System

Abstract

To efficiently evaluate the utterances and submitted objects of students during a lesson and provide appropriate feedback.SOLUTION: A system according to an embodiment comprises a loading unit, a summarization unit, a scoring unit, a report card creation unit, and a feedback generation unit. The loading unit loads utterances and submitted objects of students into the system. The summarization unit summarizes the utterances and submitted objects loaded by the loading unit. The scoring unit evaluates into scores on the basis of the summary generated by the summarization unit. The report card creation unit creates a report card on the basis of result of scoring by the scoring unit. The feedback generation unit generates feedback words on the basis of the report card created by the report card creation unit.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have the disadvantage that it is difficult to efficiently evaluate students' comments and submissions during class and provide appropriate feedback.

[0005] The system according to the embodiment aims to efficiently evaluate students' comments and submissions during lessons and provide appropriate feedback. [Means for solving the problem]

[0006] The system according to the embodiment includes a reading unit, a summarizing unit, a scoring unit, a report card creation unit, and a feedback generating unit. The reading unit reads comments and submissions made by students during class. The summarizing unit summarizes the comments and submissions read by the reading unit. The scoring unit scores the students based on the summary generated by the summarizing unit. The report card creation unit creates a report card based on the results of the scoring by the scoring unit. The feedback generating unit generates feedback text based on the report card created by the report card creation unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently evaluate students' comments and submissions during lessons and provide appropriate feedback. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed 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 and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The system according to the embodiment of the present invention is a system that reads all remarks and all submitted materials of students during class, summarizes them, and scores them. This system creates a report card and also generates feedback text. Specifically, first, there is a reading unit that reads the remarks and submitted materials of students during class. This reading unit may include processing of a generation AI. Next, there is a summarizing unit that summarizes the read remarks and submitted materials. This summarizing unit includes processing of a generation AI. There is a scoring unit that scores based on the summarized content. This scoring unit includes processing of an AI or a generation AI. There is a report card creation unit that creates a report card based on the result of the scoring. This report card creation unit also includes processing of an AI or a generation AI. Finally, there is a feedback generation unit that generates feedback text based on the report card. This feedback generation unit includes processing of a generation AI. Furthermore, there is a judgment unit that judges whether the read remarks and submitted materials were made using a generation AI. This judgment unit includes processing of an AI or a generation AI. The scoring unit uses the judgment result by the judgment unit to score. There is also a notification unit that notifies the student of the report card and feedback text. This notification unit may include AI processing. The scoring unit scores based on the quality of the remarks and the completeness of the submission. The summarizing unit adjusts the summarizing method based on the student's past remarks during class and the history of the submission. The scoring unit scores using the student's attribute information. For example, the reading unit converts the student's remarks during class into text data using voice recognition technology, and scans the submission and converts it into digital data. The summarizing unit uses a generating AI to extract the main points of the remarks and the submission and generate a concise summary. The scoring unit evaluates the logic of the remarks and the completeness of the submission based on the summarized content and gives a score. The report card creation unit creates a report card summarizing the grades for each subject based on the results of the scoring. The feedback generation unit generates feedback text for the student based on the contents of the report card. The judgment unit determines whether the remarks and submissions were made using the generating AI, and reflects the result in the scoring. The notification unit notifies the student of the generated report card and feedback text. This allows the system to efficiently summarize, score, report cards, and generate feedback on students' class work and contributions.

[0029] The system according to the embodiment includes a reading unit, a summarizing unit, a scoring unit, a report card creation unit, and a feedback generation unit. The reading unit reads the remarks made by the students during class and their submissions. The remarks include, for example, oral remarks, written remarks, digital remarks, etc., but are not limited to such examples. The submissions include, for example, reports, homework, projects, etc., but are not limited to such examples. The reading unit converts the students' remarks into text data using, for example, voice recognition technology. The reading unit can also convert the submissions into digital data using a scanner. For example, the reading unit records the students' remarks with a microphone and converts them into text data using voice recognition software. The reading unit can also read the submissions with a scanner and save them as image data. Furthermore, the reading unit can convert the image data into text data using OCR technology. The summarizing unit summarizes the read remarks and submissions using a generation AI. The summarization is performed based on, for example, the length of the sentence and the importance of the information to be summarized, but are not limited to such examples. For example, the summarizing unit extracts the main points of the remarks and submissions using a generation AI to generate a concise summary. The summarizing unit can also use a generating AI to extract and summarize important parts of the remarks and the submission. The scoring unit scores based on the summary generated by the summarizing unit. Scoring is performed, for example, based on the logic of the remarks and the completeness of the submission, but is not limited to such examples. For example, the scoring unit evaluates the logic of the remarks and the completeness of the submission based on the summarized content and gives a score. The scoring unit can also use AI to evaluate the summarized content and give a score. The report card creation unit creates a report card based on the results of the scoring by the scoring unit. The report card includes, for example, the grades of each subject and an overall evaluation, but is not limited to such examples. For example, the report card creation unit creates a report card that summarizes the grades of each subject based on the results of the scoring. The report card creation unit can also create a report card based on the results of the scoring using a generating AI. The feedback generation unit generates feedback text based on the report card created by the report card creation unit. The feedback text includes, for example, positive feedback and suggestions for improvement, but is not limited to such examples.For example, the feedback generation unit generates feedback text for the student based on the contents of the report card. The feedback generation unit can also generate feedback text based on the contents of the report card using a generation AI. This allows the system according to the embodiment to efficiently summarize and score students' comments and submissions during class, create report cards, and generate feedback text.

[0030] The reading unit reads the remarks made by students during class and their submissions. Examples of remarks include, but are not limited to, oral remarks, written remarks, digital remarks, and the like. Specifically, oral remarks are made during discussions and presentations in the classroom, and are recorded by a microphone and converted into text data using voice recognition technology. Written remarks refer to notes written by students during class or writings on a whiteboard, which are read by a scanner and converted into text data using OCR technology. Digital remarks are made through online classes or chat tools, and are directly acquired as digital data. Examples of submissions include, but are not limited to, reports, homework, projects, and the like. Reports may be submitted in handwritten or digital format, and if they are handwritten, they are scanned, and if they are digital, the data is directly acquired. Homework and projects may also be submitted in handwritten or digital format, and these are converted into digital data in an appropriate manner. The reading unit centrally manages these data and makes them accessible to the subsequent processing department. For example, voice recognition software converts the content of the remarks into text with high accuracy, and scanners and OCR technology accurately convert the content of the submissions into digital data. This enables the reading unit to efficiently collect students' various comments and submissions as digital data, improving the processing efficiency of the entire system.

[0031] The summarization unit uses the generation AI to summarize the read remarks and submissions. The summarization is performed, for example, based on the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. Specifically, the generation AI uses natural language processing technology to analyze the content of the remarks and submissions and extract important keywords and phrases. For example, it identifies words and phrases that appear frequently in the remarks and generates a summary based on them. It also analyzes the content of the submission and extracts the main points of each paragraph to create a summary. Since the generation AI has the ability to understand the context and evaluate the importance of information, it can accurately extract particularly important parts of the remarks and submissions. Furthermore, the summarization unit can also extract and summarize important parts of the remarks and submissions using the generation AI. For example, it extracts particularly important discussion and conclusion parts in the remarks and summarizes them briefly. It also extracts particularly important conclusion and proposal parts in the submission and summarizes them. In this way, the summarization unit efficiently summarizes the content of the remarks and submissions so that the subsequent processing department can quickly evaluate them. The summarization unit regularly updates the learning data of the generation AI to respond to the latest information and trends. This enables the summarization section to consistently provide highly accurate summaries, improving the efficiency and accuracy of the entire system.

[0032] The scoring unit scores based on the summary generated by the summarization unit. The scoring is performed, for example, based on the logic of the statement and the completeness of the submission, but is not limited to such examples. Specifically, the scoring unit evaluates the logic of the statement and the completeness of the submission based on the summarized content and gives a score. For example, the logic of the statement is evaluated based on the consistency, logical structure, persuasiveness, etc. of the statement. The completeness of the submission is evaluated based on the fullness, accuracy, originality, etc. of the content. The scoring unit can also use AI to evaluate the summarized content and give a score. The AI ​​learns past evaluation data and automatically adjusts the evaluation criteria to perform more accurate scoring. For example, the AI ​​learns the characteristics of past highly rated statements and submissions, and evaluates new statements and submissions based on that. The AI ​​can also dynamically adjust the evaluation criteria and perform flexible evaluation according to specific conditions and situations. This allows the scoring unit to quickly and accurately evaluate the summarized content and give a score. Furthermore, the scoring unit stores the evaluation results in a database for subsequent processing to access, allowing the scoring unit to perform scoring efficiently and effectively and improve the performance of the entire system.

[0033] The report card creation unit creates a report card based on the results of the scoring by the scoring unit. The report card includes, for example, the grades of each subject and an overall evaluation, but is not limited to such examples. Specifically, the report card creation unit creates a report card that summarizes the grades of each subject based on the results of the scoring. The grades of each subject are calculated based on the scores given by the scoring unit, and the overall evaluation is calculated by comprehensively evaluating the grades of each subject. The report card creation unit can also create a report card based on the results of the scoring using a generation AI. The generation AI learns past report card data and automatically selects the optimal format and evaluation criteria. For example, the generation AI generates graphs and charts to visually display the grades of each subject in an easy-to-understand manner, and automatically generates comments to concisely indicate the overall evaluation. In addition, the report card creation unit can also take into account the characteristics and tendencies of a specific student when creating a report card based on the results of the scoring using the generation AI. This allows the report card creation unit to provide a report card that is individually optimized for each student. Furthermore, the report card creation unit can store the report cards in a digital format and distribute them by printing or e-mail as necessary, which allows the report card creation unit to create report cards efficiently and effectively, improving the performance of the entire system.

[0034] The feedback generation unit generates feedback text based on the report card created by the report card creation unit. The feedback text includes, for example, positive feedback and suggestions for improvement, but is not limited to such examples. Specifically, the feedback generation unit generates feedback text for the student based on the contents of the report card. For example, based on the grades of each subject, it specifically points out particularly excellent points and points that need improvement. In addition, based on the overall evaluation, it evaluates the student's overall performance and provides future goals and advice. The feedback generation unit can also generate feedback text based on the contents of the report card using the generation AI. The generation AI learns past feedback data and automatically generates optimal feedback text. For example, the generation AI generates specific advice and encouraging words according to the student's grades and performance, and motivates the student to work on self-improvement. The generation AI can also provide personalized feedback by taking into account the individual characteristics and tendencies of the student. As a result, the feedback generation unit can provide specific and effective feedback to the student and improve the quality of learning. Furthermore, the feedback generation unit can save the generated feedback text in a digital format and distribute it by printing or email as necessary. This allows the feedback generator to provide feedback efficiently and effectively, improving overall system performance.

[0035] The system further includes a determination unit that determines the use of the generation AI for the remarks and submissions read by the reading unit. The determination unit determines the use of the generation AI for each of the remarks and submissions read by the reading unit. For example, the determination unit analyzes the style and content of the remarks and submissions and determines whether they were generated by the generation AI. The determination unit can also use a specific algorithm to determine the use of the generation AI. For example, the determination unit learns the characteristics of the text generated by the generation AI and determines the use of the generation AI for the remarks and submissions based on the characteristics. This enables the system to determine whether the remarks and submissions were generated using the generation AI.

[0036] The system further includes a notification unit that notifies the student of the report card created by the report card creation unit and the feedback text generated by the feedback generation unit. The notification unit notifies the student of the report card created by the report card creation unit and the feedback text generated by the feedback generation unit. The notification is performed by, for example, email notification, app notification, paper notification, and the like, but is not limited to such examples. For example, the notification unit transmits the generated report card and feedback text to the student by email. The notification unit can also notify the student of the generated report card and feedback text through a dedicated application. Furthermore, the notification unit can print the generated report card and feedback text and provide them to the student on paper. In this way, the system can notify the student of the report card and feedback text.

[0037] The scoring unit can perform scoring using the judgment result by the judgment unit. The scoring unit further performs scoring using the judgment result by the judgment unit. For example, the scoring unit assigns a score taking into consideration whether or not the remark or submission was made using the generation AI. The scoring unit can also adjust the criteria for scoring based on the judgment result by the judgment unit. For example, the scoring unit can apply stricter criteria than normal criteria to remarks or submissions made using the generation AI. This allows the system to perform scoring taking into consideration the use of the generation AI.

[0038] The scoring unit can score based on the quality of the remark and the completeness of the submission. The scoring unit can score based on the quality of the remark and the completeness of the submission. The quality of the remark includes, but is not limited to, the accuracy of the content, logic, and expressiveness. The completeness of the submission includes, but is not limited to, the fullness of the content, the consistency of the format, and compliance with the submission deadline. For example, the scoring unit can give a high score if the content of the remark is accurate and logical. Also, the scoring unit can give a high score if the content of the submission is full and well-formed. This allows the system to score based on the quality of the remark and the completeness of the submission.

[0039] The summarization unit can adjust the summarization method based on the student's past utterances during lessons and the history of his / her submissions. The summarization unit adjusts the summarization method based on the student's past utterances during lessons and the history of his / her submissions. The past history includes, for example, past utterance records, evaluation results of submissions, etc., but is not limited to such examples. For example, the summarization unit adjusts the summarization method of utterances based on the student's past utterance records. The summarization unit can also adjust the summarization method of submissions based on the evaluation results of past submissions. This allows the system to adjust the summarization method based on the past history.

[0040] The scoring unit can perform scoring using attribute information of the student. The scoring unit further performs scoring using attribute information of the student. The attribute information includes, for example, age, grade, learning history, etc., but is not limited to such examples. For example, the scoring unit adjusts the scoring criteria based on the age of the student. The scoring unit can also adjust the scoring criteria based on the grade of the student. Furthermore, the scoring unit can adjust the scoring criteria based on the learning history of the student. This allows the system to perform scoring taking into account the attribute information of the student.

[0041] The reading unit can analyze the student's past comments and the history of his / her submissions, and select the optimal reading method. For example, the reading unit reads in a similar format based on the format of assignments submitted by the student in the past. The reading unit can also analyze the frequency of the student's past comments, and read at an appropriate time. Furthermore, the reading unit can refer to the contents of the student's past submissions and prioritize reading highly relevant contents. This makes it possible to select the optimal reading method based on the past history.

[0042] The reading unit can perform filtering based on the student's current learning situation and areas of interest when reading. For example, the reading unit preferentially reads comments and submissions related to a subject currently being studied by the student. The reading unit can also filter related comments and submissions based on the student's areas of interest. Furthermore, the reading unit can also read comments and submissions of an appropriate level of difficulty according to the student's learning progress. This makes it possible to perform filtering based on the student's current learning situation and areas of interest.

[0043] During reading, the reading unit can prioritize reading highly relevant comments and submissions in consideration of the geographical location information of the student. For example, when the student is in a specific area, the reading unit prioritizes reading comments and submissions related to the area. In addition, when the student is traveling, the reading unit can also prioritize reading comments and submissions related to the travel destination. Furthermore, when the student is at home, the reading unit can also prioritize reading comments and submissions related to learning at home. In this way, highly relevant comments and submissions can be prioritized and read based on the geographical location information.

[0044] The reading unit can analyze the student's social media activity and read related comments and submissions at the time of reading. The reading unit reads related comments and submissions based on, for example, the content shared by the student on social media. The reading unit can also analyze the student's social media activity time and determine the optimal reading timing. Furthermore, the reading unit can prioritize reading related comments and submissions based on the student's social media interests. This makes it possible to read related comments and submissions based on social media activity.

[0045] The summarization unit can adjust the level of detail of the summary based on the importance of the comments and submissions when generating the summary. For example, the summarization unit can provide a detailed summary for important comments and submissions. The summarization unit can also provide a brief summary for less important comments and submissions. Furthermore, the summarization unit can adjust the length of the summary depending on the importance of the comments and submissions. This allows the level of detail of the summary to be adjusted based on the importance of the comments and submissions.

[0046] The summarization unit may apply different summarization algorithms depending on the category of the comments and submissions when generating the summarization. For example, the summarization unit may apply a science-specific summarization algorithm to science comments and submissions. The summarization unit may also apply a literature-specific summarization algorithm to literature comments and submissions. The summarization unit may also apply a mathematics-specific summarization algorithm to mathematics comments and submissions. This allows different summarization algorithms to be applied depending on the category.

[0047] When generating summaries, the summarization unit can determine the priority of summaries based on the submission times of comments and submissions. For example, the summarization unit prioritizes summarization of recently submitted comments and submissions. The summarization unit can also summarize older comments and submissions later. Furthermore, the summarization unit can adjust the order of summaries depending on the submission times. This makes it possible to determine the priority of summaries based on the submission times.

[0048] The summarization unit can adjust the order of summaries based on the relevance of comments and submissions when generating summaries. For example, the summarization unit prioritizes summarization of highly relevant comments and submissions. The summarization unit can also postpone summarization of less relevant comments and submissions. Furthermore, the summarization unit can adjust the order of summaries according to the relevance of comments and submissions. This makes it possible to adjust the order of summaries based on relevance.

[0049] The scoring unit can improve the accuracy of the scoring by considering the interrelationship between the statement and the submission when scoring. For example, the scoring unit can give a high score when the statement and the submission are consistent. The scoring unit can also deduct points when the statement and the submission are inconsistent. Furthermore, the scoring unit can adjust the score based on the relevance between the statement and the submission. In this way, the accuracy of the scoring can be improved by considering the interrelationship between the statement and the submission.

[0050] The scoring unit can perform scoring by taking into consideration attribute information of the student. The scoring unit adjusts the scoring criteria based on the student's age, for example. The scoring unit can also adjust the scoring criteria based on the student's grade. Furthermore, the scoring unit can adjust the scoring criteria based on the student's learning history. In this way, the accuracy of scoring is improved by taking into consideration the student's attribute information.

[0051] The scoring unit can score comments and submissions while taking into account the geographic distribution of the comments and submissions. For example, if comments and submissions are concentrated in a particular region, the scoring unit can apply scoring criteria related to that region. Also, if comments and submissions are distributed over a wide area, the scoring unit can apply general scoring criteria. Furthermore, the scoring unit can adjust the scores based on the geographic distribution of the comments and submissions. In this way, the accuracy of scoring is improved by taking the geographic distribution into account.

[0052] The scoring unit can improve the accuracy of the scoring by referring to related literature of the statement and the submission when scoring. For example, the scoring unit can give a high score when the statement and the submission match the related literature. The scoring unit can also reduce points when the statement and the submission contradict the related literature. Furthermore, the scoring unit can adjust the score based on the related literature of the statement and the submission. In this way, the accuracy of the scoring can be improved by referring to the related literature.

[0053] The report card creation unit can optimize the current report card by referring to past report card data when creating the report card. The report card creation unit adjusts the evaluation criteria for the current report card based on the student's past report card data, for example. The report card creation unit can also analyze grade trends from the past report card data and reflect them in the current report card. Furthermore, the report card creation unit can optimize the display format of the current report card by referring to the past report card data. In this way, the current report card can be optimized by referring to the past report card data.

[0054] The report card creation unit can apply different report card creation methods to each category of comments and submissions when creating a report card. For example, the report card creation unit applies a report card creation method dedicated to science to comments and submissions related to science. The report card creation unit can also apply a report card creation method dedicated to literature to comments and submissions related to literature. Furthermore, the report card creation unit can also apply a report card creation method dedicated to mathematics to comments and submissions related to mathematics. In this way, the accuracy of the report card is improved by applying different report card creation methods to each category.

[0055] The report card creation unit can analyze changes in the report card based on the submission dates of comments and submitted items when creating the report card. For example, the report card creation unit reflects comments and submitted items that are due soon in the report card with priority. The report card creation unit can also reflect comments and submitted items that are due earlier in the report card at a later date. Furthermore, the report card creation unit can analyze changes in the report card according to the submission dates and determine the optimal display method. This makes it possible to analyze changes in the report card based on the submission dates.

[0056] The report card creation unit can create the report card by referring to market data related to comments and submitted items when creating the report card. The report card creation unit can adjust the evaluation criteria for the report card, for example, based on market data related to comments and submitted items. The report card creation unit can also optimize the display format of the report card by referring to the related market data. Furthermore, the report card creation unit can adjust the content of the report card based on market data related to comments and submitted items. In this way, the accuracy of the report card is improved by referring to the related market data.

[0057] The feedback generating unit can adjust the level of detail of the feedback based on the importance of the comments and submissions when generating the feedback. For example, the feedback generating unit provides detailed feedback for important comments and submissions. The feedback generating unit can also provide brief feedback for less important comments and submissions. Furthermore, the feedback generating unit can adjust the length of the feedback depending on the importance of the comments and submissions. This makes it possible to adjust the level of detail of the feedback based on the importance of the comments and submissions.

[0058] The feedback generation unit can apply different feedback algorithms depending on the category of the comments and submissions when generating feedback. For example, the feedback generation unit applies a feedback algorithm dedicated to science to comments and submissions related to science. The feedback generation unit can also apply a feedback algorithm dedicated to literature to comments and submissions related to literature. Furthermore, the feedback generation unit can apply a feedback algorithm dedicated to mathematics to comments and submissions related to mathematics. In this way, different feedback algorithms can be applied depending on the category.

[0059] The feedback generation unit can determine the priority of feedback based on the submission time of comments and submissions when generating feedback. For example, the feedback generation unit gives priority to feedback of recently submitted comments and submissions. The feedback generation unit can also give feedback of older comments and submissions later. Furthermore, the feedback generation unit can adjust the order of feedback depending on the submission time. This makes it possible to determine the priority of feedback based on the submission time.

[0060] The feedback generation unit can adjust the order of feedback based on the relevance between comments and submissions when generating feedback. For example, the feedback generation unit gives priority to feedback of highly relevant comments and submissions. The feedback generation unit can also give feedback of less relevant comments and submissions later. Furthermore, the feedback generation unit can adjust the order of feedback according to the relevance between comments and submissions. This makes it possible to adjust the order of feedback based on the relevance.

[0061] When making a judgment, the judgment unit can improve the accuracy of the judgment by taking into account the interrelationship between the utterance and the submission. For example, the judgment unit recommends the use of the generation AI when the utterance and the submission are consistent. The judgment unit can also refrain from using the generation AI when the utterance and the submission are contradictory. Furthermore, the judgment unit can determine the use of the generation AI based on the relevance between the utterance and the submission. This improves the accuracy of the judgment by taking into account the interrelationship between the utterance and the submission.

[0062] When making a judgment, the judgment unit can make the judgment taking into account the geographic distribution of the comments and submissions. For example, if the comments and submissions are concentrated in a particular region, the judgment unit applies judgment criteria related to that region. In addition, if the comments and submissions are distributed over a wide area, the judgment unit can also apply general judgment criteria. Furthermore, the judgment unit can make a judgment based on the geographic distribution of the comments and submissions. In this way, the accuracy of the judgment is improved by taking the geographic distribution into account.

[0063] At the time of notification, the notification unit can select the optimal notification method by referring to the student's past notification history. The notification unit selects the optimal notification method based on, for example, the student's past notification history. The notification unit can also analyze and apply an effective notification method from the past notification history. Furthermore, the notification unit can also optimize the notification display format by referring to the student's past notification history. In this way, the optimal notification method can be selected by referring to the past notification history.

[0064] At the time of notification, the notification unit can select the optimal notification method by taking into consideration the device information of the student. For example, if the student is using a smartphone, the notification unit provides a notification method that matches the screen size. In addition, if the student is using a tablet, the notification unit can also provide a notification method that is optimized for a large screen. Furthermore, if the student is using a smartwatch, the notification unit can also provide a simple and highly visible notification method. In this way, the optimal notification method can be selected by taking into consideration the device information.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The system further includes a determination unit that determines the use of the generation AI for the remarks and submissions read by the reading unit. The determination unit determines the use of the generation AI for each of the remarks and submissions read by the reading unit. For example, the determination unit analyzes the style and content of the remarks and submissions and determines whether they were generated by the generation AI. The determination unit can also use a specific algorithm to determine the use of the generation AI. For example, the determination unit learns the characteristics of the text generated by the generation AI and determines the use of the generation AI for the remarks and submissions based on the characteristics. This enables the system to determine whether the remarks and submissions were generated using the generation AI.

[0067] The system further includes a notification unit that notifies the student of the report card created by the report card creation unit and the feedback text generated by the feedback generation unit. The notification is performed by, for example, email notification, app notification, paper notification, or other methods, but is not limited to these examples. For example, the notification unit transmits the generated report card and feedback text to the student by email. The notification unit can also notify the student of the generated report card and feedback text through a dedicated application. Furthermore, the notification unit can print the generated report card and feedback text and provide them to the student on paper. In this way, the system can notify the student of the report card and feedback text.

[0068] The scoring unit can perform scoring using the judgment result by the judgment unit. For example, the scoring unit assigns a score taking into consideration whether or not the remark or submission was made using the generation AI. The scoring unit can also adjust the criteria for scoring based on the judgment result by the judgment unit. For example, the scoring unit can apply stricter criteria than normal criteria to remarks or submissions made using the generation AI. This allows the system to perform scoring taking into consideration the use of the generation AI.

[0069] The scoring unit can score based on the quality of the remark and the completeness of the submission. The quality of the remark includes, but is not limited to, for example, the accuracy of the content, logic, and expressiveness. The completeness of the submission includes, but is not limited to, for example, the completeness of the content, the consistency of the format, and compliance with the submission deadline. For example, the scoring unit can give a high score if the content of the remark is accurate and logical. Also, the scoring unit can give a high score if the content of the submission is complete and well-formed. This allows the system to score based on the quality of the remark and the completeness of the submission.

[0070] The summarization unit can adjust the summarization method based on the student's past remarks during lessons and the history of his / her submissions. The past history includes, but is not limited to, for example, past remark records and evaluation results of submissions. For example, the summarization unit adjusts the summarization method of the remarks based on the student's past remark records. The summarization unit can also adjust the summarization method of the submission based on the evaluation results of the past submissions. This allows the system to adjust the summarization method based on the past history.

[0071] The reading unit can analyze the student's past comments and the history of his / her submissions, and select the optimal reading method. For example, the reading unit reads in a similar format based on the format of assignments submitted by the student in the past. The reading unit can also analyze the frequency of the student's past comments, and read at an appropriate time. Furthermore, the reading unit can refer to the contents of the student's past submissions and prioritize reading highly relevant contents. This makes it possible to select the optimal reading method based on the past history.

[0072] The reading unit can perform filtering based on the student's current learning situation and areas of interest when reading. For example, the reading unit preferentially reads comments and submissions related to a subject currently being studied by the student. The reading unit can also filter related comments and submissions based on the student's areas of interest. Furthermore, the reading unit can also read comments and submissions of an appropriate level of difficulty according to the student's learning progress. This makes it possible to perform filtering based on the student's current learning situation and areas of interest.

[0073] During reading, the reading unit can prioritize reading highly relevant comments and submissions in consideration of the geographical location information of the student. For example, when the student is in a specific area, the reading unit prioritizes reading comments and submissions related to the area. In addition, when the student is traveling, the reading unit can also prioritize reading comments and submissions related to the travel destination. Furthermore, when the student is at home, the reading unit can also prioritize reading comments and submissions related to learning at home. In this way, highly relevant comments and submissions can be prioritized and read based on the geographical location information.

[0074] The process flow of the first embodiment will be briefly described below.

[0075] Step 1: The reader reads students' comments during class and their submissions. Comments include oral, written, and digital comments. Submissions include reports, homework, and projects. The reader converts students' comments into text data using voice recognition technology and converts submissions into digital data using a scanner. In addition, the reader can also convert image data into text data using OCR technology. Step 2: The Summarizer uses generative AI to summarize the comments and submissions. The summarization is based on the length of the text and the importance of the information being summarized. The Summarizer extracts the main points of the comments and submissions and generates a concise summary. Step 3: The scoring section assigns a score based on the summary generated by the summarization section. The scoring section assigns a score based on the logic of the comments and the completeness of the submission. The scoring section evaluates the logic of the comments and the completeness of the submission based on the summarized content and assigns a score. Step 4: The report card creation unit creates a report card based on the results of the scoring unit. The report card includes the grades for each subject and an overall evaluation. The report card creation unit creates a report card that summarizes the grades for each subject based on the results of the scoring unit. Step 5: The feedback generation unit generates feedback text based on the report card created by the report card creation unit. The feedback text includes positive feedback and suggestions for improvement. The feedback generation unit generates feedback text for the student based on the contents of the report card.

[0076] (Example 2) The system according to the embodiment of the present invention is a system that reads all remarks and all submitted materials of students during class, summarizes them, and scores them. This system creates a report card and also generates feedback text. Specifically, first, there is a reading unit that reads the remarks and submitted materials of students during class. This reading unit may include processing of a generation AI. Next, there is a summarizing unit that summarizes the read remarks and submitted materials. This summarizing unit includes processing of a generation AI. There is a scoring unit that scores based on the summarized content. This scoring unit includes processing of an AI or a generation AI. There is a report card creation unit that creates a report card based on the result of the scoring. This report card creation unit also includes processing of an AI or a generation AI. Finally, there is a feedback generation unit that generates feedback text based on the report card. This feedback generation unit includes processing of a generation AI. Furthermore, there is a judgment unit that judges whether the read remarks and submitted materials were made using a generation AI. This judgment unit includes processing of an AI or a generation AI. The scoring unit uses the judgment result by the judgment unit to score. There is also a notification unit that notifies the student of the report card and feedback text. This notification unit may include AI processing. The scoring unit scores based on the quality of the remarks and the completeness of the submission. The summarizing unit adjusts the summarizing method based on the student's past remarks during class and the history of the submission. The scoring unit scores using the student's attribute information. For example, the reading unit converts the student's remarks during class into text data using voice recognition technology, and scans the submission and converts it into digital data. The summarizing unit uses a generating AI to extract the main points of the remarks and the submission and generate a concise summary. The scoring unit evaluates the logic of the remarks and the completeness of the submission based on the summarized content and gives a score. The report card creation unit creates a report card summarizing the grades for each subject based on the results of the scoring. The feedback generation unit generates feedback text for the student based on the contents of the report card. The judgment unit determines whether the remarks and submissions were made using the generating AI, and reflects the result in the scoring. The notification unit notifies the student of the generated report card and feedback text. This allows the system to efficiently summarize, score, report cards, and generate feedback on students' class work and contributions.

[0077] The system according to the embodiment includes a reading unit, a summarizing unit, a scoring unit, a report card creation unit, and a feedback generation unit. The reading unit reads the remarks made by the students during class and their submissions. The remarks include, for example, oral remarks, written remarks, digital remarks, etc., but are not limited to such examples. The submissions include, for example, reports, homework, projects, etc., but are not limited to such examples. The reading unit converts the students' remarks into text data using, for example, voice recognition technology. The reading unit can also convert the submissions into digital data using a scanner. For example, the reading unit records the students' remarks with a microphone and converts them into text data using voice recognition software. The reading unit can also read the submissions with a scanner and save them as image data. Furthermore, the reading unit can convert the image data into text data using OCR technology. The summarizing unit summarizes the read remarks and submissions using a generation AI. The summarization is performed based on, for example, the length of the sentence and the importance of the information to be summarized, but are not limited to such examples. For example, the summarizing unit extracts the main points of the remarks and submissions using a generation AI to generate a concise summary. The summarizing unit can also use a generating AI to extract and summarize important parts of the remarks and the submission. The scoring unit scores based on the summary generated by the summarizing unit. Scoring is performed, for example, based on the logic of the remarks and the completeness of the submission, but is not limited to such examples. For example, the scoring unit evaluates the logic of the remarks and the completeness of the submission based on the summarized content and gives a score. The scoring unit can also use AI to evaluate the summarized content and give a score. The report card creation unit creates a report card based on the results of the scoring by the scoring unit. The report card includes, for example, the grades of each subject and an overall evaluation, but is not limited to such examples. For example, the report card creation unit creates a report card that summarizes the grades of each subject based on the results of the scoring. The report card creation unit can also create a report card based on the results of the scoring using a generating AI. The feedback generation unit generates feedback text based on the report card created by the report card creation unit. The feedback text includes, for example, positive feedback and suggestions for improvement, but is not limited to such examples.For example, the feedback generation unit generates feedback text for the student based on the contents of the report card. The feedback generation unit can also generate feedback text based on the contents of the report card using a generation AI. This allows the system according to the embodiment to efficiently summarize and score students' comments and submissions during class, create report cards, and generate feedback text.

[0078] The reading unit reads the remarks made by students during class and their submissions. Examples of remarks include, but are not limited to, oral remarks, written remarks, digital remarks, and the like. Specifically, oral remarks are made during discussions and presentations in the classroom, and are recorded by a microphone and converted into text data using voice recognition technology. Written remarks refer to notes written by students during class or writings on a whiteboard, which are read by a scanner and converted into text data using OCR technology. Digital remarks are made through online classes or chat tools, and are directly acquired as digital data. Examples of submissions include, but are not limited to, reports, homework, projects, and the like. Reports may be submitted in handwritten or digital format, and if they are handwritten, they are scanned, and if they are digital, the data is directly acquired. Homework and projects may also be submitted in handwritten or digital format, and these are converted into digital data in an appropriate manner. The reading unit centrally manages these data and makes them accessible to the subsequent processing department. For example, voice recognition software converts the content of the remarks into text with high accuracy, and scanners and OCR technology accurately convert the content of the submissions into digital data. This enables the reading unit to efficiently collect students' various comments and submissions as digital data, improving the processing efficiency of the entire system.

[0079] The summarization unit uses the generation AI to summarize the read remarks and submissions. The summarization is performed, for example, based on the length of the sentence and the importance of the information to be summarized, but is not limited to such examples. Specifically, the generation AI uses natural language processing technology to analyze the content of the remarks and submissions and extract important keywords and phrases. For example, it identifies words and phrases that appear frequently in the remarks and generates a summary based on them. It also analyzes the content of the submission and extracts the main points of each paragraph to create a summary. Since the generation AI has the ability to understand the context and evaluate the importance of information, it can accurately extract particularly important parts of the remarks and submissions. Furthermore, the summarization unit can also extract and summarize important parts of the remarks and submissions using the generation AI. For example, it extracts particularly important discussion and conclusion parts in the remarks and summarizes them briefly. It also extracts particularly important conclusion and proposal parts in the submission and summarizes them. In this way, the summarization unit efficiently summarizes the content of the remarks and submissions so that the subsequent processing department can quickly evaluate them. The summarization unit regularly updates the learning data of the generation AI to respond to the latest information and trends. This enables the summarization section to consistently provide highly accurate summaries, improving the efficiency and accuracy of the entire system.

[0080] The scoring unit scores based on the summary generated by the summarization unit. The scoring is performed, for example, based on the logic of the statement and the completeness of the submission, but is not limited to such examples. Specifically, the scoring unit evaluates the logic of the statement and the completeness of the submission based on the summarized content and gives a score. For example, the logic of the statement is evaluated based on the consistency, logical structure, persuasiveness, etc. of the statement. The completeness of the submission is evaluated based on the fullness, accuracy, originality, etc. of the content. The scoring unit can also use AI to evaluate the summarized content and give a score. The AI ​​learns past evaluation data and automatically adjusts the evaluation criteria to perform more accurate scoring. For example, the AI ​​learns the characteristics of past highly rated statements and submissions, and evaluates new statements and submissions based on that. The AI ​​can also dynamically adjust the evaluation criteria and perform flexible evaluation according to specific conditions and situations. This allows the scoring unit to quickly and accurately evaluate the summarized content and give a score. Furthermore, the scoring unit stores the evaluation results in a database for subsequent processing to access, allowing the scoring unit to perform scoring efficiently and effectively and improve the performance of the entire system.

[0081] The report card creation unit creates a report card based on the results of the scoring by the scoring unit. The report card includes, for example, the grades of each subject and an overall evaluation, but is not limited to such examples. Specifically, the report card creation unit creates a report card that summarizes the grades of each subject based on the results of the scoring. The grades of each subject are calculated based on the scores given by the scoring unit, and the overall evaluation is calculated by comprehensively evaluating the grades of each subject. The report card creation unit can also create a report card based on the results of the scoring using a generation AI. The generation AI learns past report card data and automatically selects the optimal format and evaluation criteria. For example, the generation AI generates graphs and charts to visually display the grades of each subject in an easy-to-understand manner, and automatically generates comments to concisely indicate the overall evaluation. In addition, the report card creation unit can also take into account the characteristics and tendencies of a specific student when creating a report card based on the results of the scoring using the generation AI. This allows the report card creation unit to provide a report card that is individually optimized for each student. Furthermore, the report card creation unit can store the report cards in a digital format and distribute them by printing or e-mail as necessary, which allows the report card creation unit to create report cards efficiently and effectively, improving the performance of the entire system.

[0082] The feedback generation unit generates feedback text based on the report card created by the report card creation unit. The feedback text includes, for example, positive feedback and suggestions for improvement, but is not limited to such examples. Specifically, the feedback generation unit generates feedback text for the student based on the contents of the report card. For example, based on the grades of each subject, it specifically points out particularly excellent points and points that need improvement. In addition, based on the overall evaluation, it evaluates the student's overall performance and provides future goals and advice. The feedback generation unit can also generate feedback text based on the contents of the report card using the generation AI. The generation AI learns past feedback data and automatically generates optimal feedback text. For example, the generation AI generates specific advice and encouraging words according to the student's grades and performance, and motivates the student to work on self-improvement. The generation AI can also provide personalized feedback by taking into account the individual characteristics and tendencies of the student. As a result, the feedback generation unit can provide specific and effective feedback to the student and improve the quality of learning. Furthermore, the feedback generation unit can save the generated feedback text in a digital format and distribute it by printing or email as necessary. This allows the feedback generator to provide feedback efficiently and effectively, improving overall system performance.

[0083] The system further includes a determination unit that determines the use of the generation AI for the remarks and submissions read by the reading unit. The determination unit determines the use of the generation AI for each of the remarks and submissions read by the reading unit. For example, the determination unit analyzes the style and content of the remarks and submissions and determines whether they were generated by the generation AI. The determination unit can also use a specific algorithm to determine the use of the generation AI. For example, the determination unit learns the characteristics of the text generated by the generation AI and determines the use of the generation AI for the remarks and submissions based on the characteristics. This enables the system to determine whether the remarks and submissions were generated using the generation AI.

[0084] The system further includes a notification unit that notifies the student of the report card created by the report card creation unit and the feedback text generated by the feedback generation unit. The notification is performed by, for example, email notification, app notification, paper notification, or other methods, but is not limited to these examples. For example, the notification unit transmits the generated report card and feedback text to the student by email. The notification unit can also notify the student of the generated report card and feedback text through a dedicated application. Furthermore, the notification unit can print the generated report card and feedback text and provide them to the student on paper. In this way, the system can notify the student of the report card and feedback text.

[0085] The scoring unit can perform scoring using the judgment result by the judgment unit. For example, the scoring unit assigns a score taking into consideration whether or not the remark or submission was made using the generation AI. The scoring unit can also adjust the criteria for scoring based on the judgment result by the judgment unit. For example, the scoring unit can apply stricter criteria than normal criteria to remarks or submissions made using the generation AI. This allows the system to perform scoring taking into consideration the use of the generation AI.

[0086] The scoring unit can score based on the quality of the remark and the completeness of the submission. The quality of the remark includes, but is not limited to, for example, the accuracy of the content, logic, and expressiveness. The completeness of the submission includes, but is not limited to, for example, the completeness of the content, the consistency of the format, and compliance with the submission deadline. For example, the scoring unit can give a high score if the content of the remark is accurate and logical. Also, the scoring unit can give a high score if the content of the submission is complete and well-formed. This allows the system to score based on the quality of the remark and the completeness of the submission.

[0087] The summarization unit can adjust the summarization method based on the student's past remarks during lessons and the history of his / her submissions. The past history includes, but is not limited to, for example, past remark records and evaluation results of submissions. For example, the summarization unit adjusts the summarization method of the remarks based on the student's past remark records. The summarization unit can also adjust the summarization method of the submission based on the evaluation results of the past submissions. This allows the system to adjust the summarization method based on the past history.

[0088] The scoring unit can perform scoring using attribute information of the student. The attribute information includes, for example, age, grade, learning history, etc., but is not limited to such examples. For example, the scoring unit adjusts the scoring criteria based on the student's age. The scoring unit can also adjust the scoring criteria based on the student's grade. Furthermore, the scoring unit can adjust the scoring criteria based on the student's learning history. This allows the system to perform scoring taking into account the student's attribute information.

[0089] The reading unit can estimate the student's emotions and adjust the timing of reading the remarks and submissions based on the estimated student's emotions. For example, if the student is nervous, the reading unit delays reading until the student relaxes. Also, if the student is concentrating, the reading unit can read the remarks and submissions at that timing. Furthermore, if the student is tired, the reading unit can read after a break. This makes it possible to adjust the reading timing according to the student's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0090] The reading unit can analyze the student's past comments and the history of his / her submissions, and select the optimal reading method. For example, the reading unit reads in a similar format based on the format of assignments submitted by the student in the past. The reading unit can also analyze the frequency of the student's past comments, and read at an appropriate time. Furthermore, the reading unit can refer to the contents of the student's past submissions and prioritize reading highly relevant contents. This makes it possible to select the optimal reading method based on the past history.

[0091] The reading unit can perform filtering based on the student's current learning situation and areas of interest when reading. For example, the reading unit preferentially reads comments and submissions related to a subject currently being studied by the student. The reading unit can also filter related comments and submissions based on the student's areas of interest. Furthermore, the reading unit can also read comments and submissions of an appropriate level of difficulty according to the student's learning progress. This makes it possible to perform filtering based on the student's current learning situation and areas of interest.

[0092] The reading unit can estimate the student's emotions and determine the priority of the comments and submissions to be read based on the estimated student's emotions. For example, when the student is excited, the reading unit prioritizes reading important comments and submissions. In addition, when the student is calm, the reading unit can also read all comments and submissions equally. Furthermore, when the student is tired, the reading unit can also prioritize reading simple comments and submissions. This makes it possible to determine the priority of comments and submissions according to the student's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0093] During reading, the reading unit can prioritize reading highly relevant comments and submissions in consideration of the geographical location information of the student. For example, when the student is in a specific area, the reading unit prioritizes reading comments and submissions related to the area. In addition, when the student is traveling, the reading unit can also prioritize reading comments and submissions related to the travel destination. Furthermore, when the student is at home, the reading unit can also prioritize reading comments and submissions related to learning at home. In this way, highly relevant comments and submissions can be prioritized and read based on the geographical location information.

[0094] The reading unit can analyze the student's social media activity and read related comments and submissions at the time of reading. The reading unit reads related comments and submissions based on, for example, the content shared by the student on social media. The reading unit can also analyze the student's social media activity time and determine the optimal reading timing. Furthermore, the reading unit can prioritize reading related comments and submissions based on the student's social media interests. This makes it possible to read related comments and submissions based on social media activity.

[0095] The summarization unit can estimate the student's emotion and adjust the way of expressing the summary based on the estimated emotion of the student. For example, the summarization unit provides a detailed summary when the student is relaxed. The summarization unit can also provide a concise summary when the student is in a hurry. Furthermore, the summarization unit can also provide a visually appealing summary when the student is excited. This allows the way of expressing the summary to be adjusted according to the student's emotion. The estimation of emotion is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0096] The summarization unit can adjust the level of detail of the summary based on the importance of the comments and submissions when generating the summary. For example, the summarization unit can provide a detailed summary for important comments and submissions. The summarization unit can also provide a brief summary for less important comments and submissions. Furthermore, the summarization unit can adjust the length of the summary depending on the importance of the comments and submissions. This allows the level of detail of the summary to be adjusted based on the importance of the comments and submissions.

[0097] The summarization unit may apply different summarization algorithms depending on the category of the comments and submissions when generating the summarization. For example, the summarization unit may apply a science-specific summarization algorithm to science comments and submissions. The summarization unit may also apply a literature-specific summarization algorithm to literature comments and submissions. The summarization unit may also apply a mathematics-specific summarization algorithm to mathematics comments and submissions. This allows different summarization algorithms to be applied depending on the category.

[0098] The summarization unit can estimate the student's emotion and adjust the length of the summary based on the estimated student's emotion. For example, the summarization unit can provide a longer summary when the student is relaxed. Also, the summarization unit can provide a shorter summary when the student is in a hurry. Furthermore, the summarization unit can provide a visually appealing summary when the student is excited. This allows the length of the summary to be adjusted according to the student's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0099] When generating summaries, the summarization unit can determine the priority of summaries based on the submission times of comments and submissions. For example, the summarization unit prioritizes summarization of recently submitted comments and submissions. The summarization unit can also summarize older comments and submissions later. Furthermore, the summarization unit can adjust the order of summaries depending on the submission times. This makes it possible to determine the priority of summaries based on the submission times.

[0100] The summarization unit can adjust the order of summaries based on the relevance of comments and submissions when generating summaries. For example, the summarization unit prioritizes summarization of highly relevant comments and submissions. The summarization unit can also postpone summarization of less relevant comments and submissions. Furthermore, the summarization unit can adjust the order of summaries according to the relevance of comments and submissions. This makes it possible to adjust the order of summaries based on relevance.

[0101] The scoring unit can estimate the emotion of the student and adjust the scoring criteria based on the estimated emotion of the student. For example, when the student is relaxed, the scoring unit applies a normal scoring criterion. In addition, the scoring unit can relax the scoring criterion when the student is nervous. Furthermore, the scoring unit can tighten the scoring criterion when the student is excited. This makes it possible to adjust the scoring criteria according to the emotion of the student. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (for example, LLM) or a multimodal generation AI.

[0102] The scoring unit can improve the accuracy of the scoring by considering the interrelationship between the statement and the submission when scoring. For example, the scoring unit can give a high score when the statement and the submission are consistent. The scoring unit can also deduct points when the statement and the submission are inconsistent. Furthermore, the scoring unit can adjust the score based on the relevance between the statement and the submission. In this way, the accuracy of the scoring can be improved by considering the interrelationship between the statement and the submission.

[0103] The scoring unit can perform scoring by taking into consideration attribute information of the student. The scoring unit adjusts the scoring criteria based on the student's age, for example. The scoring unit can also adjust the scoring criteria based on the student's grade. Furthermore, the scoring unit can adjust the scoring criteria based on the student's learning history. In this way, the accuracy of scoring is improved by taking into consideration the student's attribute information.

[0104] The scoring unit can estimate the emotion of the student and adjust the order of displaying the scoring results based on the estimated emotion of the student. For example, when the student is relaxed, the scoring unit displays the scoring results in a normal order. Also, when the student is nervous, the scoring unit can display important scoring results first. Furthermore, when the student is excited, the scoring unit can display the scoring results in a visually attractive order. This makes it possible to adjust the order of displaying the scoring results according to the emotion of the student. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0105] The scoring unit can score comments and submissions while taking into account the geographic distribution of the comments and submissions. For example, if comments and submissions are concentrated in a particular region, the scoring unit can apply scoring criteria related to that region. Also, if comments and submissions are distributed over a wide area, the scoring unit can apply general scoring criteria. Furthermore, the scoring unit can adjust the scores based on the geographic distribution of the comments and submissions. In this way, the accuracy of scoring is improved by taking the geographic distribution into account.

[0106] The scoring unit can improve the accuracy of the scoring by referring to related literature of the statement and the submission when scoring. For example, the scoring unit can give a high score when the statement and the submission match the related literature. The scoring unit can also reduce points when the statement and the submission contradict the related literature. Furthermore, the scoring unit can adjust the score based on the related literature of the statement and the submission. In this way, the accuracy of the scoring can be improved by referring to the related literature.

[0107] The report card creation unit can estimate the emotion of the student and adjust the display method of the report card based on the estimated emotion of the student. For example, when the student is relaxed, the report card creation unit displays a normal report card. Also, when the student is nervous, the report card creation unit can display a visually attractive report card. Furthermore, when the student is excited, the report card creation unit can display a detailed report card. This makes it possible to adjust the display method of the report card according to the emotion of the student. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0108] The report card creation unit can optimize the current report card by referring to past report card data when creating the report card. The report card creation unit adjusts the evaluation criteria for the current report card based on the student's past report card data, for example. The report card creation unit can also analyze grade trends from the past report card data and reflect them in the current report card. Furthermore, the report card creation unit can optimize the display format of the current report card by referring to the past report card data. In this way, the current report card can be optimized by referring to the past report card data.

[0109] The report card creation unit can apply different report card creation methods to each category of comments and submissions when creating a report card. For example, the report card creation unit applies a report card creation method dedicated to science to comments and submissions related to science. The report card creation unit can also apply a report card creation method dedicated to literature to comments and submissions related to literature. Furthermore, the report card creation unit can also apply a report card creation method dedicated to mathematics to comments and submissions related to mathematics. In this way, the accuracy of the report card is improved by applying different report card creation methods to each category.

[0110] The report card creation unit can estimate the emotion of the student and adjust the importance of the report card based on the estimated emotion of the student. For example, when the student is relaxed, the report card creation unit displays the report card with normal importance. Also, when the student is nervous, the report card creation unit can display the report card with important items emphasized. Furthermore, when the student is excited, the report card creation unit can display a detailed report card. This makes it possible to adjust the importance of the report card according to the emotion of the student. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0111] The report card creation unit can analyze changes in the report card based on the submission dates of comments and submitted items when creating the report card. For example, the report card creation unit reflects comments and submitted items that are due soon in the report card with priority. The report card creation unit can also reflect comments and submitted items that are due earlier in the report card at a later date. Furthermore, the report card creation unit can analyze changes in the report card according to the submission dates and determine the optimal display method. This makes it possible to analyze changes in the report card based on the submission dates.

[0112] The report card creation unit can create the report card by referring to market data related to comments and submitted items when creating the report card. The report card creation unit can adjust the evaluation criteria for the report card, for example, based on market data related to comments and submitted items. The report card creation unit can also optimize the display format of the report card by referring to the related market data. Furthermore, the report card creation unit can adjust the content of the report card based on market data related to comments and submitted items. In this way, the accuracy of the report card is improved by referring to the related market data.

[0113] The feedback generating unit can estimate the student's emotion and adjust the expression method of the feedback wording based on the estimated student's emotion. For example, the feedback generating unit provides detailed feedback when the student is relaxed. Also, the feedback generating unit can provide concise feedback when the student is in a hurry. Furthermore, the feedback generating unit can provide visually attractive feedback when the student is excited. This makes it possible to adjust the expression method of the feedback wording according to the student's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0114] The feedback generating unit can adjust the level of detail of the feedback based on the importance of the comments and submissions when generating the feedback. For example, the feedback generating unit provides detailed feedback for important comments and submissions. The feedback generating unit can also provide brief feedback for less important comments and submissions. Furthermore, the feedback generating unit can adjust the length of the feedback depending on the importance of the comments and submissions. This makes it possible to adjust the level of detail of the feedback based on the importance of the comments and submissions.

[0115] The feedback generation unit can apply different feedback algorithms depending on the category of the comments and submissions when generating feedback. For example, the feedback generation unit applies a feedback algorithm dedicated to science to comments and submissions related to science. The feedback generation unit can also apply a feedback algorithm dedicated to literature to comments and submissions related to literature. Furthermore, the feedback generation unit can apply a feedback algorithm dedicated to mathematics to comments and submissions related to mathematics. In this way, different feedback algorithms can be applied depending on the category.

[0116] The feedback generation unit can estimate the student's emotion and adjust the length of the feedback text based on the estimated student's emotion. For example, the feedback generation unit provides longer feedback when the student is relaxed. Also, the feedback generation unit can provide shorter feedback when the student is in a hurry. Furthermore, the feedback generation unit can provide visually appealing feedback when the student is excited. This allows the length of the feedback text to be adjusted according to the student's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0117] The feedback generation unit can determine the priority of feedback based on the submission time of comments and submissions when generating feedback. For example, the feedback generation unit gives priority to feedback of recently submitted comments and submissions. The feedback generation unit can also give feedback of older comments and submissions later. Furthermore, the feedback generation unit can adjust the order of feedback depending on the submission time. This makes it possible to determine the priority of feedback based on the submission time.

[0118] The feedback generation unit can adjust the order of feedback based on the relevance between comments and submissions when generating feedback. For example, the feedback generation unit gives priority to feedback of highly relevant comments and submissions. The feedback generation unit can also give feedback of less relevant comments and submissions later. Furthermore, the feedback generation unit can adjust the order of feedback according to the relevance between comments and submissions. This makes it possible to adjust the order of feedback based on the relevance.

[0119] The judgment unit can estimate the student's emotions and adjust the criteria for determining the use of the generation AI based on the estimated student's emotions. For example, the judgment unit recommends the use of the generation AI when the student is relaxed. The judgment unit can also refrain from using the generation AI when the student is nervous. Furthermore, the judgment unit can also recommend the use of the generation AI when the student is excited. This makes it possible to adjust the criteria for determining the use of the generation AI according to the student's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0120] When making a judgment, the judgment unit can improve the accuracy of the judgment by taking into account the interrelationship between the utterance and the submission. For example, the judgment unit recommends the use of the generation AI when the utterance and the submission are consistent. The judgment unit can also refrain from using the generation AI when the utterance and the submission are contradictory. Furthermore, the judgment unit can determine the use of the generation AI based on the relevance between the utterance and the submission. This improves the accuracy of the judgment by taking into account the interrelationship between the utterance and the submission.

[0121] The judgment unit can estimate the student's emotion and adjust the order of displaying the judgment results based on the estimated student's emotion. For example, when the student is relaxed, the judgment unit displays the judgment results in a normal order. Also, when the student is nervous, the judgment unit can display important judgment results first. Furthermore, when the student is excited, the judgment unit can display the judgment results in a visually attractive order. This makes it possible to adjust the order of displaying the judgment results according to the student's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0122] When making a judgment, the judgment unit can make the judgment taking into account the geographic distribution of the comments and submissions. For example, if the comments and submissions are concentrated in a particular region, the judgment unit applies judgment criteria related to that region. In addition, if the comments and submissions are distributed over a wide area, the judgment unit can also apply general judgment criteria. Furthermore, the judgment unit can make a judgment based on the geographic distribution of the comments and submissions. In this way, the accuracy of the judgment is improved by taking the geographic distribution into account.

[0123] The notification unit can estimate the student's emotion and adjust the notification display method based on the estimated student's emotion. For example, the notification unit uses a normal notification method when the student is relaxed. Also, the notification unit can use a visually attractive notification method when the student is nervous. Furthermore, the notification unit can use a detailed notification method when the student is excited. This makes it possible to adjust the notification display method according to the student's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0124] At the time of notification, the notification unit can select the optimal notification method by referring to the student's past notification history. The notification unit can also analyze and apply an effective notification method from the past notification history. Furthermore, the notification unit can also optimize the notification display format by referring to the student's past notification history. In this way, the optimal notification method can be selected by referring to the past notification history.

[0125] The notification unit can estimate the student's emotion and determine the priority of notifications based on the estimated student's emotion. For example, when the student is relaxed, the notification unit can perform notifications in normal priority order. Also, when the student is nervous, the notification unit can perform important notifications first. Furthermore, when the student is excited, the notification unit can perform notifications in a visually attractive order. This makes it possible to determine the priority of notifications according to the student's emotion. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0126] At the time of notification, the notification unit can select the optimal notification method by taking into consideration the device information of the student. For example, if the student is using a smartphone, the notification unit provides a notification method that matches the screen size. In addition, if the student is using a tablet, the notification unit can also provide a notification method that is optimized for a large screen. Furthermore, if the student is using a smartwatch, the notification unit can also provide a simple and highly visible notification method. In this way, the optimal notification method can be selected by taking into consideration the device information.

[0127] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0128] The system further includes a determination unit that determines the use of the generation AI for the remarks and submissions read by the reading unit. The determination unit determines the use of the generation AI for each of the remarks and submissions read by the reading unit. For example, the determination unit analyzes the style and content of the remarks and submissions and determines whether they were generated by the generation AI. The determination unit can also use a specific algorithm to determine the use of the generation AI. For example, the determination unit learns the characteristics of the text generated by the generation AI and determines the use of the generation AI for the remarks and submissions based on the characteristics. This enables the system to determine whether the remarks and submissions were generated using the generation AI.

[0129] The system further includes a notification unit that notifies the student of the report card created by the report card creation unit and the feedback text generated by the feedback generation unit. The notification is performed by, for example, email notification, app notification, paper notification, or other methods, but is not limited to these examples. For example, the notification unit transmits the generated report card and feedback text to the student by email. The notification unit can also notify the student of the generated report card and feedback text through a dedicated application. Furthermore, the notification unit can print the generated report card and feedback text and provide them to the student on paper. In this way, the system can notify the student of the report card and feedback text.

[0130] The scoring unit can perform scoring using the judgment result by the judgment unit. For example, the scoring unit assigns a score taking into consideration whether or not the remark or submission was made using the generation AI. The scoring unit can also adjust the criteria for scoring based on the judgment result by the judgment unit. For example, the scoring unit can apply stricter criteria than normal criteria to remarks or submissions made using the generation AI. This allows the system to perform scoring taking into consideration the use of the generation AI.

[0131] The scoring unit can score based on the quality of the remark and the completeness of the submission. The quality of the remark includes, but is not limited to, for example, the accuracy of the content, logic, and expressiveness. The completeness of the submission includes, but is not limited to, for example, the completeness of the content, the consistency of the format, and compliance with the submission deadline. For example, the scoring unit can give a high score if the content of the remark is accurate and logical. Also, the scoring unit can give a high score if the content of the submission is complete and well-formed. This allows the system to score based on the quality of the remark and the completeness of the submission.

[0132] The summarization unit can adjust the summarization method based on the student's past remarks during lessons and the history of his / her submissions. The past history includes, but is not limited to, for example, past remark records and evaluation results of submissions. For example, the summarization unit adjusts the summarization method of the remarks based on the student's past remark records. The summarization unit can also adjust the summarization method of the submission based on the evaluation results of the past submissions. This allows the system to adjust the summarization method based on the past history.

[0133] The reading unit can estimate the student's emotions and adjust the timing of reading the remarks and submissions based on the estimated student's emotions. For example, if the student is nervous, the reading unit delays reading until the student relaxes. Also, if the student is concentrating, the reading unit can read the remarks and submissions at that timing. Furthermore, if the student is tired, the reading unit can read after a break. This makes it possible to adjust the reading timing according to the student's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0134] The reading unit can analyze the student's past comments and the history of his / her submissions, and select the optimal reading method. For example, the reading unit reads in a similar format based on the format of assignments submitted by the student in the past. The reading unit can also analyze the frequency of the student's past comments, and read at an appropriate time. Furthermore, the reading unit can refer to the contents of the student's past submissions and prioritize reading highly relevant contents. This makes it possible to select the optimal reading method based on the past history.

[0135] The reading unit can perform filtering based on the student's current learning situation and areas of interest when reading. For example, the reading unit preferentially reads comments and submissions related to a subject currently being studied by the student. The reading unit can also filter related comments and submissions based on the student's areas of interest. Furthermore, the reading unit can also read comments and submissions of an appropriate level of difficulty according to the student's learning progress. This makes it possible to perform filtering based on the student's current learning situation and areas of interest.

[0136] The reading unit can estimate the student's emotions and determine the priority of the comments and submissions to be read based on the estimated student's emotions. For example, when the student is excited, the reading unit prioritizes reading important comments and submissions. In addition, when the student is calm, the reading unit can also read all comments and submissions equally. Furthermore, when the student is tired, the reading unit can also prioritize reading simple comments and submissions. This makes it possible to determine the priority of comments and submissions according to the student's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0137] During reading, the reading unit can prioritize reading highly relevant comments and submissions in consideration of the geographical location information of the student. For example, when the student is in a specific area, the reading unit prioritizes reading comments and submissions related to the area. In addition, when the student is traveling, the reading unit can also prioritize reading comments and submissions related to the travel destination. Furthermore, when the student is at home, the reading unit can also prioritize reading comments and submissions related to learning at home. In this way, highly relevant comments and submissions can be prioritized and read based on the geographical location information.

[0138] The process flow of the second embodiment will be briefly described below.

[0139] Step 1: The reader reads students' comments during class and their submissions. Comments include oral, written, and digital comments. Submissions include reports, homework, and projects. The reader converts students' comments into text data using voice recognition technology and converts submissions into digital data using a scanner. In addition, the reader can also convert image data into text data using OCR technology. Step 2: The Summarizer uses generative AI to summarize the comments and submissions. The summarization is based on the length of the text and the importance of the information being summarized. The Summarizer extracts the main points of the comments and submissions and generates a concise summary. Step 3: The scoring section assigns a score based on the summary generated by the summarization section. The scoring section assigns a score based on the logic of the comments and the completeness of the submission. The scoring section evaluates the logic of the comments and the completeness of the submission based on the summarized content and assigns a score. Step 4: The report card creation unit creates a report card based on the results of the scoring unit. The report card includes the grades for each subject and an overall evaluation. The report card creation unit creates a report card that summarizes the grades for each subject based on the results of the scoring unit. Step 5: The feedback generation unit generates feedback text based on the report card created by the report card creation unit. The feedback text includes positive feedback and suggestions for improvement. The feedback generation unit generates feedback text for the student based on the contents of the report card.

[0140] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0141] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0142] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0143] For example, the reading unit can read the remarks and submissions of the students using the microphone 38B or the camera 42 of the smart device 14. The summarizing unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. The scoring unit is realized by the specific processing unit 290 of the data processing device 12 and scores based on the summarized content. The report card creation unit is realized by the specific processing unit 290 of the data processing device 12 and creates a report card based on the results of the scoring. The feedback generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates feedback text based on the contents of the report card. The judgment unit is realized by the specific processing unit 290 of the data processing device 12 and judges whether the remarks and submissions were made using the generation AI. The notification unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and notifies the student of the report card and feedback text. The reading unit estimates the emotion of the student using the camera 42 and the microphone 38B of the smart device 14, and adjusts the reading timing based on the estimated emotion. The correspondence between each unit and the device or the control unit is not limited to the above example, and various changes are possible.

[0144] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0145] 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.

[0146] 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, the RAM 30, and the 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.

[0147] 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.

[0148] 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 the voice according to instructions from the processor 46.

[0149] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0150] 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 performed in a secure state.

[0151] Fig. 4 shows an example of 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.

[0152] 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.

[0153] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0154] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0155] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0156] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0157] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0158] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0159] For example, the reading unit can read the student's remarks and submissions using the microphone 238 or the camera 42 of the smart glasses 214. The summarizing unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. The scoring unit is realized by the specific processing unit 290 of the data processing device 12 and scores based on the summarized content. The report card creation unit is realized by the specific processing unit 290 of the data processing device 12 and creates a report card based on the result of the scoring. The feedback generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates feedback text based on the content of the report card. The judgment unit is realized by the specific processing unit 290 of the data processing device 12 and judges whether the remarks and submissions were made using the generation AI. The notification unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and notifies the student of the report card and feedback text. The reading unit estimates the student's emotion using the camera 42 and microphone 238 of the smart glasses 214, and adjusts the reading timing based on the estimated emotion. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0160] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0161] 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.

[0162] 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, the RAM 30, and the 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.

[0163] 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.

[0164] 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 the voice according to instructions from the processor 46.

[0165] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0166] 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 performed in a secure state.

[0167] 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.

[0168] 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.

[0169] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0170] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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 identification processing unit 290 using these models.

[0171] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0172] 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 voice indicating a user input for 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.

[0173] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0174] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0175] For example, the reading unit can read the remarks and submissions of the students using the microphone 238 or the camera 42 of the headset type terminal 314. The summarizing unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. The scoring unit is realized by the specific processing unit 290 of the data processing device 12, and scores based on the summarized content. The report card creation unit is realized by the specific processing unit 290 of the data processing device 12, and creates a report card based on the results of the scoring. The feedback generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates feedback text based on the content of the report card. The judgment unit is realized by the specific processing unit 290 of the data processing device 12, and judges whether the remarks and submissions were made using the generation AI. The notification unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12, and notifies the student of the report card and feedback text. The reading unit estimates the emotion of the student using the camera 42 and microphone 238 of the headset terminal 314, and adjusts the timing of reading based on the estimated emotion. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0176] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0177] 7, a 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.

[0178] 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, the RAM 30, and the 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.

[0179] 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.

[0180] 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 the voice according to instructions from the processor 46.

[0181] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0182] 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 performed in a secure state.

[0183] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0184] 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.

[0185] 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.

[0186] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0187] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 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.

[0188] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0189] 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 a voice indicating a user input for 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.

[0190] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0191] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0192] For example, the reading unit can read the remarks and submissions of the students using the microphone 238 and the camera 42 of the robot 414. The summarizing unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. The scoring unit is realized by the specific processing unit 290 of the data processing device 12, and scores based on the summarized content. The report card creation unit is realized by the specific processing unit 290 of the data processing device 12, and creates a report card based on the results of the scoring. The feedback generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates feedback text based on the content of the report card. The judgment unit is realized by the specific processing unit 290 of the data processing device 12, and judges whether the remarks and submissions were made using the generation AI. The notification unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12, and notifies the student of the report card and feedback text. The reading unit estimates the emotion of the student using the camera 42 and microphone 238 of the robot 414, and adjusts the timing of reading based on the estimated emotion. The correspondence between each unit and the device or control unit is not limited to the above example, and various modifications are possible.

[0193] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0194] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0195] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0196] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0197] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0198] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0199] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0200] 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.

[0201] 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 Universal Serial Bus (USB) 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.

[0202] In addition, 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 upon request from the data processing device 12.

[0203] 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.

[0204] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0205] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0206] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0207] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0208] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0209] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0210] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0211] (Appendix 1) A reading section that reads students' comments and submissions during class, a summary unit that summarizes the comments and the submissions read by the reading unit; a scoring unit that scores the summary based on the summary generated by the summarizing unit; a report card creation unit that creates a report card based on the result of the scoring by the scoring unit; a feedback generating unit that generates a feedback message based on the report card created by the report card creating unit; A system characterized by: (Appendix 2) The method further includes a determination unit that determines whether or not to use a generation AI for each of the comments and the submissions read by the reading unit. 2. The system of claim 1, (Appendix 3) The school further includes a notification unit that notifies the student of the report card created by the report card creation unit and the feedback message created by the feedback generation unit. 2. The system of claim 1, (Appendix 4) The scoring unit is The scoring is performed by further using the judgment result by the judgment unit. 2. The system of claim 1, (Appendix 5) The scoring unit is A score will be assigned based on the quality of the comments and the completeness of the submission. 2. The system of claim 1, (Appendix 6) The summary portion comprises: Adjust the summarization method based on the student's past class utterances and submission history. 2. The system of claim 1, (Appendix 7) The scoring unit is The scoring is performed by further using the attribute information of the student. 2. The system of claim 1, (Appendix 8) The reading unit is Estimate student sentiment and adjust the timing of comments and submissions based on the estimated student sentiment 2. The system of claim 1, (Appendix 9) The reading unit is Analyze students' past comments and submission history to determine the best way to load them 2. The system of claim 1, (Appendix 10) The reading unit is Filter at load time based on students' current learning status and interests 2. The system of claim 1, (Appendix 11) The reading unit is Estimate student sentiment and prioritize comments and submissions based on estimated student sentiment 2. The system of claim 1, (Appendix 12) The reading unit is During import, the geographic location of students is taken into account to prioritize relevant comments and submissions 2. The system of claim 1, (Appendix 13) The reading unit is Upon loading, analyze students' social media activity and load relevant comments and submissions 2. The system of claim 1, (Appendix 14) The summary portion comprises: Estimate the student's emotions and adjust the way the summary is presented based on the estimated student emotions. 2. The system of claim 1, (Appendix 15) The summary portion comprises: When generating summaries, adjust the level of detail in the summary based on the importance of the comments and submissions 2. The system of claim 1, (Appendix 16) The summary portion comprises: When generating summaries, apply different summarization algorithms depending on the category of comments and submissions 2. The system of claim 1, (Appendix 17) The summary portion comprises: Estimate student sentiment and adjust the length of the summary based on the estimated student sentiment 2. The system of claim 1, (Appendix 18) The summary portion comprises: During summary generation, prioritize summaries based on the time of contributions and submissions 2. The system of claim 1, (Appendix 19) The summary portion comprises: When generating summaries, adjust the order of summaries based on the relevance of comments to submissions 2. The system of claim 1, (Appendix 20) The scoring unit is Estimate student emotions and adjust the grading scale based on the estimated student emotions 2. The system of claim 1, (Appendix 21) The scoring unit is When scoring, the accuracy of scoring will be improved by considering the correlation between comments and submissions. 2. The system of claim 1, (Appendix 22) The scoring unit is When scoring, the student's attribute information is taken into consideration. 2. The system of claim 1, (Appendix 23) The scoring unit is Infer student emotions and adjust the order in which the scoring results are displayed based on the estimated student emotions 2. The system of claim 1, (Appendix 24) The scoring unit is When scoring, the geographical distribution of comments and submissions is taken into account. 2. The system of claim 1, (Appendix 25) The scoring unit is When scoring, improve accuracy by referencing related literature on comments and submissions. 2. The system of claim 1, (Appendix 26) The report card creation unit Infer student emotions and adjust report card presentation based on the estimated student emotions 2. The system of claim 1, (Appendix 27) The report card creation unit When creating report cards, refer to past report card data to optimize the current report card 2. The system of claim 1, (Appendix 28) The report card creation unit When creating report cards, apply different report card creation methods to different categories of comments and submissions. 2. The system of claim 1, (Appendix 29) The report card creation unit Infer student emotions and adjust the importance of report cards based on the estimated student emotions 2. The system of claim 1, (Appendix 30) The report card creation unit When preparing report cards, analyze changes in the report cards based on comments and the timing of submission of assignments 2. The system of claim 1, (Appendix 31) The report card creation unit When creating report cards, refer to relevant market data for comments and submissions to create report cards. 2. The system of claim 1, (Appendix 32) The feedback generating unit is Infer student emotions and adjust feedback language based on the estimated student emotions 2. The system of claim 1, (Appendix 33) The feedback generating unit is When generating feedback, adjust the level of detail in your feedback based on the importance of what is said and what is submitted 2. The system of claim 1, (Appendix 34) The feedback generating unit is Apply different feedback algorithms depending on the category of comments and submissions when generating feedback 2. The system of claim 1, (Appendix 35) The feedback generating unit is Infer student emotions and adjust the length of feedback based on the estimated student emotions 2. The system of claim 1, (Appendix 36) The feedback generating unit is When feedback is generated, it is prioritized based on what was said and when the submission was made 2. The system of claim 1, (Appendix 37) The feedback generating unit is When generating feedback, adjust the order of feedback based on the relevance of what is said to the submission 2. The system of claim 1, (Appendix 38) The determination unit is Estimate student emotions and adjust the criteria for judging the use of generative AI based on the estimated student emotions. 2. The system of claim 1, (Appendix 39) The determination unit is When making decisions, consider the correlation between comments and submissions to improve the accuracy of the decision 2. The system of claim 1, (Appendix 40) The determination unit is Infer students' emotions and adjust the order in which judgment results are displayed based on the estimated student emotions 2. The system of claim 1, (Appendix 41) The determination unit is When making a decision, the geographical distribution of comments and submissions will be taken into account. 2. The system of claim 1, (Appendix 42) The notification unit is Estimate student emotions and adjust notification display based on estimated student emotions 2. The system of claim 1, (Appendix 43) The notification unit is When notifying students, the system will refer to their past notification history to select the most appropriate notification method. 2. The system of claim 1, (Appendix 44) The notification unit is Estimate student emotions and prioritize notifications based on estimated student emotions 2. The system of claim 1, (Appendix 45) The notification unit is When notifying students, the most appropriate notification method is selected based on the student's device information. 2. The system of claim 1, [Explanation of symbols]

[0212] 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. A reading section that reads students' comments and submissions during class, a summary unit that summarizes the comments and the submissions read by the reading unit; a scoring unit that scores the summary based on the summary generated by the summarizing unit; a report card creation unit that creates a report card based on the result of the scoring by the scoring unit; a feedback generating unit that generates a feedback message based on the report card created by the report card creating unit; A system characterized by:

2. The system further includes a determination unit that determines the use of a generation AI for each of the comments and the submissions read by the reading unit.

2. The system of claim 1 .

3. The school further includes a notification unit that notifies the student of the report card created by the report card creation unit and the feedback message created by the feedback generation unit.

2. The system of claim 1 .

4. The scoring unit is The scoring is performed by further using the judgment result by the judgment unit.

3. The system of claim 2.

5. The scoring unit is A score will be assigned based on the quality of the comments and the completeness of the submission.

2. The system of claim 1 .

6. The summary portion comprises: Adjust the summarization method based on the student's past class utterances and submission history.

2. The system of claim 1 .

7. The scoring unit is The scoring is performed by further using the attribute information of the student.

2. The system of claim 1 .

8. The reading unit is Estimate student sentiment and adjust the timing of comments and submissions based on the estimated student sentiment 2. The system of claim 1 .

9. The reading unit is Analyze students' past comments and submission history to determine the best way to load them 2. The system of claim 1 .

Images