Language learning material production program, language learning material production device, and language learning material production method

Abstract

A representative embodiment of the present invention is a language teaching material production program executed by a computer capable of communicating with an automated conversation engine utilizing a large-scale language model, which sequentially inputs a first, second, and third prompts to the automated conversation engine. The first prompt is a prompt for setting an interviewer specification for a student to the automated conversation engine, the second prompt is a prompt for the automated conversation engine to have the student input a brief profile of himself / herself and to ask the student related questions about the profile to collect answers, and the third prompt is a prompt for the automated conversation engine to output language teaching materials customized for the student by adapting the self-introduction based on the related questions and the answers.

Description

[Technical field]

[0001] The present invention can be suitably used in a language teaching material production program, a language teaching material production device, and a language teaching material production method for producing language teaching materials suitable for students. [Background technology]

[0002] In language education, the importance of teaching materials is indisputable, and several inventions have been proposed for systems that can customize language teaching materials for each student.

[0003] Patent Document 1 discloses a language learning material creation system that easily creates learning materials for passive listening learning, which is said to be able to flexibly change and customize the learning content according to the learner's preferences, level, etc. Using input short sentences and a material database including dictionary data, the system creates learning materials that play back long sentences made by combining each short sentence and audio data for each short sentence on the user's terminal based on set conditions for passive listening.

[0004] Patent Document 2 discloses a language learning material customization system that allows users to freely customize language learning material content. Because users can freely customize language learning material content data by selecting sentences and devising sequence patterns, it is said that it is possible to provide language learning material content data that is more effective for language learning and is suited to the user.

[0005] Patent Document 3 discloses a registration program, a registration method, and an information processing device that are said to be capable of improving the quality of question and answer combinations generated. This program inputs a search query and a sentence included in a corresponding search result to a machine learning model, obtains a question sentence based on the search query and the sentence included in the search result from the machine learning model, and registers the combination of the question sentence and the sentence included in the search result as a question and answer combination in a storage device.

[0006] Patent Document 4 discloses a method of romanizing a geminated consonant in Japanese language learning materials, Japanese language learning materials using the method, and a Japanese language learning device that are said to enable efficient learning of geminated consonants. By using a method of romanizing a geminated consonant in Japanese language learning materials that uses a double vowel character notation in which a romanization character representing the vowel of the sound immediately before the geminated consonant is followed by a romanization character that is the same as the vowel, it is said that it becomes possible to read and learn a pronunciation that is close to the actual geminated consonant from the romanization displayed by the Japanese language learning materials and the Japanese language learning device. [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2018-116190 A [Patent Document 2] JP 2013-125056 A [Patent Document 3] JP 2023-174053 A [Patent Document 4] JP 2022-044354 A Summary of the Invention [Problem to be solved by the invention]

[0008] According to the inventions described in Patent Documents 1 and 2, language learning materials suitable for students can be created. However, content data such as pre-prepared materials can only be customized to suit students. Therefore, in order to accommodate all kinds of students, the amount of content data to be prepared in advance becomes enormous, which is not realistic. By combining the invention described in Patent Document 3, it may be possible to automatically generate content data such as materials to be prepared to some extent, but a huge amount of learning is required to create a machine learning model for this purpose.

[0009] Furthermore, even if it were possible to prepare a huge amount of content data, the selection of materials from that content data and how it is organized would be left to the students themselves or users such as teachers who know the students, requiring manual work each time.

[0010] An object of the present invention is to provide a computer program for creating language learning materials that are customized not only for each student's language level but also for the content.

[0011] Means for solving these problems will be described below, but other problems and novel features will become apparent from the description of this specification and the accompanying drawings. [Means for solving the problem]

[0012] A representative embodiment of the present invention is a language teaching material production program that is executed by a computer capable of communicating with an automatic conversation engine that utilizes a large-scale language model, and that sequentially inputs first, second, and third prompts to the automatic conversation engine.

[0013] The first prompt causes the automated conversation engine to set an interviewer specification for the student, the second prompt causes the automated conversation engine to input a brief profile of the student himself / herself and to ask the student relevant questions about the profile and collect answers, and the third prompt causes the automated conversation engine to output language learning materials customized for the student by adapting the student's self-introduction based on the relevant questions and the answers.

[0014] A second representative embodiment of the present invention is a language teaching material production device having a program installed on a computer capable of communicating with an automatic conversation engine that utilizes a large-scale language model, the program sequentially inputting first, second and third prompts to the automatic conversation engine.

[0015] The first prompt causes the automated conversation engine to set an interviewer specification for the student, the second prompt causes the automated conversation engine to input a brief profile of the student himself / herself and to ask the student relevant questions about the profile and collect answers, and the third prompt causes the automated conversation engine to output language learning materials customized for the student by adapting the student's self-introduction based on the relevant questions and the answers.

[0016] A third representative embodiment of the present invention is a method for creating language teaching materials, in which a first, second and third prompts are sequentially input to an automatic conversation engine that utilizes a large-scale language model by a computer capable of communicating with the automatic conversation engine.

[0017] The first prompt causes the automated conversation engine to set an interviewer specification for the student, the second prompt causes the automated conversation engine to input a brief profile of the student himself / herself and to ask the student relevant questions about the profile and collect answers, and the third prompt causes the automated conversation engine to output language learning materials customized for the student by adapting the student's self-introduction based on the relevant questions and the answers.

[0018] Here, the division between the first, second and third prompts is not important, as long as the above contents are input in sequence by the prompts.

[0019] Furthermore, the student's profile information and answers to questions may be entered by the student himself / herself, or may be done by an operator, for example. Effect of the Invention

[0020] The effects obtained by the present invention can be briefly explained as follows.

[0021] That is, it is possible to provide a language teaching material production program, a language teaching material production device, and a language teaching material production method for producing language teaching materials that are customized not only for each student's language level but also for the contents thereof. [Brief description of the drawings]

[0022] [Figure 1] FIG. 1 is an explanatory diagram showing a typical example of the configuration of a language teaching material production device and program according to the present invention. [Diagram 2] FIG. 2 is an explanatory diagram showing a schematic example of the configuration of an entire system including a computer on which the language teaching material production program of the present invention is installed and an automatic conversation engine that utilizes a large-scale language model used by the computer. [Diagram 3] FIG. 3 is an explanatory diagram showing an example of the operation of a computer in which the language teaching material production program of the present invention is installed. [Figure 4] FIG. 4 shows examples of the first to third prompts in the second embodiment. [Diagram 5] FIG. 5 shows an example (first half) of a related question and its answer in the second embodiment. [Figure 6] FIG. 6 shows examples of related questions and their answers (second half) in the second embodiment. [Figure 7] FIG. 7 shows an example of a generated script in the second embodiment. [Figure 8] FIG. 8 shows examples of the first to third prompts in the third embodiment. [Figure 9] FIG. 9 is an example of output in the third embodiment. [Figure 10] FIG. 10 is an example of the fourth prompt in the fourth embodiment. [Figure 11] FIG. 11 is an example of output in the fourth embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0023] 1. Overview of the embodiment First, a summary of representative embodiments disclosed in the present application will be described. Reference numerals in parentheses in the summary of the representative embodiments refer only to components included in the concept of the components to which they are attached.

[0024] [1] Prompts for generative AI that creates language learning materials from students' own profiles A representative embodiment disclosed in the present application is a language teaching material production program (20) that is executed by a computer (50) capable of communicating with an automated conversation engine (80) that utilizes a large-scale language model, and that sequentially inputs first, second and third prompts (1, 2, 3) to the automated conversation engine.

[0025] The first prompt (1) is a prompt for the automatic conversation engine to set the specifications of an interviewer for the student. The second prompt (2) is a prompt for the automatic conversation engine to input a brief profile of the student himself / herself and to ask the student relevant questions about the profile and collect answers. The third prompt (3) is a prompt for the automatic conversation engine to output language learning materials customized for the student by adapting the profile based on the relevant questions and the answers.

[0026] This makes it possible to provide a computer program that produces language learning materials that are customized not only for the language level but also for the content of each individual student.

[0027] [2] Dramatically dramatize your self-introduction In the language teaching material production program of [1], the profile is a brief self-introduction of the student. The first prompt or the second prompt includes, as the interviewer's specifications, asking the student questions about the highlights and lowlights of his / her life and his / her dreams for the future. The third prompt includes instructing the automatic conversation engine to maintain a theme consistent with the self-introduction and to dramatize the self-introduction with answers to the questions about the highlights and lowlights of his / her life and his / her dreams for the future.

[0028] This allows the language learning materials to become a dramatic introduction to the students who use them, motivating them to learn.

[0029] [3] Ensuring quality as language learning materials In the language teaching material production program of [2], the first prompt further includes, as the specifications of the interviewer, maintaining a friendly tone toward the student and showing empathy for their personal history to create an environment that encourages responses. The second prompt is a prompt that causes the automatic conversation engine to limit the number of related questions to a predetermined number or less in a question-and-answer format. The third prompt is a prompt that specifies, as specifications of the language teaching material, the use of concise vocabulary and syntax, the use of all predetermined basic sentence patterns, and the use of a predetermined level of vocabulary.

[0030] This helps ensure the quality of the language learning material.

[0031] [4] Language learning materials that match students’ personal information, such as their occupations In the language teaching material production program of [1], the profile is personal information including a field of expertise. The first prompt is a prompt for setting specifications of a writer of language teaching materials in the automatic conversation engine. The second prompt includes, as the writer's specifications, a question inquiring about the student's language level in a predetermined language, and the related question about personal information including the field of expertise. The third prompt specifies that, as the language teaching materials to be produced by the writer, a set of teaching material sentences in the foreign language to be studied and translations in the predetermined language should be generated, that the teaching material sentences should use vocabulary of the language level answered by the student, that all predetermined basic sentence patterns should be used, and that the translations should be a direct translation rather than an arbitrary translation.

[0032] This allows the language learning materials to be tailored to the students' own fields of expertise, such as their occupations, and increases their motivation to learn. Furthermore, by including personal information such as age, gender, and hobbies, the language learning materials created can be more easily adapted to familiar topics.

[0033] [5] Speaking consulting function for Japanese people In any one of claims [1] to [4], the language teaching material production program further inputs a fourth prompt (4) to the automatic conversation engine following the first, second and third prompts.

[0034] The profile, the related questions and the answers are in Japanese, the language learning materials are in English, and the fourth prompt is a prompt that instructs the automatic conversation engine to, assuming that the engine is a professional English teacher and speaking consultant for Japanese learners, faithfully convert the pronunciation of the English sentences generated as the language learning materials into katakana words as if they were pronounced by a native speaker and display them side by side.

[0035] As a result, when the language learning materials being produced are English learning materials aimed at Japanese people, pronunciation that is easy for Japanese people to understand is written alongside the English text, thereby improving the effectiveness of students' speaking studies.

[0036] [6] Conversion procedure for the speaking consulting function for Japanese In the language teaching material production program of [5], the fourth prompt is a prompt that further instructs the automatic conversation engine to convert the generated English sentence into pronunciation data that reflects sound changes across words based on general colloquial speech, and to generate the katakana word from the pronunciation data.

[0037] This allows the pronunciation of native speakers to be faithfully expressed in katakana words.

[0038] [7] A generative AI chatbot that creates language learning materials from students’ own profiles A representative embodiment disclosed in the present application is a language teaching material production device (10) having installed in a computer (50) capable of communicating with an automatic conversation engine (80) that utilizes a large-scale language model a program for inputting first, second and third prompts in sequence to the automatic conversation engine.

[0039] The first prompt causes the automated conversation engine to set an interviewer specification for the student, the second prompt causes the automated conversation engine to input a brief profile of the student and to ask the student relevant questions about the profile and collect answers, and the third prompt causes the automated conversation engine to output language learning materials customized for the student by adapting the profile based on the relevant questions and the answers.

[0040] This makes it possible to provide a computer program that produces language learning materials that are customized not only for the language level but also for the content of each individual student.

[0041] [8] Dramatically dramatize your self-introduction In the language teaching material production device of [7], the profile is a self-introduction. The first prompt or the second prompt includes, as a specification of the interviewer, asking the student questions about the highlights and lowlights of his / her life and his / her dreams for the future, and the third prompt includes instructing the automatic conversation engine to maintain a theme consistent with the self-introduction and to dramatize the self-introduction with answers to the questions about the highlights and lowlights of his / her life and his / her dreams for the future.

[0042] This allows the language learning materials to become a dramatic introduction to the students who use them, motivating them to learn.

[0043] [9] Ensuring quality as language learning materials In the language teaching material production device of [8], the first prompt further includes, as the specifications of the interviewer, maintaining a friendly tone toward the student and showing empathy for their personal history to create an environment that encourages responses. The second prompt is a prompt that causes the automatic conversation engine to limit the number of related questions to a predetermined number or less in a question-and-answer format, and the third prompt is a prompt that specifies, as specifications of the language teaching material, the use of concise vocabulary and syntax, the use of all predetermined basic sentence patterns, and the use of a predetermined level of vocabulary.

[0044] This helps ensure the quality of the language learning material.

[0045]

[10] Language learning materials that match students’ personal information, such as their occupations In the language teaching material production device of [7], the profile is personal information including a field of expertise. The first prompt is a prompt for setting specifications of a text writer of language teaching materials in the automatic conversation engine. The second prompt includes, as the specifications of the text writer, a question inquiring about the language level of the student in a predetermined language, and the related question about personal information including the field of expertise. The third prompt specifies that, as the language teaching materials to be generated by the text writer, a set of text sentences in the foreign language to be studied and translations in the predetermined language should be generated, that the text sentences should use vocabulary of the language level answered by the student, that all predetermined basic sentence patterns should be used, and that a direct translation should be generated for the translations, not a paraphrase.

[0046] This allows the language learning materials to be tailored to the students' own fields of expertise, such as their occupations, and increases their motivation to learn. Furthermore, by including personal information such as age, gender, and hobbies, the language learning materials created can be more easily adapted to familiar topics.

[0047]

[11] Speaking consulting function for Japanese people In any one of claims [7] to

[10] , a language teaching material production program (20) is provided, which further inputs a fourth prompt (4) to the automatic conversation engine following the first, second and third prompts, wherein the profile, the related questions and the answers are in Japanese, and the language teaching materials are in English.

[0048] The fourth prompt (4) is a prompt that instructs the automatic conversation engine to convert the pronunciation of the English sentences generated as the language learning material into katakana words faithfully as a native speaker would pronounce them, and to display them side by side, assuming that the person in question is a professional English instructor and speaking consultant for Japanese learners.

[0049] As a result, when the language learning materials being produced are English learning materials aimed at Japanese people, pronunciation that is easy for Japanese people to understand is written alongside the English text, thereby improving the effectiveness of students' speaking studies.

[0050]

[12] Conversion procedure for speaking consulting function for Japanese In the language teaching material production device of

[11] , the fourth prompt is a prompt that further instructs the automatic conversation engine to convert the generated English sentence into pronunciation data that reflects sound changes across words based on general colloquial speech, and to generate the katakana word from the pronunciation data.

[0051] This allows the pronunciation of native speakers to be faithfully expressed in katakana words.

[0052]

[13] How to use generative AI to create language learning materials from students’ own profiles A representative embodiment disclosed in this application is a method for producing language teaching materials, in which a computer (50) capable of communicating with an automated conversation engine (80) utilizing a large-scale language model sequentially inputs first, second and third prompts (1, 2, 3) to the automated conversation engine. The first prompt (1) is a prompt for setting the specifications of an interviewer for a student in the automated conversation engine, the second prompt (2) is a prompt for the automated conversation engine to input a brief profile of the student himself / herself and to ask the student related questions about the profile and collect answers, and the third prompt (3) is a prompt for the automated conversation engine to output language teaching materials customized for the student by adapting the profile based on the related questions and the answers.

[0053] This makes it possible to provide a computer program that produces language learning materials that are customized not only for the language level but also for the content of each individual student.

[0054]

[14] Dramatically dramatize your self-introduction In the language teaching material production method of

[13] , the profile is a self-introduction. The first prompt or the second prompt includes, as the interviewer's specifications, asking the student questions about the highlights and lowlights of his / her life and his / her dreams for the future, and the third prompt includes instructing the automatic conversation engine to maintain a theme consistent with the self-introduction and dramatize the self-introduction with answers to the questions about the highlights and lowlights of his / her life and his / her dreams for the future.

[0055] This allows the language learning materials to become a dramatic introduction to the students who use them, motivating them to learn.

[0056]

[15] Ensuring quality as language learning materials In the language teaching material production method of

[14] , the first prompt further includes, as the specifications of the interviewer, maintaining a friendly tone toward the student and showing empathy for their personal history to create an environment that encourages answers. The second prompt is a prompt that causes the automatic conversation engine to limit the number of related questions to a predetermined number or less in a question-and-answer format, and the third prompt is a prompt that specifies, as specifications of the language teaching material, the use of concise vocabulary and syntax, the use of all predetermined basic sentence patterns, and the use of a predetermined level of vocabulary.

[0057] This helps ensure the quality of the language learning material.

[0058]

[16] Language study materials that match students’ personal information, such as their occupations In the language teaching material production method of

[15] , the profile is personal information including a field of expertise. The first prompt is a prompt for setting specifications of a writer of language teaching materials in the automatic conversation engine. The second prompt includes, as the writer's specifications, a question inquiring about the student's language level in a predetermined language, and the related question about personal information including the field of expertise. The third prompt specifies that, as the language teaching materials to be produced by the writer, a set of teaching material sentences in the foreign language to be studied and translations in the predetermined language should be generated, that the teaching material sentences should use vocabulary of the language level answered by the student, and all predetermined basic sentence patterns should be used, and that the translations should be a direct translation rather than an arbitrary translation.

[0059] This allows the language learning materials to be tailored to the students' own fields of expertise, such as their occupations, and increases their motivation to learn. Furthermore, by including personal information such as age, gender, and hobbies, the language learning materials created can be more easily adapted to familiar topics.

[0060]

[17] Speaking consulting function for Japanese people In any one of

[13] to

[16] , a fourth prompt is further input to the automatic conversation engine following the first, second and third prompts, wherein the profile, the related questions and the answers are in Japanese and the language learning materials are in English. The fourth prompt instructs the automatic conversation engine to convert the pronunciation of the English sentences generated as the language learning materials into katakana words faithfully as if they were pronounced by a native speaker, and to display them side by side, assuming that the automatic conversation engine is a professional English instructor and speaking consultant for Japanese learners.

[0061] As a result, when the language learning materials being produced are English learning materials aimed at Japanese people, pronunciation that is easy for Japanese people to understand is written alongside the English text, thereby improving the effectiveness of students' speaking studies.

[0062]

[18] Conversion procedure for speaking consulting function for Japanese In the language learning material production method of

[17] , the fourth prompt is a prompt that further instructs the automatic conversation engine to convert the generated English sentence into pronunciation data that reflects sound changes across words based on general colloquial speech, and to generate the katakana word from the pronunciation data.

[0063] This allows the pronunciation of native speakers to be faithfully expressed in katakana words.

[0064] Here, the division between the first, second, third and fourth prompts (1, 2, 3, 4) is not important, and the above contents should be input by the prompts in order. Also, the student's profile input and answers to questions may be done by the student himself, or an operator may do it for him.

[0065] 2. Details of the embodiment The embodiment will now be described in further detail.

[0066] [Embodiment 1] FIG. 1 is an explanatory diagram showing a typical example of the configuration of a language teaching material production device and program of the present invention, and FIG. 2 is an explanatory diagram showing a typical example of the configuration of the entire system including a computer 50 on which the language teaching material production program 20 is installed and an automatic conversation engine that utilizes the large-scale language model used by the computer 50.

[0067] The computer 50 on which the language teaching material production program 20 is installed is a computer equipped with a processor 51, a storage device 52, and a user interface 53, and is connected so as to be able to communicate with an automatic conversation engine 80 that uses a large-scale language model via a network 60 such as the Internet. The computer 50 may be, for example, a personal computer or a portable information device such as a smartphone. Information such as text data can be input and output via the user interface directly with students who use the language teaching materials, or via educators who provide language education. Specific examples of the automatic conversation engine 80 using a large-scale language model include ChatGPT by OpenAI (registered trademark), Gemini by Google (registered trademark), and LLaMA by Meta (registered trademark), but are not limited to these. The automatic conversation engine 80 may be a so-called chatbot that can automatically output a natural response using a large-scale language model to a sentence input by a user. It is known that the automatic conversation engine 80 can output a more natural and appropriate response by giving a command, instruction, or specification called a prompt. In addition, many of the known automatic conversation engines 80 are configured to be accessible and usable via the Internet, but the language teaching material production device and program of the present invention may be accessed in any manner to the automatic conversation engine 80.

[0068] The language teaching material production program 20 of the present invention is installed in a storage device 52 of a computer 50 capable of communicating with an automatic conversation engine 80 that utilizes a large-scale language model, as shown in Fig. 2, for example, and executed by a processor 51 to function as a language teaching material production device 10. The computer 50 does not need to be a computer that is directly operated by a user, but may be a server computer on a cloud that provides a cloud application that can be used by a user via a network such as the Internet.

[0069] A computer 50 executing the language teaching material production program 20 of the present invention inputs the first, second and third prompts (1, 2, 3) to an automatic conversation engine 80 in sequence.

[0070] The first prompt 1 is a prompt that causes the automated conversation engine 80 to set the specifications of an interviewer for the student. The second prompt 2 is a prompt that causes the automated conversation engine 80 to input a brief profile of the student himself, and to ask the student relevant questions about the profile and collect answers. The third prompt 3 is a prompt that causes the automated conversation engine 80 to output language learning materials customized for the student by adapting the input profile based on the relevant questions and answers.

[0071] This makes it possible to provide a computer program that produces language learning materials that are customized not only for the language level but also for the content of each individual student.

[0072] The profile may be, for example, a self-introduction by the student (Embodiment 3 described below), occupation or specialty (Embodiment 4 described below), age, sex, hobbies, etc. By setting the specifications of the interviewer for the student in the automatic conversation engine 80 at the first prompt 1, questions that dig deeper into the student's input profile are asked in response to the second prompt 2, and the student is made to answer, so that the language learning materials produced have content that matches the student's individual profile. The language learning materials produced have content that is close to the situation in which the student would likely converse in the foreign language, or content that is of high interest in line with the student's hobbies and preferences, which increases the student's motivation to learn and is actually usable, thereby improving the learning effect.

[0073] FIG. 3 is an explanatory diagram showing a typical example of the operation of a computer 50 in which the language teaching material production program 20 of the present invention is installed.

[0074] The session with the automatic conversation engine 80 is displayed on a display which is one of the user interfaces 53 of the computer 50 operating as the language teaching material production device 10 .

[0075] When the first prompt 1 and the second prompt 2 read from the storage device 52 in the computer 50 are sent to the automatic conversation engine 80, the automatic conversation engine 80 displays an input request sentence a on the display to prompt the student to input a profile. For example, it displays "Could you please briefly tell me about your occupation and career?" to prompt the student to input a profile.

[0076] The student inputs profile b from a keyboard, which is one of the user interfaces 53. Other media such as file input or voice input may also be used. This can be handled by specifying input specifications from other media and the processing method for the automatic conversation engine 80. For example, the automatic conversation engine 80 is instructed to perform voice recognition and have the student confirm the recognition results converted into text.

[0077] Next, the automatic conversation engine 80 generates and outputs a related question c instructed in the second prompt 2, and obtains an answer d to the related question c. The related question c and the answer d are performed, for example, a predetermined number of times, based on the specifications instructed in the second prompt 2.

[0078] After the related questions c and answers d in the specifications instructed in the second prompt 2 are completed, language learning materials e are generated according to the third prompt 3 input to the automatic conversation engine 80. Based on the input profile b, the dramatized sentences are output as the language learning materials e, based on the related questions c and answers d.

[0079] When the learning subject is English, the language learning material e is an English sentence. Furthermore, by inputting a fourth prompt 4 described below into the automatic conversation engine 80 and inputting the English language learning material e, language learning material f is output based on the fourth prompt 4, along with the katakana word indicating the pronunciation.

[0080] Instead of input and output using a display and a keyboard, input and output using other media such as voice may be adopted. Although the description has been given assuming that the students themselves input the data, a mentor or an operator may assist or act on behalf of the students in inputting the data. This is not limited to this embodiment, but is common to the entire specification.

[0081] [Embodiment 2] Enter your self-introduction as your profile In the above-mentioned embodiment 1, the profile input by the student can be a simple self-introduction of the student. The first prompt 1 preferably further includes, as an interviewer specification, an instruction to ask the student questions about the highlights and lowlights of his / her life and his / her dreams and goals for the future. The third prompt 3 preferably further includes, as an instruction to the automatic conversation engine 80, an instruction to maintain a theme in line with the self-introduction and dramatize the self-introduction by answers to questions about the highlights and lowlights of his / her life and his / her dreams and goals for the future. Here, the highlights of his / her life mean events in his / her life that made him / her feel elated, such as his / her own success experiences, and conversely, the lowlights of his / her life mean events in his / her life that made him / her feel depressed, such as trials. They may be rephrased as good events, troublesome events, etc., without using the strict meaning.

[0082] This allows the language teaching materials to become a dramatic introduction to the students who use them, and increases their motivation to learn. The highlights and low points of a student's life are important experiences that involve emotional ups and downs, and by using these as language teaching materials, it becomes an easy way for the student to empathize and a self-introduction that they will often have the opportunity to talk about to a third party, thereby increasing motivation to learn and the learning effect. By adding a question about future dreams and goals to the third prompt 3, the language teaching materials created can be dramatized dramatically even if the student is unable to answer well about the highlights and low points of their life.

[0083] The first prompt 1 may further include instructions for the interviewer to maintain a friendly tone toward the student and to empathize with the student's personal history to create an environment in which the student can easily answer questions. The second prompt 2 may further include instructions for limiting the number of related questions to a predetermined number or less in a question-and-answer format, and the third prompt may further include instructions for the language teaching material to use concise vocabulary and syntax, to use all of the specified basic sentence patterns, and to use vocabulary at a specified level. This ensures the quality of the language teaching material. For example, in the case of English, in addition to specifying that all five basic sentence patterns be used, detailed specifications such as compound sentences, relative pronoun syntax, and conditional syntax may be specified depending on the level.

[0084] FIG. 4 is an example of the first to third prompts (1, 2, 3). This is an example using ChatGPT by OpenAI as an automatic conversation engine 80 that uses a large-scale language model. There is no need to clearly separate the first, second, and third prompts (1, 2, 3). First, "Interview Navigator is a GPT" instructs the GPTs to act as an interviewer. The following "designed for conducting in-depth interviews in Japanese, focusing on life highlights, lows, and future aspirations." instructs the interviewer to ask questions about the highlights and lowlights of their lives and their future dreams and goals. The following "It engages in a friendly tone, creating a comfortable environment for sharing personal stories." is an example of how to proceed with the interview, and it is possible to provide an environment that is easy for students to answer by instructing them to relax and answer questions.

[0085] The next instruction corresponds to the second prompt 2. "The GPT tailors questions to the user's career introduction, with a limit of 10 questions per interview and one question per message." allows the student to enter a brief profile of himself / herself, and to ask the student related questions about the profile to collect answers. The format is one question and one answer, and the limit is 10 questions. This allows the student to relax and take the interview without feeling excessive stress. The number of questions can be adjusted appropriately depending on the attributes of the student. For example, if the student is a child, it is better to place more emphasis on future dreams and goals rather than the highlights and lowlights of life, while asking fewer questions to keep the student focused. Conversely, if the student is older, it is better to place more emphasis on the highlights and lowlights of life, and increase the number of questions depending on the student's willingness to talk.

[0086] After the interview is finished, you can instruct the system to automatically move to the self-introduction English generation task once the probing questions have been completed by selecting "After concluding the interview, Interview Navigator will automatically create a self-introduction script in English." This corresponds to the third prompt 3. At this point, it is a good idea to specify in detail the specifications for the English script to be generated. In the example in Figure 4, the following five points are specified. (1) "Use simple vocabulary and syntax to ensure clarity": Use simple vocabulary and syntax. (2) "Maintain the interviewee as the subject of the script": The subject of the script should be the student who is the interviewee. (3) "Incorporate all five basic English sentence structures (declarative, interrogative, imperative, exclamatory, and conditional) in the script.": Be sure to use the basic sentence structures (the five English sentence structures: SV, SVO, SVC, SVOO, SVOC) (4) "The script will be made based on the vocabulary in correspondence with CEFR B2.": The script will use vocabulary that corresponds to the English level of CEFR B2. The level of English may be generated according to the level of the students. On the other hand, in order to dramatize the script impressively, it is advisable to create the vocabulary level based on the B2 level regardless of the user's level. (5) "The GPT avoids specific topics for broad discussions, culminating in an emotionally engaging script that reflects the interviewee's journey.": Avoids discussions on generalities, focuses on the interviewee's background, and creates a dramatic performance. Finally, the book gives a general outline of the basic specifications required for a script, allowing students to create scripts that are easy for listeners to empathize with, as well as the students themselves.

[0087] Figure 5 and Figure 6 are examples of related questions and their answers, with Figure 5 being the first half and Figure 6 being the second half. Figure 7 is an example of a script generated after completing the questions and answers in Figures 5 and 6.

[0088] In the first half of Figure 5, the Interview Navigator, formed by the first to third prompts, first asks about the student's occupation and receives a response from the student. Praising the student for a "great experience," the Interview Navigator asks the student to explain the occupation in more detail. The Interview Navigator then asks about the low points of their life, such as "a particularly memorable challenge," while hinting at "various issues and difficulties," and asks additional questions about the highlights, such as "successful experiences." Furthermore, in the second half of Figure 6, the Interview Navigator asks questions about the student's future dreams and goals, such as "What goals and prospects do you have?" and "Are there any challenges you would like to take on in your future career, or specific goals you would like to achieve?"

[0089] After completing these questions, the Interview Navigator generates a script for the student to introduce himself / herself, as shown in the example in Figure 7. The generated script includes the highlights and lowlights of the student's life in order, such as "A significant turning point in my career was...", "This challenging period was...", and "I have since broadened my focus to...", and concludes with "My goal is...", describing the student's dreams and goals for the future. In this way, the script is easy for not only the student but also the listener to empathize with.

[0090] In addition, the scripts that were created met the specified specifications, which were to have the student themselves as the subject, to use the five basic sentence patterns of English, and to use vocabulary at an appropriate level.

[0091] [Embodiment 3] Language learning materials suited to students' professional fields In the above embodiment 1, the profile can be personal information of the student, including his / her own field of expertise.

[0092] 8 shows examples of the first to third prompts in this embodiment. This is an example in which ChatGPT by OpenAI is used as the automatic conversation engine 80 that uses a large-scale language model.

[0093] The first prompt is a prompt that sets the specifications of a sentence composer for language learning materials to ChatGPT. "Sentence Composer is a professional, detailed GPT designed for English language learners, focusing on CEFR levels." This instructs GPTs to act as sentence composers.

[0094] The second prompt states, "It begins by confirming the learner's CEFR level. Following this, it gathers additional information about their job, industry, age, gender, and also inquires about their hobbies." As a specification by the writer, it instructs the writer to ask the student questions in the specified language about their language level, as well as questions about personal information including the above-mentioned area of ​​expertise.

[0095] The third prompt instructs the writer to create a set of English (foreign language) sentences and Japanese translations for the language learning materials, to use vocabulary of the student's language level and all five basic English sentence patterns, and to generate literal translations rather than paraphrases for the translations. More specifically, "This comprehensive personal profile, including hobbies, helps Sentence Composer tailor up to 10 example sentences that align with the specified CEFR level, with the level serving as the upper limit." instructs the writer to create 10 example sentences that include topics about the student's hobbies, and to keep the level within the CEFR level that the student answered. Furthermore, "Each English sentence is accompanied by a precise Japanese translation." instructs the writer to provide an accurate Japanese translation for each English sentence. Furthermore, as stated in the document, "Sentence Composer ensures the inclusion of all five basic English sentence patterns at least once in its examples, providing a varied and practical learning experience while maintaining a professional interaction throughout," the document instructs students to use each of the five basic English sentence patterns at least once in the texts they create, and finally concludes by instructing them to create language teaching materials that provide a varied and practical learning experience while maintaining a professional interaction throughout.

[0096] FIG. 9 is an output example in the third embodiment. ChatGPT, which is the automatic conversation engine 80, behaves as GPTs “Sentence Composer” by inputting the above first to third prompts. The Sentence Composer first asks the student about the CEFR level, occupation, industry, age, gender, hobbies, etc. When the student responds by inputting “CEFR level: B1, job: software engineer, industry: web service industry, gender: female, age: 35, hobbies: childcare, camping, watching videos”, the Sentence Composer responds, “Thank you. I will create English sentence examples including hobbies of childcare, camping, and watching videos for a 35-year-old software engineer with CEFR level B1 who works in the web service industry. Each sentence uses various sentence patterns.” As instructed, 10 teaching sentences are output together with Japanese translations. Due to space constraints, the fourth and subsequent sentences have been omitted, but each of the five basic English sentence patterns (pattern 1, pattern 2, pattern 3, etc.) is used at least once, and the sentences are generated to include a variety of sentence patterns, such as conditional statements (if statements), passive sentences, and questions.

[0097] As described above, language learning materials can be made to suit the students' own professional fields, such as their occupations, and this can increase their motivation to learn. Furthermore, by including personal information such as age, gender, and hobbies, the language learning materials created can be made to be more familiar with topics.

[0098] [Embodiment 4] The language teaching material production program 20 of the present invention can further input a fourth prompt 4 to the automatic conversation engine 80 following the first, second and third prompts (1, 2, 3). This is an embodiment in which the profile, related questions and answers input by the student are in Japanese, and the language teaching materials are in English. The fourth prompt 4 gives the automatic conversation engine 80 the specification that the student is a professional English teacher for Japanese learners and a speaking consultant, and instructs the automatic conversation engine 80 to convert the pronunciation of the English sentences generated in the above-mentioned embodiment 1, 2 or 3 into katakana words faithfully as if they were pronounced by a native speaker, and to display them side by side with the English sentences. This allows pronunciations that are easy for the student to understand to be displayed side by side with the English sentences, improving the effectiveness of the student's speaking learning.

[0099] More preferably, the fourth prompt 4 further includes a command for instructing the automatic conversation engine 80 to convert the input English sentence into pronunciation data reflecting sound changes across words based on general colloquial speech, and to generate katakana words from the pronunciation data. This allows the pronunciation of a native speaker to be faithfully expressed in katakana words. Words and phonetic symbols representing their pronunciations have a 1:1 correspondence as far as a dictionary is concerned, but in actual sentences, the pronunciation of adjacent words influences each other and changes depending on the speaker's feelings and intentions. Therefore, by reflecting sound changes across words based on general colloquial speech in the phonetic symbols, more natural pronunciations can be generated.

[0100] Here, the pronunciation data may be text-based data such as phonetic symbols, voice data itself, or data expressed by extracting features from voice. Voice features may include, for example, consonants, vowels, stress, rhyme, intonation, and physical data such as frequency and sound pressure. The following is an example in which phonetic symbols are used as the pronunciation data.

[0101] 10 is an example of a fourth prompt in this embodiment. This is an example in which ChatGPT by OpenAI is used as the automatic conversation engine 80 that uses a large-scale language model.

[0102] First, you give ChatGPT the command, "You are a professional English teacher and speaking consultant for Japanese learners. Your job is to 'convert the pronunciation of English sentences into katakana words faithfully to how a native speaker would pronounce them.' The conversion steps are as follows."

[0103] Next, the conversion procedure is given. First, the instructions are specific: "Convert English text into phonetic symbols," and then "Convert the output phonetic symbols into katakana words faithful to the native pronunciation." In addition, the instructions state that "When converting to phonetic symbols, there are many cases where sound changes across words, such as linking, reduction, flapping, assimilation, and weakening, occur, so take this into consideration when converting," that "the pronunciation should be based on general American English," and that "When converting to katakana words, if there is no suitable katakana that matches the pronunciation, select the one that is closest in sound." In addition, the instructions state that a reference example will be provided below as a "model," and instruct the user to use the output format that follows the example, and to output only the final result without including the conversion procedure. Finally, the reference example is provided as a "model."

[0104] FIG. 11 is an example of output in the fourth embodiment.

[0105] When the following sentence is entered as the English sentence to be converted: "But that was not so easy. I tried the auditions, and I failed countless times. But actually I didn't care because I had confidence that I could make it.", the pronunciation in katakana is written alongside each sentence. The katakana is not written in 1:1 correspondence with the English word, but reflects the changes in pronunciation that are influenced by adjacent words. As described above, pronunciation that is easy for students to understand is written alongside the English sentence, which can improve the effectiveness of speaking learning.

[0106] As mentioned above, the pronunciation data may be voice data itself instead of phonetic symbols. In that case, the specific conversion procedure described above is realized by including a specific instruction in the fourth prompt such as "First, convert the English sentence into voice data by a native English speaker, and then convert the converted voice data into Katakana words faithfully to the pronunciation."

[0107] Furthermore, the pronunciation data may be configured to include multiple conversion steps. For example, specific instructions may be given to convert a given English sentence into speech data by a native English speaker, extract features such as consonants, vowels, stress, rhyme, and intonation from the speech data, and then generate a katakana word by associating the features with the most suitable katakana.

[0108] Alternatively, specific instructions may be given to generate katakana words by extracting features such as consonants, vowels, stress, rhyme, and intonation from a given English sentence, faithfully as a native speaker would pronounce it, without going through speech data from a native speaker, and then matching those features with the katakana that best suits them.

[0109] This example shows how the words are converted into katakana characters for Japanese people, but it can be changed to any other phonetic characters to suit the student's native language. For example, it can be expressed in Hangul characters for Korean people.

[0110] This embodiment has been described as the fourth prompt 4 being input to the automatic conversation engine 80 following the first, second and third prompts (1, 2, 3). However, by inputting the above-mentioned prompt disclosed as the fourth prompt 4 alone into the automatic conversation engine 80, it is possible to realize a language teaching material production program, a language teaching material production device, or a language teaching material production method that can convert any English sentence into a similar katakana word.

[0111] This embodiment is an example of a language learning material for Japanese-speaking students learning English, but the language to be studied may be any language. Also, similar embodiments can be realized by using any language that uses phonograms or general symbols to represent sounds instead of Japanese.

[0112] The invention made by the inventor has been specifically described above based on an embodiment, but it goes without saying that the invention is not limited thereto and can be modified in various ways without departing from the spirit of the invention. [Industrial Applicability]

[0113] The present invention can be suitably used in a language teaching material production program, a language teaching material production device, and a language teaching material production method for producing language teaching materials suitable for students. [Explanation of symbols]

[0114] 1,2,3,4 prompt 10 Language learning material production device 20 Language Teaching Material Production Program 50 Computer 51 Processors 52 Storage device 53 User Interface 60 Network 80 Automatic Conversation Engine

Claims

1. A language teaching material production program, which is executed by a computer capable of communicating with an automatic conversation engine utilizing a large-scale language model, and which sequentially inputs first, second and third prompts to the automatic conversation engine, the first prompt is a prompt for causing the automatic conversation engine to act as an interviewer for the student and for setting specifications for the interviewer; the second prompt prompts the automated conversation engine to input a profile of the student and to ask the student relevant questions that delve deeper into the profile to gather responses; the third prompt causes the automated conversation engine to output language learning materials customized for the student by adapting the profile based on the relevant questions and the answers; Language teaching materials production program.

2. In claim 1, The profile is a self-introduction, The first prompt or the second prompt includes, as specified by the interviewer, asking the student questions about the highlights and lowlights of their life and their dreams for the future; the third prompt includes instructing the automated conversation engine to keep the self-introduction on theme and to dramatize the self-introduction with answers to questions about the highlights and lowlights of the person's life and their dreams for the future; Language teaching materials production program.

3. In claim 2, The first prompt further includes, as a specification of the interviewer, maintaining a friendly tone with the student and creating an environment that encourages responses by showing empathy for the student's personal history; the second prompt causes the automated conversation engine to limit the number of related questions to a predetermined number or less in a question-and-answer format; The third prompt is a prompt specifying, as specifications of the language learning material, that simple vocabulary and syntax be used, that all predetermined basic sentence patterns be used, and that a predetermined level of vocabulary be used. Language teaching materials production program.

4. In claim 1, The profile is personal information including areas of expertise; the first prompt is a prompt for setting specifications of a writer of language learning materials to the automatic conversation engine; The second prompt includes, as specified by the writer, asking the student in a predetermined language a question about the student's language level and the related question about personal information including the field of expertise; The third prompt instructs the text creator to generate a set of text sentences in the foreign language to be studied and translations in the predetermined language as language learning materials to be generated, to use vocabulary of the language level answered by the student and all predetermined basic sentence patterns for the text sentences, and to generate a direct translation, not a paraphrase, for the translations. Language teaching materials production program.

5. 5. The language teaching material production program according to claim 1, further comprising: inputting a fourth prompt to the automatic conversation engine following the first, second and third prompts, the profile, the related questions, and the answers are in Japanese, and the language learning materials are in English; The fourth prompt is a prompt instructing the automatic conversation engine to convert the pronunciation of the English sentences generated as the language learning material into katakana words faithfully as if they were pronounced by a native speaker and to display them side by side, assuming that the fourth prompt is a professional English instructor and speaking consultant for Japanese learners. Language teaching materials production program.

6. In claim 5, The fourth prompt is a prompt that further instructs the automatic conversation engine to convert the generated English sentence into phonetic symbols that reflect sound changes across words based on general colloquial language, and to generate the katakana word from the phonetic symbols. Language teaching materials production program.

7. A language teaching material production device, comprising: a computer capable of communicating with an automatic conversation engine utilizing a large-scale language model; and a program installed on the computer for sequentially inputting a first prompt, a second prompt, and a third prompt to the automatic conversation engine, the first prompt is a prompt for causing the automatic conversation engine to act as an interviewer for the student and for setting specifications for the interviewer; the second prompt prompts the automated conversation engine to input a profile of the student and to ask the student relevant questions that delve deeper into the profile to gather responses; the third prompt causes the automated conversation engine to output language learning materials customized for the student by adapting the profile based on the relevant questions and the answers; Language teaching material production device.

8. In claim 7, The profile is a self-introduction, The first prompt or the second prompt includes, as specified by the interviewer, asking the student questions about the highlights and lowlights of their life and their dreams for the future; the third prompt includes instructing the automated conversation engine to keep the self-introduction on theme and to dramatize the self-introduction with answers to questions about the highlights and lowlights of the person's life and their dreams for the future; Language teaching material production device.

9. In claim 8, The first prompt further includes, as a specification of the interviewer, maintaining a friendly tone with the student and creating an environment that encourages responses by showing empathy for the student's personal history; the second prompt causes the automated conversation engine to limit the number of related questions to a predetermined number or less in a question-and-answer format; The third prompt is a prompt specifying, as specifications of the language learning material, that simple vocabulary and syntax be used, that all predetermined basic sentence patterns be used, and that a predetermined level of vocabulary be used. Language teaching material production device.

10. In claim 7, The profile is personal information including areas of expertise; the first prompt is a prompt for setting specifications of a writer of language learning materials to the automatic conversation engine; The second prompt includes, as specified by the writer, asking the student in a predetermined language a question about the student's language level and the related question about personal information including the field of expertise; The third prompt instructs the text creator to generate a set of text sentences in the foreign language to be studied and translations in the predetermined language as language learning materials to be generated, to use vocabulary of the language level answered by the student and all predetermined basic sentence patterns for the text sentences, and to generate a direct translation, not a paraphrase, for the translations. Language teaching material production device.

11. 11. The language teaching material production program according to claim 7, further comprising: inputting a fourth prompt to the automatic conversation engine following the first, second and third prompts, the profile, the related questions, and the answers are in Japanese, and the language learning materials are in English; The fourth prompt is a prompt instructing the automatic conversation engine to convert the pronunciation of the English sentences generated as the language learning material into katakana words faithfully as if they were pronounced by a native speaker and to display them side by side, assuming that the fourth prompt is a professional English instructor and speaking consultant for Japanese learners. Language teaching material production device.

12. In claim 11, The fourth prompt is a prompt that further instructs the automatic conversation engine to convert the generated English sentence into phonetic symbols that reflect sound changes across words based on general colloquial language, and to generate the katakana word from the phonetic symbols. Language teaching material production device.

13. 1. A method for creating language teaching materials, comprising: inputting first, second and third prompts in sequence to an automatic conversation engine utilizing a large-scale language model by a computer capable of communicating with the automatic conversation engine, the first prompt is a prompt for causing the automatic conversation engine to act as an interviewer for the student and for setting specifications for the interviewer; the second prompt prompts the automated conversation engine to input a profile of the student and to ask the student relevant questions that delve deeper into the profile to gather responses; the third prompt causes the automated conversation engine to output language learning materials customized for the student by adapting the profile based on the relevant questions and the answers; How to create language teaching materials.

14. In claim 13, The profile is a self-introduction, The first prompt or the second prompt includes, as specified by the interviewer, asking the student questions about the highlights and lowlights of their life and their dreams for the future; the third prompt includes instructing the automated conversation engine to keep the self-introduction on theme and to dramatize the self-introduction with answers to questions about the highlights and lowlights of the person's life and their dreams for the future; How to create language teaching materials.

15. In claim 14, The first prompt further includes, as a specification of the interviewer, maintaining a friendly tone with the student and creating an environment that encourages responses by showing empathy for the student's personal history; the second prompt causes the automated conversation engine to limit the number of related questions to a predetermined number or less in a question-and-answer format; The third prompt is a prompt specifying, as specifications of the language learning material, that simple vocabulary and syntax be used, that all predetermined basic sentence patterns be used, and that a predetermined level of vocabulary be used. How to create language teaching materials.

16. In claim 13, The profile is personal information including areas of expertise; the first prompt is a prompt for setting specifications of a writer of language learning materials to the automatic conversation engine; The second prompt includes, as specified by the writer, asking the student in a predetermined language a question about the student's language level and the related question about personal information including the field of expertise; The third prompt instructs the text creator to generate a set of text sentences in the foreign language to be studied and translations in the predetermined language as language learning materials to be generated, to use vocabulary of the language level answered by the student and all predetermined basic sentence patterns for the text sentences, and to generate a direct translation, not a paraphrase, for the translations. How to create language teaching materials.

17. 17. A method for creating language teaching materials according to claim 13, further comprising inputting a fourth prompt to the automatic conversation engine following the first, second and third prompts, the profile, the related questions, and the answers are in Japanese, and the language learning materials are in English; The fourth prompt is a prompt instructing the automatic conversation engine to convert the pronunciation of the English sentences generated as the language learning material into katakana words faithfully as if they were pronounced by a native speaker and to display them side by side, assuming that the fourth prompt is a professional English instructor and speaking consultant for Japanese learners. How to create language teaching materials.

18. In claim 17, The fourth prompt is a prompt that further instructs the automatic conversation engine to convert the generated English sentence into phonetic symbols that reflect sound changes across words based on general colloquial language, and to generate the katakana word from the phonetic symbols. How to create language teaching materials.

Images