System

Abstract

To provide a system capable of comprehensively analyzing the grammar, punctuation, spelling, and consistency, clarity, and style of a sentence of an essay and reducing the scoring burden of a teacher.SOLUTION: The system includes a grammar analyzer, a punctuation analyzer, a spelling analyzer, a sentence consistency analyzer, a clarity analyzer, a style analyzer, a summary generator, and a scoring criteria setter. Using the generated AI, the grammar analyzer comprehensively analyzes the grammar of the essay, the punctuation analyzer comprehensively analyzes the punctuation of the essay, the spelling analyzer comprehensively analyzes the spelling of the essay, the sentence coherence analyzer comprehensively analyzes the sentence coherence of the essay, the clarity analyzer comprehensively analyzes the clarity of the essay, and the style analyzer comprehensively analyzes the style of the essay. The summary generation unit generates a summary from which the core content of the essay can be quickly grasped. The scoring standard setting unit sets a customizable scoring standard.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to comprehensively analyze essays, not only for grammar and punctuation, but also for consistency, clarity, and style, placing a heavy burden on teachers.

[0005] The system according to the embodiment aims to reduce the burden of grading teachers by comprehensively analyzing essays for grammar, punctuation, spelling, coherence, clarity, and style. [Means for solving the problem]

[0006] The system according to the embodiment includes a grammar analysis unit, a punctuation analysis unit, a spelling analysis unit, a writing consistency analysis unit, a clarity analysis unit, a style analysis unit, a summary generation unit, and a scoring criteria setting unit. The grammar analysis unit uses a generative AI to comprehensively analyze the grammar of an essay. The punctuation analysis unit uses a generative AI to comprehensively analyze the punctuation of an essay. The spelling analysis unit uses a generative AI to comprehensively analyze the spelling of an essay. The writing consistency analysis unit uses a generative AI to comprehensively analyze the writing consistency of an essay. The clarity analysis unit uses a generative AI to comprehensively analyze the clarity of an essay. The style analysis unit uses a generative AI to comprehensively analyze the style of an essay. The summary generation unit generates a summary that allows a reader to quickly grasp the core content of the essay. The scoring criteria setting unit sets customizable scoring criteria. [Effects of the Invention]

[0007] The system according to the embodiment comprehensively analyzes essays for grammar, punctuation, spelling, coherence, clarity, and style, reducing the burden of grading for teachers. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) Essay Master Assist, an embodiment of the present invention, is a system that uses generative AI to comprehensively analyze essays' grammar, punctuation, spelling, consistency, clarity, and style, generate summaries that allow students to quickly grasp the core content of the essay, and set customizable grading criteria. This reduces the burden of grading essays and provides valuable feedback for both teachers and students.

[0029] The Essay Master Assist according to the embodiment includes a grammar analysis unit, a punctuation analysis unit, a spelling analysis unit, a sentence coherence analysis unit, a clarity analysis unit, a style analysis unit, a summary generation unit, and a scoring criteria setting unit. The grammar analysis unit comprehensively analyzes the grammar of an essay using a generative AI. For example, the grammar analysis unit detects grammatical errors and suggests corrections. The grammar analysis unit can also provide detailed explanations of the causes of grammatical errors and specific advice on how to correct them. The grammar analysis unit can also analyze the frequency and patterns of grammatical errors to identify individual student weaknesses and propose personalized study plans. The punctuation analysis unit comprehensively analyzes the punctuation of an essay using a generative AI. For example, the punctuation analysis unit detects punctuation errors and suggests corrections. The punctuation analysis unit can also provide detailed explanations of the causes of punctuation errors and specific advice on how to correct them. The punctuation analysis module analyzes the frequency and patterns of punctuation errors to identify individual students' weaknesses and propose personalized learning plans. The spelling analysis module uses generative AI to comprehensively analyze the spelling of an essay. For example, the spelling analysis module can detect spelling errors and suggest corrections. The spelling analysis module can also provide detailed explanations of the causes of spelling errors and specific advice on how to correct them. The spelling analysis module can also analyze the frequency and patterns of spelling errors to identify individual students' weaknesses and propose personalized learning plans. The writing coherence analysis module uses generative AI to comprehensively analyze the coherence of an essay's writing. For example, the writing coherence analysis module analyzes whether each paragraph is logically connected and suggests areas for improvement. The writing coherence analysis module can also compare an essay with other excellent essays and provide specific examples to suggest areas for improvement. The writing coherence analysis module can also use sentiment estimation to analyze the emotional impact that feedback on writing coherence has on students and emphasize positive feedback. The clarity analysis module uses generative AI to comprehensively analyze the clarity of an essay. For example, the clarity analysis module analyzes whether the argument is clearly communicated and suggests areas for improvement.The clarity analysis unit can also compare an essay with other excellent essays and suggest areas for improvement by providing specific examples. The clarity analysis unit can also use an emotion estimation function to analyze the emotional impact of clarity feedback on students and highlight positive feedback. The style analysis unit uses generative AI to comprehensively analyze the style of an essay. For example, the style analysis unit can analyze whether the writing style is appropriate and suggest areas for improvement. The style analysis unit can also compare an essay with other excellent essays and suggest areas for improvement by providing specific examples. The style analysis unit can also use an emotion estimation function to analyze the emotional impact of style feedback on students and highlight positive feedback. The summary generation unit uses generative AI to generate summaries that allow students to quickly grasp the core content of an essay. For example, the summary generation unit provides a concise summary of the essay's main points and conclusions. The summary generation unit can also highlight important keywords and phrases when generating summaries to help students understand them. The summary generation unit can also use an emotion estimation function to analyze students' emotional reactions to the summary and suggest summary generation methods that elicit positive emotions. The grading criteria setting unit uses generative AI to evaluate essays based on customizable grading criteria set by the teacher. For example, the grading criteria setting unit sets grading criteria that focus on specific evaluation items (e.g., grammar, content, coherence) and grades essays based on those criteria. The grading criteria setting unit can also compare essays with other excellent essays and provide specific examples to improve the transparency of evaluation. The grading criteria setting unit can also use emotion estimation to analyze students' emotional responses to the grading criteria and suggest grading criteria setting methods that elicit positive emotions. This reduces the burden of essay grading and provides valuable feedback for both teachers and students. For example, teachers can reduce the time it takes to grade essays, and students can receive specific feedback to improve their learning effectiveness.

[0030] The grammar analysis unit can detect grammatical errors, explain the cause of the error in detail, and provide specific advice on how to correct it. For example, when the generative AI detects a grammatical error, the grammar analysis unit explains the cause of the error in detail and provides specific advice on how to correct it. For example, it points out errors in subject-verb agreement and shows the correct grammatical structure. Furthermore, when the grammar analysis unit detects an error in punctuation usage, it explains the cause of the error and provides specific advice on how to use punctuation appropriately. For example, it points out errors in comma usage and shows the correct usage. Furthermore, when the grammar analysis unit detects a spelling error, it explains the cause of the error and provides specific advice on how to correct it. For example, it points out errors in homonyms and shows the correct usage of the word. This improves students' learning effectiveness by providing detailed explanations of grammatical errors and specific correction suggestions.

[0031] The punctuation analysis unit can detect punctuation errors, explain the cause of the error in detail, and provide specific advice on how to correct it. For example, when the generation AI detects a punctuation error, the punctuation analysis unit explains the cause of the error in detail and provides specific advice on how to correct it. For example, it points out errors in comma usage and shows the correct usage. Furthermore, when the punctuation analysis unit detects a grammatical error, it explains the cause of the error in detail and provides specific advice on how to correct it. For example, it points out errors in subject-verb agreement and shows the correct grammatical structure. Furthermore, when the punctuation analysis unit detects a spelling error, it explains the cause of the error and provides specific advice on how to correct it. For example, it points out errors in homonyms and shows the correct usage of the word. This improves students' learning effectiveness by providing detailed explanations of punctuation errors and specific correction suggestions.

[0032] The spelling analyzer can detect spelling errors, explain the cause of the error in detail, and provide specific advice on how to correct it. For example, when the generation AI detects a spelling error, the spelling analyzer will explain the cause of the error in detail and provide specific advice on how to correct it. For example, it will point out homonym errors and show the correct word usage. Furthermore, when the spelling analyzer detects a grammatical error, it will explain the cause of the error in detail and provide specific advice on how to correct it. For example, it will point out errors in subject-verb agreement and show the correct grammatical structure. Furthermore, when the spelling analyzer detects an error in punctuation usage, it will explain the cause of the error and provide specific advice on how to use punctuation appropriately. For example, it will point out errors in comma usage and show the correct usage. This will improve students' learning effectiveness by providing detailed explanations of spelling errors and specific correction suggestions.

[0033] The grammar analysis unit can analyze the frequency and patterns of grammar errors to identify students' weak points and propose personalized study plans. For example, when the generative AI detects grammar errors, the grammar analysis unit analyzes the frequency and patterns of those errors to identify individual students' weak points. For example, for a student who makes many errors regarding a specific grammatical structure, the grammar analysis unit proposes a study plan specialized for that grammatical structure. The grammar analysis unit also analyzes the frequency and patterns of punctuation errors to identify individual students' weak points. For example, for a student who makes many errors regarding the use of commas, the grammar analysis unit proposes a study plan specialized for the use of commas. The grammar analysis unit also analyzes the frequency and patterns of spelling errors to identify individual students' weak points. For example, for a student who makes many errors regarding the spelling of a specific word, the grammar analysis unit proposes a study plan specialized for that word. In this way, students' weak points are identified and personalized study plans are provided, thereby improving learning effectiveness.

[0034] The punctuation analysis unit can analyze the frequency and patterns of punctuation errors to identify students' weak points and propose personalized study plans. For example, when the generative AI detects punctuation errors, the punctuation analysis unit analyzes the frequency and patterns of those errors to identify individual students' weak points. For example, for a student who makes many errors in comma usage, the punctuation analysis unit proposes a study plan specialized for comma usage. The punctuation analysis unit also analyzes the frequency and patterns of grammatical errors to identify individual students' weak points. For example, for a student who makes many errors in a specific grammatical structure, the punctuation analysis unit proposes a study plan specialized for that grammatical structure. The punctuation analysis unit also analyzes the frequency and patterns of spelling errors to identify individual students' weak points. For example, for a student who makes many errors in the spelling of a specific word, the punctuation analysis unit proposes a study plan specialized for that word. In this way, students' weak points are identified and personalized study plans are provided, thereby improving learning effectiveness.

[0035] The spelling analysis unit can analyze the frequency and patterns of spelling errors to identify students' weak points and propose personalized study plans. For example, when the generative AI detects spelling errors, the spelling analysis unit analyzes the frequency and patterns of those errors to identify the weak points of individual students. For example, for a student who makes many spelling errors for a specific word, the spelling analysis unit proposes a study plan specialized for that word. The spelling analysis unit also analyzes the frequency and patterns of grammatical errors to identify the weak points of individual students. For example, for a student who makes many errors regarding a specific grammatical structure, the spelling analysis unit proposes a study plan specialized for that grammatical structure. The spelling analysis unit also analyzes the frequency and patterns of punctuation errors to identify the weak points of individual students. For example, for a student who makes many errors regarding the use of commas, the spelling analysis unit proposes a study plan specialized for the use of commas. In this way, students' weak points are identified and personalized study plans are provided, thereby improving learning effectiveness.

[0036] The grammar analysis unit, punctuation analysis unit, and spelling analysis unit can link the results of grammar, punctuation, and spelling analysis with language learning applications to provide comprehensive language learning support. For example, the grammar analysis unit, punctuation analysis unit, and spelling analysis unit link the results of grammar, punctuation, and spelling errors detected by the generative AI with other language learning applications. For example, after pointing out a grammatical error, practice questions specific to that grammar item are provided. Also, the results of punctuation error detection are linked with other language learning applications. For example, after pointing out an error in comma usage, practice questions specific to that usage are provided. Also, the results of spelling error detection are linked with other language learning applications. For example, after pointing out an error in the spelling of a specific word, practice questions specific to that word are provided. In this way, by linking the results of grammar, punctuation, and spelling analysis with other language learning applications, comprehensive language learning support is provided.

[0037] The grammar analysis unit, punctuation analysis unit, and spelling analysis unit can use generative AI to correct grammar, punctuation, and spelling errors in essays in real time, providing an interactive editor that allows students to learn as they write. For example, the grammar analysis unit, punctuation analysis unit, and spelling analysis unit can provide an interactive editor that uses generative AI to detect grammar, punctuation, and spelling errors in real time and suggest corrections. For example, the system can point out errors while a student is writing an essay and immediately display correction suggestions. Another example is an interactive editor that detects grammar errors in real time and suggests corrections. For example, the system can point out errors in subject-verb agreement and display the correct grammatical structure. Another example is an interactive editor that detects punctuation errors in real time and suggests corrections. For example, the system can point out errors in comma usage and display the correct usage. This provides an interactive editor that corrects grammar, punctuation, and spelling errors in real time, allowing students to learn as they write.

[0038] The text coherence analysis unit and clarity analysis unit can suggest specific areas for improvement and provide detailed instructions on how to revise a text when evaluating the coherence and clarity of the text. For example, when the generation AI evaluates the coherence of a text, the text coherence analysis unit and clarity analysis unit suggest specific areas for improvement and provide detailed instructions on how to revise the text. For example, they can provide specific advice on strengthening the logical connections between paragraphs. Furthermore, when evaluating the clarity of a text, they suggest specific areas for improvement and provide detailed instructions on how to revise the text. For example, they can provide specific advice on clarifying arguments. Furthermore, when the generation AI evaluates the coherence and clarity of a text, they suggest specific areas for improvement and provide detailed instructions on how to revise the text. For example, they can provide specific advice on removing redundant expressions and making the text more concise. In this way, the text coherence and clarity can be evaluated and specific areas for improvement and corrections can be provided to improve students' writing skills.

[0039] The text coherence analysis unit can compare a text with other excellent essays and provide specific examples to suggest areas for improvement. For example, when the generation AI evaluates the coherence of a text, it compares it with other excellent essays and provides specific examples to suggest areas for improvement. For example, it may use an essay with a logical paragraph structure as an example to suggest areas for improvement. Also, when evaluating the clarity of a text, it compares it with other excellent essays and provides specific examples to suggest areas for improvement. For example, it may use an essay with a clear argument as an example to suggest areas for improvement. Also, when the generation AI evaluates the coherence and clarity of a text, it compares it with other excellent essays and provides specific examples to suggest areas for improvement. For example, it may use an essay with concise and clear expression as an example to suggest areas for improvement. In this way, by comparing it with other excellent essays and providing specific examples to suggest areas for improvement, students' writing skills can be improved.

[0040] The text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of text, but can also be applied to academic texts to help improve overall writing skills. For example, the text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of essays, but can also be applied to academic papers and reports to help improve overall writing skills. For example, they evaluate the logical structure of a paper and suggest areas for improvement. Furthermore, the text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of essays, but can also be applied to academic reports to help improve overall writing skills. For example, they evaluate the clarity of a report's arguments and suggest areas for improvement. Furthermore, the text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of essays, but can also be applied to other academic texts to help improve overall writing skills. For example, they provide advice on removing redundant expressions from academic papers and making them more concise. This not only evaluates the coherence and clarity of text, but can also be applied to other academic texts to help improve overall writing skills.

[0041] The text coherence analysis unit and clarity analysis unit can generate visual aids to aid visual understanding when evaluating the coherence and clarity of text. For example, the text coherence analysis unit and clarity analysis unit generate visual aids to facilitate visual understanding when a generation AI evaluates the coherence and clarity of text. For example, they generate a flowchart showing the logical connections between paragraphs. Also, when evaluating the clarity of text, they generate visual aids to facilitate visual understanding. For example, they generate a mind map showing the flow of arguments. Also, when a generation AI evaluates the coherence and clarity of text, they generate visual aids to facilitate visual understanding. For example, they generate a flowchart showing specific advice for deleting redundant expressions. In this way, they generate visual aids to facilitate visual understanding when evaluating the coherence and clarity of text.

[0042] When evaluating the style of an essay, the style analysis unit can provide specific advice for improving the style and show how to enrich the expression. For example, when a generative AI evaluates the style of an essay, the style analysis unit provides specific advice for improving the style and shows how to enrich the expression. For example, it provides specific advice for increasing stylistic variation. Furthermore, when evaluating the style, it indicates specific areas for improvement and explains in detail how to enrich the expression. For example, it provides specific advice for using metaphors and rhetorical techniques. Furthermore, when a generative AI evaluates the style of an essay, it provides specific advice for improving the style and shows how to enrich the expression. For example, it provides specific advice for improving the rhythm and flow of sentences. In this way, the style of an essay is evaluated and specific advice for improving the style is provided to enrich the expression.

[0043] The style analysis unit can compare the essay with other excellent essays and provide specific examples to suggest areas for style improvement. For example, when the generative AI evaluates the style of an essay, it compares it with other excellent essays and provides specific examples to suggest areas for style improvement. For example, it may use examples of essays with stylistic variation to suggest areas for improvement. In addition, when evaluating style, it compares it with other excellent essays and provides specific examples to suggest areas for style improvement. For example, it may use examples of essays that use metaphors and rhetorical devices to suggest areas for improvement. In addition, when the generative AI evaluates the style of an essay, it compares it with other excellent essays and provides specific examples to suggest areas for style improvement. For example, it may use examples of essays with good sentence rhythm and flow to suggest areas for improvement. In this way, by comparing it with other excellent essays and providing specific examples to suggest areas for style improvement, it enriches the expression.

[0044] The style analysis unit not only evaluates the style of an essay, but can also be applied to other documents, helping to improve overall writing skills. For example, the style analysis unit not only evaluates the style of an essay, but also applies it to business documents, helping to improve overall writing skills. For example, it evaluates the writing style of a business letter and suggests areas for improvement. Furthermore, the generative AI not only evaluates the style of an essay, but also applies it to creative writing, helping to improve overall writing skills. For example, it evaluates the writing style of a short story and suggests areas for improvement. Furthermore, the generative AI not only evaluates the style of an essay, but also applies it to other documents, helping to improve overall writing skills. For example, it evaluates the writing style of a report and suggests areas for improvement. In this way, not only evaluates the style of an essay, but also applies it to other documents, helping to improve overall writing skills.

[0045] The style analysis unit can generate visual aids to aid visual understanding when evaluating the style of an essay. For example, the style analysis unit generates visual aids to facilitate visual understanding when the generative AI evaluates the style of an essay. For example, it generates a style guide that shows variations in writing style. Also, when evaluating the style, it generates visual aids to facilitate visual understanding. For example, it generates templates that show metaphors and rhetorical techniques. Also, when the generative AI evaluates the style of an essay, it generates visual aids to facilitate visual understanding. For example, it generates a style guide that shows the rhythm and flow of sentences. In this way, it generates visual aids to facilitate visual understanding when evaluating the style of an essay.

[0046] The summary generation unit can highlight important keywords and phrases when generating a summary of an essay, to help understand the summary. For example, when the generation AI generates a summary of an essay, the summary generation unit highlights important keywords and phrases to help understand the summary. For example, it highlights main points in bold or color. Also, when generating a summary, it highlights important keywords and phrases to make it easier to understand visually. For example, it highlights keywords. Also, when the generation AI generates a summary of an essay, it highlights important keywords and phrases to help understand the summary. For example, it highlights the conclusion. This allows it to highlight important keywords and phrases when generating a summary of an essay, to help understand the summary.

[0047] When generating a summary, the summary generation unit can indicate the relevance to other related documents and provide background information for the summary. For example, when the generation AI generates a summary of an essay, the summary generation unit indicates the relevance to other related documents and provides background information for the summary. For example, it displays a list of references. When generating a summary, it also indicates the relevance to related papers and literature and provides background information. For example, it cites related research results. When generating a summary of an essay, the generation AI also indicates the relevance to other related documents and provides background information for the summary. For example, it displays related data and statistical information. This allows it to indicate the relevance to other related documents and provide background information for the summary when generating a summary.

[0048] The summary generation unit not only generates summaries for essays, but can also be applied to other documents to support comprehensive information organization. For example, the summary generation unit not only generates summaries for essays, but also generates summaries for reports, supporting comprehensive information organization. For example, it provides a summary that concisely summarizes the main points of a report. It also generates summaries for presentation materials to make them easier to understand visually. For example, it provides a summary that concisely summarizes the main points of slides. It also not only generates summaries for essays, but can also be applied to other documents to support comprehensive information organization. For example, it provides a summary that concisely summarizes the main points of a research paper. This allows it to not only generate summaries for essays, but also apply them to other documents to support comprehensive information organization.

[0049] The summary generation unit can generate visual aids to aid visual understanding when generating a summary of an essay. For example, when the generation AI generates a summary of an essay, the summary generation unit generates visual aids to make it easier to understand visually. For example, it generates graphs and charts that show the main points. Also, when generating a summary, it generates visual aids to make it easier to understand visually. For example, it generates graphs to visualize data. Also, when the generation AI generates a summary of an essay, it generates visual aids to make it easier to understand visually. For example, it generates a chart to highlight the conclusion. In this way, when generating a summary of an essay, it generates visual aids to make it easier to understand visually.

[0050] The scoring criteria setting unit can explain specific evaluation reasons in detail when evaluating an essay based on customizable scoring criteria set by a teacher. For example, the scoring criteria setting unit explains specific evaluation reasons in detail when the generation AI evaluates ... reasons for evaluating grammar in detail. Furthermore, when evaluating an essay based on the scoring criteria, the scoring criteria setting unit explains specific evaluation reasons in detail. For example, the scoring criteria setting unit explains reasons for evaluating content in detail. Furthermore, when the generation AI evaluates an essay based on customizable scoring criteria set by a teacher, the scoring criteria setting unit explains specific evaluation reasons in detail. For example, the scoring criteria setting unit explains reasons for evaluating coherence in detail. Thus, when evaluating an essay based on customizable scoring criteria set by a teacher, the scoring criteria setting unit explains specific evaluation reasons in detail.

[0051] The scoring criteria setting unit can improve the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, when the generation AI applies the scoring criteria, the scoring criteria setting unit improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, it indicates evaluation criteria for grammar. Also, when applying the scoring criteria, it improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, it indicates evaluation criteria for content. Also, when the generation AI applies the scoring criteria, it improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, it indicates evaluation criteria for coherence. This improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples.

[0052] The scoring criteria setting unit can not only customize the scoring criteria for essays, but also apply them to other evaluation criteria to provide comprehensive evaluation support. For example, the scoring criteria setting unit not only allows the generation AI to customize the scoring criteria for essays, but also applies them to the evaluation criteria for presentations, thereby providing comprehensive evaluation support. For example, it evaluates the structure and content of presentations. It can also customize project evaluation criteria to provide comprehensive evaluation support. For example, it evaluates the progress and results of a project. It can also not only customize the scoring criteria for essays, but also apply them to other evaluation criteria to provide comprehensive evaluation support. For example, it sets evaluation criteria for group discussions. This allows it to not only customize the scoring criteria for essays, but also apply them to other evaluation criteria to provide comprehensive evaluation support.

[0053] The scoring criteria setting unit can generate visual aids to assist visual understanding when customizing the scoring criteria for an essay. For example, the scoring criteria setting unit generates visual aids to facilitate visual understanding when the generation AI customizes the scoring criteria for an essay. For example, it generates an evaluation rubric. Also, when customizing the scoring criteria, it generates visual aids to facilitate visual understanding. For example, it generates a checklist. Also, when customizing the scoring criteria for an essay, it generates visual aids to facilitate visual understanding. For example, it generates a graph showing the evaluation criteria. In this way, it generates visual aids to facilitate visual understanding when customizing the scoring criteria for an essay.

[0054] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0055] The Essay Master Assist can further include a voice input unit. The voice input unit allows users to input essays by voice, and the generative AI converts the speech into text. For example, what the user speaks can be converted into text in real time to assist in essay creation. The voice input unit can also use voice recognition technology to analyze the user's pronunciation and intonation and suggest areas for improvement. The voice input unit can also allow the user to confirm the content of the essay by voice and provide voice feedback. This makes essay creation more interactive and efficient.

[0056] Essay Master Assist can also include a translation unit. The translation unit provides the function of translating essays into other languages. For example, an essay written in English can be translated into Japanese, and vice versa. The translation unit can also take context into account to improve translation accuracy. Furthermore, the translation unit can provide feedback on the translation results and evaluate the quality of the translation. This makes essays multilingual and promotes international communication.

[0057] Essay Master Assist can also include a citation manager, which provides functionality for managing citations and references used in an essay. For example, the citation manager can automatically format citations and follow the appropriate citation style (APA, MLA, etc.). The citation manager can also list all citations used in an essay and detect duplicate or incorrect citations. Furthermore, the citation manager can automatically generate a reference list and add it to the end of the essay. This makes citation management easier and improves the reliability of the essay.

[0058] Essay Master Assist can also include a collaboration section, which allows multiple users to edit essays simultaneously. For example, teachers and students can collaborate on essays in real time and instantly reflect feedback. The collaboration section can also save the editing history and track who edited which part. Furthermore, the collaboration section provides a comment function, allowing users to add comments to specific parts of the essay. This allows for efficient collaboration on essays.

[0059] Essay Master Assist can also be equipped with a plug-in section. The plug-in section provides plug-ins for integration with other educational tools and applications. For example, it can integrate with online dictionaries and thesauruses to allow users to easily search for word meanings and synonyms when writing essays. The plug-in section can also integrate with learning management systems (LMS) to centrally manage essay submissions and evaluations. Furthermore, the plug-in section can integrate with other AI tools to perform more advanced analysis of essay content. This expands the functionality of Essay Master Assist and improves user convenience.

[0060] The processing flow of the first embodiment will be briefly explained below.

[0061] Step 1: The grammar analysis module uses generative AI to comprehensively analyze the essay's grammar. It detects grammatical errors and suggests corrections. It also provides detailed explanations of the causes of the errors and offers specific advice on how to correct them. It also analyzes the frequency and patterns of errors to identify individual student weaknesses and propose a personalized learning plan. Step 2: The punctuation analysis unit uses generative AI to comprehensively analyze the essay's punctuation. It detects punctuation errors and suggests corrections. It also provides detailed explanations of the causes of the errors and offers specific advice on how to correct them. It also analyzes the frequency and patterns of errors to identify individual students' weaknesses and proposes a personalized learning plan. Step 3: The spelling analysis module uses generative AI to comprehensively analyze the spelling of the essay. It detects spelling errors and suggests corrections. It also provides detailed explanations of the causes of the errors and offers specific advice on how to correct them. It also analyzes the frequency and patterns of errors to identify individual student weaknesses and propose a personalized learning plan. Step 4: The text coherence analysis unit uses generative AI to comprehensively analyze the coherence of the essay's text. It analyzes whether each paragraph is logically connected and suggests areas for improvement. It also compares the essay with other excellent essays and provides specific examples to suggest areas for improvement. Furthermore, it uses sentiment estimation to analyze the emotional impact of feedback on students and highlight positive feedback. Step 5: The Clarity Analysis module uses generative AI to comprehensively analyze the clarity of the essay. It analyzes whether the argument is clearly conveyed and suggests areas for improvement. It also compares the essay with other excellent essays and provides specific examples to suggest areas for improvement. Furthermore, it uses sentiment estimation to analyze the emotional impact of feedback on students and highlights positive feedback. Step 6: The style analysis module uses generative AI to comprehensively analyze the essay's style. It analyzes whether the writing style is appropriate and suggests areas for improvement. It also compares the essay with other excellent essays and provides specific examples to suggest areas for style improvement. Furthermore, it uses an emotion estimation function to analyze the emotional impact of feedback on students and highlight positive feedback. Step 7: The summary generator uses AI to generate a summary that quickly captures the core content of the essay. It provides a concise summary of the main points and conclusions, highlighting important keywords and phrases. Furthermore, it uses emotion estimation to analyze students' emotional reactions to the summary and proposes a summary generation method that elicits positive emotions. Step 8: The scoring criteria setting unit uses generative AI to evaluate the essay based on customizable scoring criteria set by the teacher. The scoring criteria are set with emphasis on specific evaluation items (grammar, content, coherence, etc.), and the essay is scored based on these criteria. The scoring criteria are also compared with other excellent essays, providing specific examples. Furthermore, the emotion estimation function is used to analyze students' emotional responses to the scoring criteria and propose a scoring criteria setting method to elicit positive emotions.

[0062] (Example 2) Essay Master Assist, an embodiment of the present invention, is a system that uses generative AI to comprehensively analyze essays' grammar, punctuation, spelling, consistency, clarity, and style, generate summaries that allow students to quickly grasp the core content of the essay, and set customizable grading criteria. This reduces the burden of grading essays and provides valuable feedback for both teachers and students.

[0063] The Essay Master Assist according to the embodiment includes a grammar analysis unit, a punctuation analysis unit, a spelling analysis unit, a sentence coherence analysis unit, a clarity analysis unit, a style analysis unit, a summary generation unit, and a scoring criteria setting unit. The grammar analysis unit comprehensively analyzes the grammar of an essay using a generative AI. For example, the grammar analysis unit detects grammatical errors and suggests corrections. The grammar analysis unit can also provide detailed explanations of the causes of grammatical errors and specific advice on how to correct them. The grammar analysis unit can also analyze the frequency and patterns of grammatical errors to identify individual student weaknesses and propose personalized study plans. The punctuation analysis unit comprehensively analyzes the punctuation of an essay using a generative AI. For example, the punctuation analysis unit detects punctuation errors and suggests corrections. The punctuation analysis unit can also provide detailed explanations of the causes of punctuation errors and specific advice on how to correct them. The punctuation analysis module analyzes the frequency and patterns of punctuation errors to identify individual students' weaknesses and propose personalized learning plans. The spelling analysis module uses generative AI to comprehensively analyze the spelling of an essay. For example, the spelling analysis module can detect spelling errors and suggest corrections. The spelling analysis module can also provide detailed explanations of the causes of spelling errors and specific advice on how to correct them. The spelling analysis module can also analyze the frequency and patterns of spelling errors to identify individual students' weaknesses and propose personalized learning plans. The writing coherence analysis module uses generative AI to comprehensively analyze the coherence of an essay's writing. For example, the writing coherence analysis module analyzes whether each paragraph is logically connected and suggests areas for improvement. The writing coherence analysis module can also compare an essay with other excellent essays and provide specific examples to suggest areas for improvement. The writing coherence analysis module can also use sentiment estimation to analyze the emotional impact that feedback on writing coherence has on students and emphasize positive feedback. The clarity analysis module uses generative AI to comprehensively analyze the clarity of an essay. For example, the clarity analysis module analyzes whether the argument is clearly communicated and suggests areas for improvement.The clarity analysis unit can also compare an essay with other excellent essays and suggest areas for improvement by providing specific examples. The clarity analysis unit can also use an emotion estimation function to analyze the emotional impact of clarity feedback on students and highlight positive feedback. The style analysis unit uses generative AI to comprehensively analyze the style of an essay. For example, the style analysis unit can analyze whether the writing style is appropriate and suggest areas for improvement. The style analysis unit can also compare an essay with other excellent essays and suggest areas for improvement by providing specific examples. The style analysis unit can also use an emotion estimation function to analyze the emotional impact of style feedback on students and highlight positive feedback. The summary generation unit uses generative AI to generate summaries that allow students to quickly grasp the core content of an essay. For example, the summary generation unit provides a concise summary of the essay's main points and conclusions. The summary generation unit can also highlight important keywords and phrases when generating summaries to help students understand them. The summary generation unit can also use an emotion estimation function to analyze students' emotional reactions to the summary and suggest summary generation methods that elicit positive emotions. The grading criteria setting unit uses generative AI to evaluate essays based on customizable grading criteria set by the teacher. For example, the grading criteria setting unit sets grading criteria that focus on specific evaluation items (e.g., grammar, content, coherence) and grades essays based on those criteria. The grading criteria setting unit can also compare essays with other excellent essays and provide specific examples to improve the transparency of evaluation. The grading criteria setting unit can also use emotion estimation to analyze students' emotional responses to the grading criteria and suggest grading criteria setting methods that elicit positive emotions. This reduces the burden of essay grading and provides valuable feedback for both teachers and students. For example, teachers can reduce the time it takes to grade essays, and students can receive specific feedback to improve their learning effectiveness.

[0064] The grammar analysis unit can detect grammatical errors, explain the cause of the error in detail, and provide specific advice on how to correct it. For example, when the generative AI detects a grammatical error, the grammar analysis unit explains the cause of the error in detail and provides specific advice on how to correct it. For example, it points out errors in subject-verb agreement and shows the correct grammatical structure. Furthermore, when the grammar analysis unit detects an error in punctuation usage, it explains the cause of the error and provides specific advice on how to use punctuation appropriately. For example, it points out errors in comma usage and shows the correct usage. Furthermore, when the grammar analysis unit detects a spelling error, it explains the cause of the error and provides specific advice on how to correct it. For example, it points out errors in homonyms and shows the correct usage of the word. This improves students' learning effectiveness by providing detailed explanations of grammatical errors and specific correction suggestions.

[0065] The punctuation analysis unit can detect punctuation errors, explain the cause of the error in detail, and provide specific advice on how to correct it. For example, when the generation AI detects a punctuation error, the punctuation analysis unit explains the cause of the error in detail and provides specific advice on how to correct it. For example, it points out errors in comma usage and shows the correct usage. Furthermore, when the punctuation analysis unit detects a grammatical error, it explains the cause of the error in detail and provides specific advice on how to correct it. For example, it points out errors in subject-verb agreement and shows the correct grammatical structure. Furthermore, when the punctuation analysis unit detects a spelling error, it explains the cause of the error and provides specific advice on how to correct it. For example, it points out errors in homonyms and shows the correct usage of the word. This improves students' learning effectiveness by providing detailed explanations of punctuation errors and specific correction suggestions.

[0066] The spelling analyzer can detect spelling errors, explain the cause of the error in detail, and provide specific advice on how to correct it. For example, when the generation AI detects a spelling error, the spelling analyzer will explain the cause of the error in detail and provide specific advice on how to correct it. For example, it will point out homonym errors and show the correct word usage. Furthermore, when the spelling analyzer detects a grammatical error, it will explain the cause of the error in detail and provide specific advice on how to correct it. For example, it will point out errors in subject-verb agreement and show the correct grammatical structure. Furthermore, when the spelling analyzer detects an error in punctuation usage, it will explain the cause of the error and provide specific advice on how to use punctuation appropriately. For example, it will point out errors in comma usage and show the correct usage. This will improve students' learning effectiveness by providing detailed explanations of spelling errors and specific correction suggestions.

[0067] The grammar analysis unit can analyze the frequency and patterns of grammar errors to identify students' weak points and propose personalized study plans. For example, when the generative AI detects grammar errors, the grammar analysis unit analyzes the frequency and patterns of those errors to identify individual students' weak points. For example, for a student who makes many errors regarding a specific grammatical structure, the grammar analysis unit proposes a study plan specialized for that grammatical structure. The grammar analysis unit also analyzes the frequency and patterns of punctuation errors to identify individual students' weak points. For example, for a student who makes many errors regarding the use of commas, the grammar analysis unit proposes a study plan specialized for the use of commas. The grammar analysis unit also analyzes the frequency and patterns of spelling errors to identify individual students' weak points. For example, for a student who makes many errors regarding the spelling of a specific word, the grammar analysis unit proposes a study plan specialized for that word. In this way, students' weak points are identified and personalized study plans are provided, thereby improving learning effectiveness.

[0068] The punctuation analysis unit can analyze the frequency and patterns of punctuation errors to identify students' weak points and propose personalized study plans. For example, when the generative AI detects punctuation errors, the punctuation analysis unit analyzes the frequency and patterns of those errors to identify individual students' weak points. For example, for a student who makes many errors in comma usage, the punctuation analysis unit proposes a study plan specialized for comma usage. The punctuation analysis unit also analyzes the frequency and patterns of grammatical errors to identify individual students' weak points. For example, for a student who makes many errors in a specific grammatical structure, the punctuation analysis unit proposes a study plan specialized for that grammatical structure. The punctuation analysis unit also analyzes the frequency and patterns of spelling errors to identify individual students' weak points. For example, for a student who makes many errors in the spelling of a specific word, the punctuation analysis unit proposes a study plan specialized for that word. In this way, students' weak points are identified and personalized study plans are provided, thereby improving learning effectiveness.

[0069] The spelling analysis unit can analyze the frequency and patterns of spelling errors to identify students' weak points and propose personalized study plans. For example, when the generative AI detects spelling errors, the spelling analysis unit analyzes the frequency and patterns of those errors to identify the weak points of individual students. For example, for a student who makes many spelling errors for a specific word, the spelling analysis unit proposes a study plan specialized for that word. The spelling analysis unit also analyzes the frequency and patterns of grammatical errors to identify the weak points of individual students. For example, for a student who makes many errors regarding a specific grammatical structure, the spelling analysis unit proposes a study plan specialized for that grammatical structure. The spelling analysis unit also analyzes the frequency and patterns of punctuation errors to identify the weak points of individual students. For example, for a student who makes many errors regarding the use of commas, the spelling analysis unit proposes a study plan specialized for the use of commas. In this way, students' weak points are identified and personalized study plans are provided, thereby improving learning effectiveness.

[0070] The grammar analysis unit uses the emotion estimation function to take into account the student's emotions when pointing out grammatical errors and provide positive feedback to maintain motivation. For example, when the generative AI points out a grammatical error, the grammar analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback. For example, by adding words of encouragement when pointing out the error. Furthermore, when pointing out a punctuation error, the grammar analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback to maintain motivation. For example, by adding words of praise when pointing out the error. Furthermore, when pointing out a spelling error, the grammar analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback. For example, by adding an encouraging message when pointing out the error. In this way, by taking into account the student's emotions and providing positive feedback, students' motivation to learn is increased.

[0071] The punctuation analysis unit uses the emotion estimation function to take into account the student's emotions when pointing out punctuation errors and provide positive feedback to maintain motivation. For example, when the generation AI points out a punctuation error, the punctuation analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback. For example, by adding words of encouragement when pointing out the error. Furthermore, when pointing out a grammatical error, the punctuation analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback to maintain motivation. For example, by adding words of praise when pointing out the error. Furthermore, when pointing out a spelling error, the punctuation analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback. For example, by adding an encouraging message when pointing out the error. In this way, by taking into account the student's emotions and providing positive feedback, the student's motivation to learn is increased.

[0072] The spelling analysis unit uses the emotion estimation function to take into account the student's emotions when pointing out spelling errors and provide positive feedback to maintain motivation. For example, when the generation AI points out a spelling error, the spelling analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback. For example, by adding words of encouragement when pointing out the error. Furthermore, when pointing out a grammatical error, the spelling analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback to maintain motivation. For example, by adding words of praise when pointing out the error. Furthermore, when pointing out a punctuation error, the spelling analysis unit uses the emotion estimation function to analyze the student's emotions and provide positive feedback. For example, by adding an encouraging message when pointing out the error. In this way, taking into account the student's emotions and providing positive feedback increases their motivation to learn.

[0073] The grammar analysis unit, punctuation analysis unit, and spelling analysis unit can link the results of grammar, punctuation, and spelling analysis with language learning applications to provide comprehensive language learning support. For example, the grammar analysis unit, punctuation analysis unit, and spelling analysis unit link the results of grammar, punctuation, and spelling errors detected by the generative AI with other language learning applications. For example, after pointing out a grammatical error, practice questions specific to that grammar item are provided. Also, the results of punctuation error detection are linked with other language learning applications. For example, after pointing out an error in comma usage, practice questions specific to that usage are provided. Also, the results of spelling error detection are linked with other language learning applications. For example, after pointing out an error in the spelling of a specific word, practice questions specific to that word are provided. In this way, by linking the results of grammar, punctuation, and spelling analysis with other language learning applications, comprehensive language learning support is provided.

[0074] The grammar analysis unit, punctuation analysis unit, and spelling analysis unit can use generative AI to correct grammar, punctuation, and spelling errors in essays in real time, providing an interactive editor that allows students to learn as they write. For example, the grammar analysis unit, punctuation analysis unit, and spelling analysis unit can provide an interactive editor that uses generative AI to detect grammar, punctuation, and spelling errors in real time and suggest corrections. For example, the system can point out errors while a student is writing an essay and immediately display correction suggestions. Another example is an interactive editor that detects grammar errors in real time and suggests corrections. For example, the system can point out errors in subject-verb agreement and display the correct grammatical structure. Another example is an interactive editor that detects punctuation errors in real time and suggests corrections. For example, the system can point out errors in comma usage and display the correct usage. This provides an interactive editor that corrects grammar, punctuation, and spelling errors in real time, allowing students to learn as they write.

[0075] The grammar analysis unit can use the emotion estimation function to monitor a student's emotions in real time while they are writing an essay and provide advice to reduce stress. For example, the grammar analysis unit uses the emotion estimation function to monitor a student's emotions in real time while they are writing an essay and provide advice to reduce stress. For example, it makes suggestions to relax when stress increases. It also monitors a student's emotions in real time and provides advice to bring out positive emotions. For example, it displays encouraging messages according to the progress of the essay. It also uses the emotion estimation function to monitor a student's emotions and provide advice to reduce negative emotions. For example, it provides specific advice when a student reaches a difficult part of the essay. In this way, it monitors a student's emotions in real time while they are writing an essay and provides advice to reduce stress.

[0076] The text coherence analysis unit and clarity analysis unit can suggest specific areas for improvement and provide detailed instructions on how to revise a text when evaluating the coherence and clarity of the text. For example, when the generation AI evaluates the coherence of a text, the text coherence analysis unit and clarity analysis unit suggest specific areas for improvement and provide detailed instructions on how to revise the text. For example, they can provide specific advice on strengthening the logical connections between paragraphs. Furthermore, when evaluating the clarity of a text, they suggest specific areas for improvement and provide detailed instructions on how to revise the text. For example, they can provide specific advice on clarifying arguments. Furthermore, when the generation AI evaluates the coherence and clarity of a text, they suggest specific areas for improvement and provide detailed instructions on how to revise the text. For example, they can provide specific advice on removing redundant expressions and making the text more concise. In this way, the text coherence and clarity can be evaluated and specific areas for improvement and corrections can be provided to improve students' writing skills.

[0077] The text coherence analysis unit can compare a text with other excellent essays and provide specific examples to suggest areas for improvement. For example, when the generation AI evaluates the coherence of a text, it compares it with other excellent essays and provides specific examples to suggest areas for improvement. For example, it may use an essay with a logical paragraph structure as an example to suggest areas for improvement. Also, when evaluating the clarity of a text, it compares it with other excellent essays and provides specific examples to suggest areas for improvement. For example, it may use an essay with a clear argument as an example to suggest areas for improvement. Also, when the generation AI evaluates the coherence and clarity of a text, it compares it with other excellent essays and provides specific examples to suggest areas for improvement. For example, it may use an essay with concise and clear expression as an example to suggest areas for improvement. In this way, by comparing it with other excellent essays and providing specific examples to suggest areas for improvement, students' writing skills can be improved.

[0078] The text coherence analysis unit and the clarity analysis unit can use the emotion estimation function to analyze the emotional impact that feedback on the coherence and clarity of text has on students and emphasize positive feedback. For example, the text coherence analysis unit and the clarity analysis unit use the emotion estimation function to analyze the emotional impact that feedback on the coherence of text has on students and emphasize positive feedback. For example, they may add words of encouragement when pointing out areas for improvement. They also analyze the emotional impact that feedback on the clarity of text has on students and emphasize positive feedback. For example, they may add words of praise when providing advice on how to clarify an argument. They also use the emotion estimation function to analyze the emotional impact that feedback on the coherence and clarity of text has on students and emphasize positive feedback. For example, they may add an encouraging message when providing advice on how to remove redundant expressions. In this way, they analyze the emotional impact that feedback on the coherence and clarity of text has on students and emphasize positive feedback, thereby increasing their motivation to learn.

[0079] The text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of text, but can also be applied to academic texts to help improve overall writing skills. For example, the text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of essays, but can also be applied to academic papers and reports to help improve overall writing skills. For example, they evaluate the logical structure of a paper and suggest areas for improvement. Furthermore, the text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of essays, but can also be applied to academic reports to help improve overall writing skills. For example, they evaluate the clarity of a report's arguments and suggest areas for improvement. Furthermore, the text coherence analysis unit and clarity analysis unit not only evaluate the coherence and clarity of essays, but can also be applied to other academic texts to help improve overall writing skills. For example, they provide advice on removing redundant expressions from academic papers and making them more concise. This not only evaluates the coherence and clarity of text, but can also be applied to other academic texts to help improve overall writing skills.

[0080] The text coherence analysis unit and clarity analysis unit can generate visual aids to aid visual understanding when evaluating the coherence and clarity of text. For example, the text coherence analysis unit and clarity analysis unit generate visual aids to facilitate visual understanding when a generation AI evaluates the coherence and clarity of text. For example, they generate a flowchart showing the logical connections between paragraphs. Also, when evaluating the clarity of text, they generate visual aids to facilitate visual understanding. For example, they generate a mind map showing the flow of arguments. Also, when a generation AI evaluates the coherence and clarity of text, they generate visual aids to facilitate visual understanding. For example, they generate a flowchart showing specific advice for deleting redundant expressions. In this way, they generate visual aids to facilitate visual understanding when evaluating the coherence and clarity of text.

[0081] The text coherence analysis unit and the clarity analysis unit use the emotion estimation function to monitor the emotions of students when they receive feedback regarding the coherence and clarity of their writing, thereby improving their acceptability of the feedback. The text coherence analysis unit and the clarity analysis unit, for example, use the emotion estimation function to monitor the emotions of students when they receive feedback regarding the coherence of their writing, thereby improving their acceptability of the feedback. For example, they provide advice to elicit positive emotions when receiving feedback. They also monitor the emotions of students when they receive feedback regarding the clarity of their writing, thereby improving their acceptability of the feedback. For example, they add words of encouragement when providing advice to clarify an argument. They also use the emotion estimation function to monitor the emotions of students when they receive feedback regarding the coherence and clarity of their writing, thereby improving their acceptability of the feedback. For example, they add words of praise when providing advice to remove redundant expressions. In this way, they monitor the emotions of students when they receive feedback regarding the coherence and clarity of their writing, thereby improving their acceptability of the feedback.

[0082] When evaluating the style of an essay, the style analysis unit can provide specific advice for improving the style and show how to enrich the expression. For example, when a generative AI evaluates the style of an essay, the style analysis unit provides specific advice for improving the style and shows how to enrich the expression. For example, it provides specific advice for increasing stylistic variation. Furthermore, when evaluating the style, it indicates specific areas for improvement and explains in detail how to enrich the expression. For example, it provides specific advice for using metaphors and rhetorical techniques. Furthermore, when a generative AI evaluates the style of an essay, it provides specific advice for improving the style and shows how to enrich the expression. For example, it provides specific advice for improving the rhythm and flow of sentences. In this way, the style of an essay is evaluated and specific advice for improving the style is provided to enrich the expression.

[0083] The style analysis unit can compare the essay with other excellent essays and provide specific examples to suggest areas for style improvement. For example, when the generative AI evaluates the style of an essay, it compares it with other excellent essays and provides specific examples to suggest areas for style improvement. For example, it may use examples of essays with stylistic variation to suggest areas for improvement. In addition, when evaluating style, it compares it with other excellent essays and provides specific examples to suggest areas for style improvement. For example, it may use examples of essays that use metaphors and rhetorical devices to suggest areas for improvement. In addition, when the generative AI evaluates the style of an essay, it compares it with other excellent essays and provides specific examples to suggest areas for style improvement. For example, it may use examples of essays with good sentence rhythm and flow to suggest areas for improvement. In this way, by comparing it with other excellent essays and providing specific examples to suggest areas for style improvement, it enriches the expression.

[0084] The style analysis unit can use the emotion estimation function to analyze the emotional impact that style feedback has on students and emphasize positive feedback. For example, the style analysis unit uses the emotion estimation function to analyze the emotional impact that style feedback has on students and emphasize positive feedback. For example, by adding words of encouragement when pointing out areas for style improvement. The style analysis unit also analyzes the emotional impact that style feedback has on students and emphasizes positive feedback. For example, by adding words of praise when providing advice to increase stylistic variation. The emotion estimation function also analyzes the emotional impact that style feedback has on students and emphasizes positive feedback. For example, by adding an encouraging message when providing advice to use metaphors and rhetorical techniques. In this way, the emotional impact that style feedback has on students and emphasising positive feedback can increase their motivation to learn.

[0085] The style analysis unit not only evaluates the style of an essay, but can also be applied to other documents, helping to improve overall writing skills. For example, the style analysis unit not only evaluates the style of an essay, but also applies it to business documents, helping to improve overall writing skills. For example, it evaluates the writing style of a business letter and suggests areas for improvement. Furthermore, the generative AI not only evaluates the style of an essay, but also applies it to creative writing, helping to improve overall writing skills. For example, it evaluates the writing style of a short story and suggests areas for improvement. Furthermore, the generative AI not only evaluates the style of an essay, but also applies it to other documents, helping to improve overall writing skills. For example, it evaluates the writing style of a report and suggests areas for improvement. In this way, not only evaluates the style of an essay, but also applies it to other documents, helping to improve overall writing skills.

[0086] The style analysis unit can generate visual aids to aid visual understanding when evaluating the style of an essay. For example, the style analysis unit generates visual aids to facilitate visual understanding when the generative AI evaluates the style of an essay. For example, it generates a style guide that shows variations in writing style. Also, when evaluating the style, it generates visual aids to facilitate visual understanding. For example, it generates templates that show metaphors and rhetorical techniques. Also, when the generative AI evaluates the style of an essay, it generates visual aids to facilitate visual understanding. For example, it generates a style guide that shows the rhythm and flow of sentences. In this way, it generates visual aids to facilitate visual understanding when evaluating the style of an essay.

[0087] The style analysis unit can use the emotion estimation function to monitor the emotions of students when they receive feedback on their style, thereby improving their acceptability of the feedback. The style analysis unit, for example, uses the emotion estimation function to monitor the emotions of students when they receive feedback on their style, thereby improving their acceptability of the feedback. For example, by adding words of encouragement when pointing out areas for improvement in style. The unit also monitors the emotions of students when they receive feedback on their style, thereby improving their acceptability of the feedback. For example, by adding words of praise when giving advice on increasing stylistic variation. The unit also uses the emotion estimation function to monitor the emotions of students when they receive feedback on their style, thereby improving their acceptability of the feedback. For example, by adding an encouraging message when giving advice on using metaphors and rhetorical techniques. In this way, the unit monitors the emotions of students when they receive feedback on their style, thereby improving their acceptability of the feedback.

[0088] The summary generation unit can highlight important keywords and phrases when generating a summary of an essay, to help understand the summary. For example, when the generation AI generates a summary of an essay, the summary generation unit highlights important keywords and phrases to help understand the summary. For example, it highlights main points in bold or color. Also, when generating a summary, it highlights important keywords and phrases to make it easier to understand visually. For example, it highlights keywords. Also, when the generation AI generates a summary of an essay, it highlights important keywords and phrases to help understand the summary. For example, it highlights the conclusion. This allows it to highlight important keywords and phrases when generating a summary of an essay, to help understand the summary.

[0089] When generating a summary, the summary generation unit can indicate the relevance to other related documents and provide background information for the summary. For example, when the generation AI generates a summary of an essay, the summary generation unit indicates the relevance to other related documents and provides background information for the summary. For example, it displays a list of references. When generating a summary, it also indicates the relevance to related papers and literature and provides background information. For example, it cites related research results. When generating a summary of an essay, the generation AI also indicates the relevance to other related documents and provides background information for the summary. For example, it displays related data and statistical information. This allows it to indicate the relevance to other related documents and provide background information for the summary when generating a summary.

[0090] The summary generation unit can use the emotion estimation function to analyze students' emotional reactions to the summary and propose a summary generation method that elicits positive emotions. The summary generation unit, for example, uses the emotion estimation function to analyze students' emotional reactions to the summary and proposes a summary generation method that elicits positive emotions. For example, by using a lot of positive expressions. The summary generation unit also analyzes students' emotional reactions to the summary and proposes a summary generation method that elicits positive emotions. For example, by emphasizing the conclusion and conveying a positive message. The emotion estimation function also analyzes students' emotional reactions to the summary and proposes a summary generation method that elicits positive emotions. For example, by emphasizing important points and providing positive feedback. In this way, the summary generation unit analyzes students' emotional reactions to the summary and proposes a summary generation method that elicits positive emotions.

[0091] The summary generation unit not only generates summaries for essays, but can also be applied to other documents to support comprehensive information organization. For example, the summary generation unit not only generates summaries for essays, but also generates summaries for reports, supporting comprehensive information organization. For example, it provides a summary that concisely summarizes the main points of a report. It also generates summaries for presentation materials to make them easier to understand visually. For example, it provides a summary that concisely summarizes the main points of slides. It also not only generates summaries for essays, but can also be applied to other documents to support comprehensive information organization. For example, it provides a summary that concisely summarizes the main points of a research paper. This allows it to not only generate summaries for essays, but also apply them to other documents to support comprehensive information organization.

[0092] The summary generation unit can generate visual aids to aid visual understanding when generating a summary of an essay. For example, when the generation AI generates a summary of an essay, the summary generation unit generates visual aids to make it easier to understand visually. For example, it generates graphs and charts that show the main points. Also, when generating a summary, it generates visual aids to make it easier to understand visually. For example, it generates graphs to visualize data. Also, when the generation AI generates a summary of an essay, it generates visual aids to make it easier to understand visually. For example, it generates a chart to highlight the conclusion. In this way, when generating a summary of an essay, it generates visual aids to make it easier to understand visually.

[0093] The summary generation unit can use the emotion estimation function to monitor the emotions of students when they receive a summary, thereby improving the acceptability of the summary. The summary generation unit, for example, uses the emotion estimation function to monitor the emotions of students when they receive a summary, thereby improving the acceptability of the summary. For example, a summary generation method for eliciting positive emotions is proposed. The emotions of students when they receive a summary are also monitored, thereby improving the acceptability of the summary. For example, positive expressions are used frequently. The emotion estimation function is also used to monitor the emotions of students when they receive a summary, thereby improving the acceptability of the summary. For example, important points are emphasized and positive feedback is provided. In this way, the emotions of students when they receive a summary are monitored, thereby improving the acceptability of the summary.

[0094] The scoring criteria setting unit can explain specific evaluation reasons in detail when evaluating an essay based on customizable scoring criteria set by a teacher. For example, the scoring criteria setting unit explains specific evaluation reasons in detail when the generation AI evaluates ... reasons for evaluating grammar in detail. Furthermore, when evaluating an essay based on the scoring criteria, the scoring criteria setting unit explains specific evaluation reasons in detail. For example, the scoring criteria setting unit explains reasons for evaluating content in detail. Furthermore, when the generation AI evaluates an essay based on customizable scoring criteria set by a teacher, the scoring criteria setting unit explains specific evaluation reasons in detail. For example, the scoring criteria setting unit explains reasons for evaluating coherence in detail. Thus, when evaluating an essay based on customizable scoring criteria set by a teacher, the scoring criteria setting unit explains specific evaluation reasons in detail.

[0095] The scoring criteria setting unit can improve the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, when the generation AI applies the scoring criteria, the scoring criteria setting unit improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, it indicates evaluation criteria for grammar. Also, when applying the scoring criteria, it improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, it indicates evaluation criteria for content. Also, when the generation AI applies the scoring criteria, it improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples. For example, it indicates evaluation criteria for coherence. This improves the transparency of the evaluation by comparing with other excellent essays and providing specific examples.

[0096] The grading criteria setting unit can use the emotion estimation function to analyze students' emotional reactions to the grading criteria and propose a grading criteria setting method for eliciting positive emotions. The grading criteria setting unit, for example, uses the emotion estimation function to analyze students' emotional reactions to the grading criteria and propose a grading criteria setting method for eliciting positive emotions. For example, it emphasizes positive feedback. It also analyzes students' emotional reactions to the grading criteria and proposes a grading criteria setting method for eliciting positive emotions. For example, it increases the transparency of evaluation. It also uses the emotion estimation function to analyze students' emotional reactions to the grading criteria and proposes a grading criteria setting method for eliciting positive emotions. For example, it explains specific evaluation reasons in detail. This analyzes students' emotional reactions to the grading criteria and proposes a grading criteria setting method for eliciting positive emotions.

[0097] The scoring criteria setting unit can not only customize the scoring criteria for essays, but also apply them to other evaluation criteria to provide comprehensive evaluation support. For example, the scoring criteria setting unit not only allows the generation AI to customize the scoring criteria for essays, but also applies them to the evaluation criteria for presentations, thereby providing comprehensive evaluation support. For example, it evaluates the structure and content of presentations. It can also customize project evaluation criteria to provide comprehensive evaluation support. For example, it evaluates the progress and results of a project. It can also not only customize the scoring criteria for essays, but also apply them to other evaluation criteria to provide comprehensive evaluation support. For example, it sets evaluation criteria for group discussions. This allows it to not only customize the scoring criteria for essays, but also apply them to other evaluation criteria to provide comprehensive evaluation support.

[0098] The scoring criteria setting unit can generate visual aids to assist visual understanding when customizing the scoring criteria for an essay. For example, the scoring criteria setting unit generates visual aids to facilitate visual understanding when the generation AI customizes the scoring criteria for an essay. For example, it generates an evaluation rubric. Also, when customizing the scoring criteria, it generates visual aids to facilitate visual understanding. For example, it generates a checklist. Also, when customizing the scoring criteria for an essay, it generates visual aids to facilitate visual understanding. For example, it generates a graph showing the evaluation criteria. In this way, it generates visual aids to facilitate visual understanding when customizing the scoring criteria for an essay.

[0099] The grading criteria setting unit can use the emotion estimation function to monitor the emotions of students when they receive an evaluation based on the grading criteria, thereby improving the acceptability of the evaluation. The grading criteria setting unit, for example, uses the emotion estimation function to monitor the emotions of students when they receive an evaluation based on the grading criteria, thereby improving the acceptability of the evaluation. For example, it emphasizes positive feedback. It also monitors the emotions of students when they receive an evaluation based on the grading criteria, thereby improving the acceptability of the evaluation. For example, it explains specific reasons for the evaluation in detail. It also uses the emotion estimation function to monitor the emotions of students when they receive an evaluation based on the grading criteria, thereby improving the acceptability of the evaluation. For example, it increases the transparency of the evaluation. This allows it to monitor the emotions of students when they receive an evaluation based on the grading criteria, thereby improving the acceptability of the evaluation.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The Essay Master Assist can further include a voice input unit. The voice input unit allows users to input essays by voice, and the generative AI converts the speech into text. For example, what the user speaks can be converted into text in real time to assist in essay creation. The voice input unit can also use voice recognition technology to analyze the user's pronunciation and intonation and suggest areas for improvement. The voice input unit can also allow the user to confirm the content of the essay by voice and provide voice feedback. This makes essay creation more interactive and efficient.

[0102] Essay Master Assist can also include a translation unit. The translation unit provides the function of translating essays into other languages. For example, an essay written in English can be translated into Japanese, and vice versa. The translation unit can also take context into account to improve translation accuracy. Furthermore, the translation unit can provide feedback on the translation results and evaluate the quality of the translation. This makes essays multilingual and promotes international communication.

[0103] Essay Master Assist can also include a citation manager, which provides functionality for managing citations and references used in an essay. For example, the citation manager can automatically format citations and follow the appropriate citation style (APA, MLA, etc.). The citation manager can also list all citations used in an essay and detect duplicate or incorrect citations. Furthermore, the citation manager can automatically generate a reference list and add it to the end of the essay. This makes citation management easier and improves the reliability of the essay.

[0104] Essay Master Assist can also include a collaboration section, which allows multiple users to edit essays simultaneously. For example, teachers and students can collaborate on essays in real time and instantly reflect feedback. The collaboration section can also save the editing history and track who edited which part. Furthermore, the collaboration section provides a comment function, allowing users to add comments to specific parts of the essay. This allows for efficient collaboration on essays.

[0105] Essay Master Assist can also be equipped with a plug-in section. The plug-in section provides plug-ins for integration with other educational tools and applications. For example, it can integrate with online dictionaries and thesauruses to allow users to easily search for word meanings and synonyms when writing essays. The plug-in section can also integrate with learning management systems (LMS) to centrally manage essay submissions and evaluations. Furthermore, the plug-in section can integrate with other AI tools to perform more advanced analysis of essay content. This expands the functionality of Essay Master Assist and improves user convenience.

[0106] Essay Master Assist can also use its emotion estimation function to suggest study plans based on the user's emotions. For example, if the user feels stressed while writing an essay, it can provide advice on how to relax. If the user is feeling positive, it can display encouraging messages to help them maintain those emotions. Furthermore, the emotion estimation function can also be used to suggest study plans based on the user's emotions and support their learning progress. This makes it possible to provide study support that takes the user's emotions into consideration.

[0107] Essay Master Assist can also use its emotion estimation function to analyze the emotional impact of essay feedback on the user and emphasize positive feedback. For example, it can consider the user's emotions when providing feedback and add encouraging words. It can also use the emotion estimation function to analyze the emotional impact of feedback on the user and provide advice to reduce negative emotions. It can also use the emotion estimation function to adjust the content of the feedback to maintain the user's motivation. This allows it to provide feedback that takes the user's emotions into consideration.

[0108] Essay Master Assist can also use its emotion estimation function to analyze the emotional impact of essay ratings on users and improve the acceptability of ratings. For example, when providing rating results, it can take the user's emotions into account and emphasize positive feedback. It can also use the emotion estimation function to analyze the emotional impact of ratings on users and provide advice to reduce negative emotions. It can also use the emotion estimation function to adjust the content of ratings and maintain the user's motivation. This allows it to provide ratings that take the user's emotions into consideration.

[0109] Essay Master Assist also uses its emotion estimation function to monitor the user's emotions in real time while they are writing an essay and provide advice to reduce stress. For example, if the user feels stressed while writing an essay, it can make suggestions to help them relax. It can also monitor the user's emotions in real time and provide advice to bring out positive emotions. Furthermore, the emotion estimation function can be used to support essay writing according to the user's emotions and increase motivation to learn. This makes it possible to support essay writing that takes the user's emotions into consideration.

[0110] Essay Master Assist can also use its emotion estimation function to analyze the emotional impact of essay feedback on the user and emphasize positive feedback. For example, it can consider the user's emotions when providing feedback and add encouraging words. It can also use the emotion estimation function to analyze the emotional impact of feedback on the user and provide advice to reduce negative emotions. It can also use the emotion estimation function to adjust the content of the feedback to maintain the user's motivation. This allows it to provide feedback that takes the user's emotions into consideration.

[0111] The processing flow of the second embodiment will be briefly explained below.

[0112] Step 1: The grammar analysis module uses generative AI to comprehensively analyze the essay's grammar. It detects grammatical errors and suggests corrections. It also provides detailed explanations of the causes of the errors and offers specific advice on how to correct them. It also analyzes the frequency and patterns of errors to identify individual student weaknesses and propose a personalized learning plan. Step 2: The punctuation analysis unit uses generative AI to comprehensively analyze the essay's punctuation. It detects punctuation errors and suggests corrections. It also provides detailed explanations of the causes of the errors and offers specific advice on how to correct them. It also analyzes the frequency and patterns of errors to identify individual students' weaknesses and proposes a personalized learning plan. Step 3: The spelling analysis module uses generative AI to comprehensively analyze the spelling of the essay. It detects spelling errors and suggests corrections. It also provides detailed explanations of the causes of the errors and offers specific advice on how to correct them. It also analyzes the frequency and patterns of errors to identify individual student weaknesses and propose a personalized learning plan. Step 4: The text coherence analysis unit uses generative AI to comprehensively analyze the coherence of the essay's text. It analyzes whether each paragraph is logically connected and suggests areas for improvement. It also compares the essay with other excellent essays and provides specific examples to suggest areas for improvement. Furthermore, it uses sentiment estimation to analyze the emotional impact of feedback on students and highlight positive feedback. Step 5: The Clarity Analysis module uses generative AI to comprehensively analyze the clarity of the essay. It analyzes whether the argument is clearly conveyed and suggests areas for improvement. It also compares the essay with other excellent essays and provides specific examples to suggest areas for improvement. Furthermore, it uses sentiment estimation to analyze the emotional impact of feedback on students and highlights positive feedback. Step 6: The style analysis module uses generative AI to comprehensively analyze the essay's style. It analyzes whether the writing style is appropriate and suggests areas for improvement. It also compares the essay with other excellent essays and provides specific examples to suggest areas for style improvement. Furthermore, it uses an emotion estimation function to analyze the emotional impact of feedback on students and highlight positive feedback. Step 7: The summary generator uses AI to generate a summary that quickly captures the core content of the essay. It provides a concise summary of the main points and conclusions, highlighting important keywords and phrases. Furthermore, it uses emotion estimation to analyze students' emotional reactions to the summary and proposes a summary generation method that elicits positive emotions. Step 8: The scoring criteria setting unit uses generative AI to evaluate the essay based on customizable scoring criteria set by the teacher. The scoring criteria are set with emphasis on specific evaluation items (grammar, content, coherence, etc.), and the essay is scored based on these criteria. The scoring criteria are also compared with other excellent essays, providing specific examples. Furthermore, the emotion estimation function is used to analyze students' emotional responses to the scoring criteria and propose a scoring criteria setting method to elicit positive emotions.

[0113] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0114] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0115] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0116] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0117] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0118] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0119] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0120] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0121] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0123] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0124] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0125] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0126] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0127] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0128] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0129] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0130] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0131] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0132] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0138] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0141] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0145] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0146] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0147] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0148] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0149] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0150] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0151] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0152] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0153] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0154] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0155] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0157] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0161] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0162] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0163] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0164] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0165] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0166] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0167] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0168] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0169] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0170] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0171] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0172] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0173] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0174] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0175] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0176] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0177] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0178] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0179] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0180] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. The system uses generative AI to comprehensively analyze the essay's grammar, punctuation, spelling, coherence, clarity, and style. It also includes a grammar analysis section, a punctuation analysis section, a spelling analysis section, a coherence analysis section, a clarity analysis section, and a style analysis section. a summary generator for generating a summary that allows the reader to quickly grasp the essence of the essay; A scoring criteria setting unit that sets customizable scoring criteria. A system characterized by:

2. The grammar analysis unit Detects the grammar errors, explains the cause of the errors in detail, and gives specific advice on how to correct them.

2. The system of claim 1.

3. The punctuation analysis unit Detects the punctuation error, provides a detailed explanation of the cause of the error, and gives specific advice on how to correct it.

2. The system of claim 1.

4. The spelling analyzer is Detect the spelling error, explain in detail the cause of the error, and give specific advice on how to correct it.

2. The system of claim 1.

5. The grammar analysis unit Analyzes the frequency and patterns of grammar errors to identify students' weaknesses and suggest personalized learning plans 2. The system of claim 1.

6. The punctuation analysis unit Analyze the frequency and patterns of punctuation errors to identify student weaknesses and suggest personalized learning plans 2. The system of claim 1.

Images