or an external database search using the information generated by the large-scale language model 71a based on the classification theme as a theme.

[0118] Thereafter, the learning material generating unit 23 refers to the database 7 in response to the query D1 (generation request based on the learning material generation request information D11) acquired in the query acquisition step S11, and generates generation data D71 including the learning material data D711 based on the generation theme included in the newly acquired generation theme information D81. In this case, the large-scale language model 71a can automatically generate the generation theme (generation theme information D81) related to the classification theme (classification theme information D15). This can further improve the efficiency of creating learning materials. In addition, since it is not necessary to select the generation theme for each learning material, even a user U with little specialized knowledge of learning materials can automatically generate learning materials. This can improve the workability of creating learning materials.

[0119] According to this embodiment, the learning material generating unit 23 generates learning materials based on a newly acquired generation theme based on a classification theme after referring to the database 7a in which the large-scale language model 71a is previously stored. Therefore, the large-scale language model 71a can automatically generate a generation theme related to the classification theme. This can further improve the efficiency of creating learning materials. In addition, since it is not necessary to select a generation theme for each learning material, even a user with little specialized knowledge of learning materials can automatically generate learning materials. This can improve the workability of creating learning materials.

[0120] (Third embodiment: learning material generation system 100) An example of the learning material generation system 100 in this embodiment will be described with reference to Fig. 7. This embodiment differs from the first embodiment in that the learning material generation system 100 further includes a query conversion unit 16. Note that a description of the same configuration as that described above will be omitted.

[0121] The user terminal 1 further includes a query conversion unit 16, as shown in FIG.

[0122] <Query conversion part 16> The query conversion unit 16 converts at least a part of the query (query data) acquired by the query acquisition unit 13. The query conversion unit 16 converts at least a part of the query by referring to, for example, an associated word database in which associated words are linked to each other and stored in advance in the server 2.

[0123] (Third embodiment: an example of the operation of the learning material generation system 100) Next, an example of the operation of the learning material generation system 100 will be described as a learning material generation method in this embodiment with reference to FIGS.

[0124] The operation of the learning material generation system 100 further includes a query conversion step S14, as shown in Fig. 8. The query conversion step S14 is executed after the query acquisition step S11. Note that the operation of the learning material generation system 100 may include performing the query conversion step S14 multiple times.

[0125] First, a description will be given of various types of information associated with the operation of the learning material generation system 100 in this embodiment. The various types of information handled by the learning material generation system 100 further include related generation theme information D82, as shown in FIG.

[0126] <Interim Data D8> The intermediately acquired data D8 includes related generated theme information D82.

[0127] <Related generated theme information D82> The related generated theme information D82 is information that specifies a theme related to a request to generate a learning material, and is similar to the generated theme information D81. The related generated theme information D82 is composed of a character string, for example, similar to the generated theme information D12, and is composed of one or more words.

[0128] The generated theme information D81 differs from the generated theme information D81 in that while the generated theme information D81 is newly generated based on the classified theme information D15 with reference to the large-scale language model 71a, the related generated theme information D82 is obtained from the related word database 72 with reference to the related word database 72 described below.

[0129] <Database 7b> The database 7b is stored in advance in the server 2. The database 7b may be the same database as the database 7, or may be a similar database different from the database 7. In the database 7b, a related word database 72 is stored in advance.

[0130] <Related Word Database 72> The related word database 72 is stored in advance in the database 7b. In the related word database 72, for example, as shown in Fig. 10, reference generated theme information D721 and reference related generated theme information D722 are stored in advance in association with each other. The related word database may be a database created in advance by the user U, or may use known concept dictionary data such as "WordNet."

[0131] The reference generating theme information D721 is composed of one or more generating theme information. The reference generating theme information D721 may include information corresponding to the generating theme information D12. The reference related generating theme information D722 is composed of one or more related generating theme information. The reference related generating theme information D722 may include information corresponding to the related generating theme information D82.

[0132] The reference generation theme information D721 is linked to the reference related generation theme information D722 including, for example, one or more related generation themes. The generation theme "X" included in the reference generation theme information D721 may be linked to the related generation theme A "X1" and the related generation theme B "X2" included in the reference related generation theme information D722. Specifically, the generation theme "Azuchi-Momoyama period" may be linked to the related generation theme A "history" and the related generation theme B "Toyotomi Hideyoshi."

[0133] Next, the operation of the learning material generation system 100 in this embodiment will be described in detail.

[0134] <Query conversion step S14> In the query conversion step S14, the query conversion unit 16 converts the query D1 by replacing the generation theme information D12 included in the query D1 acquired in the query acquisition step S11 with one piece of related generation theme information D82 acquired from the related word database 72 after referring to the related word database 72 (database 7b). That is, the query D1 executed on the database 7 includes the learning material generation request information D11 and the related generation theme information D82, but does not include the generation theme information D12 replaced with the related generation theme information D82.

[0135] In addition, the query conversion unit 16 may arbitrarily select one related generation theme to be replaced with the generation theme information D12 from one or more related generation themes included in the reference related generation theme information D722 constituting the related word database 72. In the example of Fig. 10, the query conversion unit 16 may arbitrarily select one of the generation themes "X1" and "X2" included in the reference related generation theme information D722 linked to the reference generation theme information D721 corresponding to the generation theme "X" to acquire it as the related generation theme information D82, and replace the generation theme information D12 with the generation theme information D12.

[0136] Furthermore, the query conversion unit 16 may select one related generation theme based on the track record, such as the number of times each related generation theme has been obtained from the related word database 72. For example, one related generation theme "X1" that has a high track record of being obtained from the related word database 72 may be selected as a related generation theme with an easy level of difficulty, and one related generation theme "X2" that has a low track record of being obtained from the related word database 72 may be selected as a related generation theme with a difficult level of difficulty.

[0137] <Learning material generation step S12> In the learning material generation step S12, the learning material generation unit 23 refers to the database 7 in response to the query D1 (generation request based on the learning material generation request information D11) acquired in the query acquisition step S11, and generates generation data D71 including the learning material data D711 based on the related generation theme included in the query D1 converted in the query conversion step S14. In this case, the large-scale language model 71 can automatically generate learning materials with different contents from the same generation theme (generation theme information D12). This can improve the convenience of the created learning materials.

[0138] According to this embodiment, the system further includes a query conversion unit 16 that converts the generation theme (generation theme information D12) included in the acquired query D1 into one related generation theme (related generation theme information D82). Therefore, the large-scale language model 71 can automatically generate learning materials with different contents from the same generation theme. This can improve the convenience of the created learning materials.

[0139] Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These novel embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, and are included in the scope of the invention and its equivalents described in the claims. [Explanation of symbols]

[0140] 100 Learning Material Generation System 1 User terminal 10. Chassis 101 CPU 102 ROM 103 RAM 104 Preservation Department 105~107 Interface 108 Input section 109 Display section 110 Internal Bus 11 Communications Department 12 Storage section 13 Query Acquisition Section 14 Query execution part 15 Learning material output section 16 Query conversion section 2 Server 20. Cabinet 201 CPU 202 ROM 203 RAM 204 Preservation Department 205 Interface 210 Internal Bus 21 Server Communication Department 22 Server memory unit 23 Learning Material Generation Unit 7 Database 71 Large-scale language models 72 Related Words Database 9. Communication Network U User S11 Query acquisition step S12 Learning material generation step S13 Learning material output step S14 Query transformation step D1 Query D11 Learning material generation request information D12 Generate Theme Information D13 Table of Contents Information D14 Theme Generation Request Information D15 Classification Theme Information D71 Generated Data D711, D712 learning material data D721 Reference generated theme information D722 Related generated theme information for reference D8 Interim data D81 Generate theme information D82 Related generated theme information< / user> < / system>

Claims

1. a query acquisition unit that acquires a query including a request for generating learning materials each including a combination of a question and an answer and a theme for generating the learning materials; a learning material generation unit that, when the query acquired by the query acquisition unit is executed, generates the learning material based on the generation theme by referring to a database in which a large-scale language model is previously stored; To be prepared A learning material generation system characterized by:

2. The query acquisition unit acquires the query including a request for generating the learning material and a plurality of data sets each including the generation theme and a table of contents of the questions; The learning material generation unit generates a plurality of the learning materials corresponding to the table of contents based on the plurality of data sets acquired by the query acquisition unit. The learning material generation system according to claim 1 .

3. The query acquisition unit acquires the query including the data set in which at least one of the generated theme and the table of contents is extracted from existing learning material data.

3. The learning material generation system according to claim 2,

4. The query acquisition unit acquires the query including a request for generating the theme and a classification theme thereof; The learning material generation unit generates the learning material based on the generation theme newly acquired based on the classification theme by referring to a database in which a large-scale language model is previously stored when the query acquired by the query acquisition unit is executed.

4. The learning material generation system according to claim 1, wherein:

5. A query conversion unit converts the generation theme included in the query acquired by the query acquisition unit into one of the related generation themes by referring to a database in which the generation theme and one or more related generation themes related to the generation theme are previously associated with each other, The learning material generation unit generates the learning material based on the related generation theme converted by the query conversion unit.

4. The learning material generation system according to claim 1, wherein:

6. a query acquisition step of acquiring a query including a request for generating learning material consisting of a combination of questions and answers and a theme for generating the learning material; a learning material generating step of executing the query acquired by the query acquiring step, and generating the learning material based on the generation theme by referring to a database in which a large-scale language model is stored in advance; Having A learning material generation method comprising the steps of:

7. a query acquisition step of acquiring a query including a request for generating learning material consisting of a combination of questions and answers and a theme for generating the learning material; a learning material generating step of executing the query acquired by the query acquiring step, and generating the learning material based on the generation theme by referring to a database in which a large-scale language model is stored in advance; to have a computer execute A learning material generation program characterized by:

Images