system

Abstract

The system according to the embodiment aims to automate test grading, score aggregation, and advice on how to proceed with studies. [Solution] The system according to the embodiment comprises a scanning unit, an analysis unit, a comment generation unit, an output unit, a tallying unit, a visualization unit, and an advice unit. The scanning unit scans test papers. The analysis unit analyzes the data scanned by the scanning unit. The comment generation unit generates comments based on the data analyzed by the analysis unit. The output unit prints out the comments generated by the comment generation unit and the grading results. The tallying unit tallys the grades obtained by the analysis unit. The visualization unit visualizes the grades tallied by the tallying unit. The advice unit gives advice on how to proceed with studying based on the data visualized by the visualization unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, grading tests, compiling grades, and providing advice on how to study were all done manually, which was time-consuming and labor-intensive.

[0005] The system according to the embodiment aims to automate test grading, score aggregation, and advice on how to proceed with studies. [Means for solving the problem]

[0006] The system according to the embodiment comprises a scanning unit, an analysis unit, a comment generation unit, an output unit, a tallying unit, a visualization unit, and an advice unit. The scanning unit scans the test paper. The analysis unit analyzes the data scanned by the scanning unit. The comment generation unit generates comments based on the data analyzed by the analysis unit. The output unit prints out the comments generated by the comment generation unit and the grading results. The tallying unit tallys the grades obtained by the analysis unit. The visualization unit visualizes the grades tallied by the tallying unit. The advice unit gives advice on how to proceed with studying based on the data visualized by the visualization unit. [Effects of the Invention]

[0007] The system according to the embodiment can automate test grading, score aggregation, and advice on how to proceed with studying. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An automatic marking system according to an embodiment of the present invention scans test papers, automatically marks them, and prints them out with comments. This system also aggregates scores by subject and unit, visualizes weak and strong units, and provides advice on how to proceed with study. Specifically, it consists of the following steps: First, the test paper is scanned. Next, AI analyzes the scanned data and determines whether each question is correct. Then, the AI ​​automatically generates comments and prints them out along with the grading results. Furthermore, grades are aggregated by subject and unit, visualizes weak and strong units. Finally, the AI ​​provides advice on how to proceed with study. First, the test paper is scanned. In this process, the scanner acquires image data of the test paper. Next, the AI ​​analyzes the scanned data. The AI ​​analyzes the image data and determines whether each question is correct. For example, in a multiple-choice test, the position of the marks is analyzed to determine whether the question is correct. The AI ​​then automatically generates comments. The AI ​​generates appropriate comments based on the correctness of each question. For example, if the answer is correct, the system generates a comment such as "Good job!", and if the answer is incorrect, the system generates a comment such as "Let's review it again." Next, the system prints out the grading results and the comments. The printed results include the correct / incorrect status of each question and the comments. Furthermore, the system aggregates grades by subject and unit. The AI ​​aggregates the grades for each question and summarizes the grades by subject and unit. Finally, it visualizes the weak and strong units. Based on the aggregated grades, the AI ​​displays the weak and strong units in graphs and tables. This allows users to see at a glance their strong and weak areas. Furthermore, the AI ​​provides advice on how to proceed with their studies. For example, for weak units, the system provides advice such as "You should focus on reviewing this unit." This allows the automatic grading system to scan test papers, automatically grade them, and print them out with comments. Furthermore, by aggregating grades by subject and unit and visualizing the strong and weak units, the system can provide users with appropriate advice on how to proceed with their studies.

[0029] The automatic marking system according to the embodiment includes a scanning unit, an analysis unit, a comment generation unit, an output unit, a tallying unit, a visualization unit, and an advice unit. The scanning unit scans a test paper to acquire image data. For example, the scanning unit can use a high-resolution scanner to scan the test paper and generate image data. The scanning unit can also use a smartphone camera to photograph the test paper and acquire image data. The scanning unit can also convert handwritten answers into digital data using OCR technology. The analysis unit analyzes the image data acquired by the scanning unit and determines whether each question is correct. For example, the analysis unit can use an image processing algorithm to analyze the mark positions in a multiple-choice test and determine whether the answer is correct. The analysis unit can also analyze handwritten answers and determine whether the answer is correct using handwriting recognition technology. The analysis unit can also use AI to extract text data from the image data and determine whether each question is correct. The comment generation unit generates comments based on the correctness of each question determined by the analysis unit. For example, the comment generation unit uses natural language processing technology to generate comments such as "Good job" for correct answers and "Let's review it again" for incorrect answers. The comment generation unit can also use a template-based generation method to generate comments based on the correctness of each question. Furthermore, the comment generation unit can use AI to generate appropriate comments based on the correctness of each question. The output unit prints out the comments generated by the comment generation unit and the grading results determined by the analysis unit. For example, the output unit uses a printer to print the grading results, including the correctness of each question and comments. The output unit can also save the grading results in digital format and provide them to users via email or a cloud service. Furthermore, the output unit can display the grading results to users via a web application or a mobile application. The compilation unit tallys the grades obtained by the analysis unit and compiles grades by subject or unit. For example, the compilation unit stores the grades for each question in a database and tallys grades by subject or unit.The tallying unit can also normalize the grade data to facilitate comparison between different tests. Furthermore, the tallying unit can use AI to analyze the grade data and automatically tally grades for each subject or unit. The visualization unit displays weak and strong units in graphs and tables based on the grades tallied by the tallying unit. For example, the visualization unit can visually display grades for each unit using bar graphs or pie charts. The visualization unit can also visually display the distribution of grades using heat maps. Furthermore, the visualization unit can analyze the grade data using AI and automatically visualize weak and strong units. The advice unit provides advice on how to proceed with studies based on the data visualized by the visualization unit. For example, the advice unit can provide advice such as "Focus on reviewing this unit" for weak units. Furthermore, the advice unit can provide advice such as "Study this unit in more depth" for strong units. Furthermore, the advice unit can analyze the grade data and propose individual study plans using AI. As a result, the automatic marking system according to the embodiment can scan test papers, automatically mark them, and print them out with comments. Furthermore, by tallying up grades by subject and unit, and visualizing weak and strong units, the system can provide appropriate advice to users on how to proceed with their studies.

[0030] The scanning unit can acquire image data of the test paper. For example, the scanning unit can scan the test paper with a scanner and save the image data. The scanning unit can also capture a photo of the test paper using a smartphone camera and acquire the image data. For example, the scanning unit can capture a photo of the test paper using a smartphone camera and acquire the image data using a dedicated app. The scanning unit can also write a handwritten answer sheet with a dedicated digital pen, which converts the answer sheet into digital data in real time. For example, the scanning unit can detect the movement of the digital pen with a sensor and save it as character data. This allows the scanning unit to accurately acquire image data of the test paper. Some or all of the above-mentioned processing in the scanning unit may be performed using, for example, AI, or may be performed without AI. For example, the scanning unit can input the image data acquired by scanning the test paper into a generation AI and have the generation AI generate text data from the image data.

[0031] The analysis unit can analyze the image data and determine whether each question is correct. For example, the analysis unit can use an image processing algorithm to analyze the mark positions on a multiple-choice test and determine whether the answer is correct. The analysis unit can also analyze handwritten answers and determine whether the answer is correct using handwritten character recognition technology. For example, the analysis unit can use handwritten character recognition technology to convert the characters on a handwritten answer into digital data and determine whether the answer is correct. The analysis unit can also use AI to extract text data from the image data and determine whether each question is correct. For example, the analysis unit can use AI to analyze the image data and determine whether each question is correct. This allows the analysis unit to accurately determine whether each question is correct. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the image data to a generation AI and have the generation AI determine whether the answer is correct.

[0032] The comment generation unit can generate comments based on the correctness of each question. For example, the comment generation unit can use natural language processing technology to generate comments such as "Good job" for a correct answer and "Let's review it again" for an incorrect answer. The comment generation unit can also use a template-based generation method to generate comments based on the correctness of each question. For example, the comment generation unit can use the template-based generation method to generate comments such as "Great" for a correct answer and "Try harder next time" for an incorrect answer. The comment generation unit can also use AI to generate appropriate comments based on the correctness of each question. For example, the comment generation unit can use AI to generate comments including individual feedback based on the correctness of each question. This allows the comment generation unit to generate appropriate comments based on the correctness of each question. Some or all of the above-described processing in the comment generation unit may be performed using AI, or may be performed without AI. For example, the comment generation unit can input correct / incorrect data to a generation AI and have the generation AI generate comments.

[0033] The output unit can print out comments along with the scoring results. The output unit can print the scoring results, including the correct / incorrect answers and comments for each question, using, for example, a printer. The output unit can also save the scoring results in digital format and provide them to the user via email or a cloud service. For example, the output unit can save the scoring results in PDF format and send them to the user via email. The output unit can also display the scoring results to the user via a web application or a mobile application. For example, the output unit can allow the user to check the scoring results online via a web application. This allows the output unit to print out the scoring results and comments. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the scoring results and comments to a generation AI, which can then generate a printout format.

[0034] The tallying unit can tally the grades for each question and compile grades by subject or unit. The tallying unit can, for example, store the grades for each question in a database and tally the grades by subject or unit. The tallying unit can also normalize the grade data to facilitate comparison between different tests. For example, the tallying unit can normalize the grade data to uniformly compare grades for different tests. The tallying unit can also use AI to analyze the grade data and automatically tally the grades for each subject or unit. For example, the tallying unit can use AI to analyze the grade data and automatically tally the grades for each subject or unit. This allows the tallying unit to tally the grades for each question and compile grades by subject or unit. Some or all of the above-mentioned processing in the tallying unit may be performed using AI, for example, or may be performed without using AI. For example, the tallying unit can input the grade data to a generation AI and have the generation AI tally the grades.

[0035] The visualization unit can display weak and strong units in a graph or table based on the aggregated grades. The visualization unit can visually display the grades for each unit using, for example, a bar graph or a pie chart. The visualization unit can also visually display the distribution of grades using a heat map. For example, the visualization unit can visually display the distribution of grades for each unit using a heat map. The visualization unit can also use AI to analyze grade data and automatically visualize weak and strong units. For example, the visualization unit can use AI to analyze grade data and automatically visualize weak and strong units. In this way, the visualization unit can display weak and strong units in a graph or table based on the aggregated grades. Some or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit can input grade data to a generation AI and have the generation AI visualize the grades.

[0036] The advice unit can provide advice on how to proceed with studies based on the visualized data. For example, the advice unit can provide advice such as "Let's review this unit intensively" for a unit that the student is weak at. The advice unit can also provide advice such as "Let's study this unit more in depth" for a unit that the student is strong at. For example, the advice unit can provide advice such as "Let's study this unit more in depth" for a unit that the student is strong at. The advice unit can also use AI to analyze the grade data and propose an individual study plan. For example, the advice unit can use AI to analyze the grade data and propose an individual study plan. This allows the advice unit to provide advice on how to proceed with studies based on the visualized data. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the grade data into a generation AI and have the generation AI provide advice on how to proceed with studies.

[0037] The scanning unit can automatically adjust optimal scan settings depending on the type and format of the test paper when scanning. For example, in the case of a multiple-choice test paper, the scanning unit can increase the resolution to accurately read the position of the marks. Furthermore, in the case of a handwritten test paper, the scanning unit can set appropriate scan settings to improve the accuracy of handwritten character recognition. For example, in the case of a handwritten test paper, the scanning unit can set appropriate scan settings to improve the accuracy of handwritten character recognition. Furthermore, in the case of a multi-page test paper, the scanning unit can automatically recognize the page order and scan the test paper. For example, in the case of a multi-page test paper, the scanning unit can automatically recognize the page order and scan the test paper. This allows the scanning unit to automatically adjust optimal scan settings depending on the type and format of the test paper. Some or all of the above-mentioned processing in the scanning unit may be performed using, or without, AI. For example, the scanning unit can input the type and format of the test paper into a generation AI, causing the generation AI to automatically adjust optimal scan settings.

[0038] The scanning unit can detect the condition of the paper (e.g., creases or stains) during scanning and make corrections to improve scan quality. For example, the scanning unit can detect folded portions and make corrections using image processing technology. The scanning unit can also detect stains or blemishes and remove them from the scanned image. For example, the scanning unit can detect stains or blemishes and remove them from the scanned image. The scanning unit can also detect paper distortion and correct the scanned image to obtain accurate data. For example, the scanning unit can detect paper distortion and correct the scanned image to obtain accurate data. This allows the scanning unit to detect the condition of the paper and make corrections to improve scan quality. Some or all of the above-described processing in the scanning unit may be performed using, or without, AI. For example, the scanning unit can input paper condition data to a generation AI and have the generation AI correct the scan quality.

[0039] The scanning unit can select optimal scan settings during scanning by taking into account the user's geographical location information. For example, if the user is in a high-humidity area, the scanning unit can adjust the scan settings by taking into account deformation of paper due to humidity. Furthermore, if the user is in a high-temperature area, the scanning unit can adjust the scan settings by taking into account deformation of paper due to heat. For example, if the user is in a high-temperature area, the scanning unit can adjust the scan settings by taking into account deformation of paper due to heat. Furthermore, if the user is in a low-temperature area, the scanning unit can adjust the scan settings by taking into account hardening of paper. For example, if the user is in a low-temperature area, the scanning unit can adjust the scan settings by taking into account hardening of paper. This allows the scanning unit to select optimal scan settings by taking into account the user's geographical location information. Some or all of the above-described processing in the scanning unit may be performed using, for example, AI, or may be performed without using AI. For example, the scanning unit can input the user's geographical location information into the generation AI, causing the generation AI to select optimal scan settings.

[0040] When scanning, the scanning unit can suggest optimal scan settings by referring to the user's past scan history. For example, if the user previously scanned at high resolution, the scanning unit can suggest similar settings. Furthermore, if the user previously scanned at low resolution, the scanning unit can suggest similar settings. For example, if the user previously scanned at low resolution, the scanning unit can suggest similar settings. Furthermore, if the user previously scanned in a specific format, the scanning unit can suggest similar settings. For example, if the user previously scanned in a specific format, the scanning unit can suggest similar settings. This allows the scanning unit to suggest optimal scan settings by referring to the user's past scan history. Some or all of the above-described processing in the scanning unit may be performed using, or without, AI. For example, the scanning unit can input the user's past scan history into a generation AI, causing the generation AI to suggest optimal scan settings.

[0041] During analysis, the analysis unit can apply different analysis algorithms depending on the format of the test paper. For example, the analysis unit can apply an algorithm that analyzes mark positions to a multiple-choice test paper. The analysis unit can also apply a handwriting recognition algorithm to a handwritten test paper. For example, the analysis unit can apply a handwriting recognition algorithm to a handwritten test paper. The analysis unit can also apply an option analysis algorithm to a multiple-choice test paper. For example, the analysis unit can apply an option analysis algorithm to a multiple-choice test paper. This allows the analysis unit to apply different analysis algorithms depending on the format of the test paper. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input test paper format data to a generation AI, causing the generation AI to apply the optimal analysis algorithm.

[0042] During analysis, the analysis unit can improve the accuracy of the analysis by taking into account the difficulty of each problem. For example, the analysis unit can perform a more detailed analysis on a high-difficulty problem. Furthermore, the analysis unit can perform a quick analysis on a low-difficulty problem. For example, the analysis unit can perform a quick analysis on a low-difficulty problem. Furthermore, the analysis unit can adjust parameters of the analysis algorithm according to the difficulty of each problem. For example, the analysis unit can adjust parameters of the analysis algorithm according to the difficulty of each problem. This allows the analysis unit to improve the accuracy of the analysis by taking into account the difficulty of each problem. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input difficulty data of the problem to a generation AI, and the generation AI can improve the accuracy of the analysis.

[0043] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past performance data. The analysis unit can, for example, adjust parameters of the analysis algorithm based on the user's past performance data. The analysis unit can also improve the analysis accuracy for a specific problem by referring to the user's past performance data. For example, the analysis unit can improve the analysis accuracy for a specific problem by referring to the user's past performance data. The analysis unit can also improve the reliability of the analysis results based on the user's past performance data. For example, the analysis unit can improve the reliability of the analysis results based on the user's past performance data. This allows the analysis unit to improve the accuracy of the analysis by referring to the user's past performance data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past performance data into a generation AI, and the generation AI can improve the accuracy of the analysis.

[0044] During analysis, the analysis unit can determine the priority of analysis based on the submission date of the test paper. For example, the analysis unit can prioritize analysis of test papers with an upcoming submission deadline. The analysis unit can also postpone analysis of test papers with a more distant submission deadline. For example, the analysis unit can postpone analysis of test papers with a more distant submission deadline. The analysis unit can also adjust the analysis schedule based on the submission date. For example, the analysis unit can adjust the analysis schedule based on the submission date. This allows the analysis unit to determine the priority of analysis based on the submission date of the test paper. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input submission date data into a generation AI and have the generation AI determine the priority of analysis.

[0045] When generating comments, the comment generation unit can adjust the level of detail of the comments based on the importance of each question. For example, the comment generation unit can generate detailed comments for important questions. Furthermore, the comment generation unit can generate concise comments for questions of low importance. For example, the comment generation unit can generate concise comments for questions of low importance. Furthermore, the comment generation unit can adjust the length and content of the comments according to the importance of each question. For example, the comment generation unit can adjust the length and content of the comments according to the importance of each question. This allows the comment generation unit to adjust the level of detail of the comments based on the importance of each question. Some or all of the above-described processing in the comment generation unit may be performed using, or without, AI. For example, the comment generation unit can input question importance data into a generation AI and have the generation AI adjust the level of detail of the comments.

[0046] When generating a comment, the comment generation unit can generate an individually customized comment by referring to the user's past answer history. For example, the comment generation unit can generate a comment including specific advice for a question that the user answered incorrectly in the past. The comment generation unit can also generate a comment including words of encouragement based on the user's past answer history. For example, the comment generation unit can generate a comment including words of encouragement based on the user's past answer history. The comment generation unit can also generate a detailed comment for a specific question by referring to the user's past answer history. For example, the comment generation unit can generate a detailed comment for a specific question by referring to the user's past answer history. This allows the comment generation unit to generate an individually customized comment by referring to the user's past answer history. Some or all of the above-described processing in the comment generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the comment generation unit can input the user's past answer history data into a generation AI and cause the generation AI to generate an individually customized comment.

[0047] The comment generation unit can apply different comment formats depending on the user's learning style when generating comments. For example, the comment generation unit can generate comments including diagrams and tables for a user with a visual learning style. The comment generation unit can also generate audio comments for a user with an auditory learning style. For example, the comment generation unit can generate audio comments for a user with an auditory learning style. The comment generation unit can also generate comments suggesting specific actions for a user with a tactile learning style. For example, the comment generation unit can generate comments suggesting specific actions for a user with a tactile learning style. This allows the comment generation unit to apply different comment formats depending on the user's learning style. Some or all of the above-described processing in the comment generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the comment generation unit can input the user's learning style data into a generation AI and cause the generation AI to apply different comment formats.

[0048] When generating a comment, the comment generation unit can use expressions specific to the region by taking into account the user's geographical location information. For example, if the user is in a specific region, the comment generation unit can generate a comment using a dialect of that region. Furthermore, if the user is in a specific cultural sphere, the comment generation unit can use expressions that are tailored to that culture. For example, if the user is in a specific cultural sphere, the comment generation unit can use expressions that are tailored to that culture. Furthermore, if the user is in a specific country, the comment generation unit can generate a comment in the language of that country. For example, if the user is in a specific country, the comment generation unit can generate a comment in the language of that country. This allows the comment generation unit to use expressions specific to the region by taking into account the user's geographical location information. Some or all of the above-described processing in the comment generation unit may be performed using AI, for example, or may be performed without using AI. For example, the comment generation unit can input the user's geographical location information to a generation AI and cause the generation AI to use expressions specific to the region.

[0049] The output unit can customize the printout format according to the user's preferences at the time of output. For example, if the user prefers a simple format, the output unit can print out a simple layout. Furthermore, if the user prefers a detailed format, the output unit can print out a layout including detailed information. For example, if the user prefers a detailed format, the output unit can print out a layout including detailed information. Furthermore, if the user prefers a visual format, the output unit can print out a layout that makes extensive use of graphs and diagrams. For example, if the user prefers a visual format, the output unit can print out a layout that makes extensive use of graphs and diagrams. This allows the output unit to customize the printout format according to the user's preferences. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user preference data into a generation AI and have the generation AI customize the printout format.

[0050] The output unit can automatically adjust optimal print settings according to the type and size of paper at the time of output. For example, the output unit can apply standard print settings to A4-sized paper. Furthermore, the output unit can apply print settings using large fonts and graphics to A3-sized paper. For example, the output unit can apply print settings using large fonts and graphics to A3-sized paper. Furthermore, the output unit can apply print settings suited to the characteristics of special paper. For example, the output unit can apply print settings suited to the characteristics of special paper. This allows the output unit to automatically adjust optimal print settings according to the type and size of paper. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input paper type and size data to a generation AI, causing the generation AI to automatically adjust optimal print settings.

[0051] The output unit can select the optimal output format at the time of output, taking into account the user's device information. For example, if the user is using a smartphone, the output unit can provide an output format that matches the screen size. Furthermore, if the user is using a tablet, the output unit can provide an output format optimized for a large screen. For example, if the user is using a tablet, the output unit can provide an output format optimized for a large screen. Furthermore, if the user is using a personal computer, the output unit can provide a high-resolution output format. For example, if the user is using a personal computer, the output unit can provide a high-resolution output format. This allows the output unit to select the optimal output format taking into account the user's device information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's device information to a generation AI, causing the generation AI to select the optimal output format.

[0052] At the time of output, the output unit can suggest optimal output settings by referring to the user's past output history. For example, the output unit can suggest similar settings based on an output format used by the user in the past. The output unit can also suggest an optimal format from the user's past output history. For example, the output unit can suggest an optimal format from the user's past output history. The output unit can also analyze the user's past output history and suggest the most efficient output settings. For example, the output unit can analyze the user's past output history and suggest the most efficient output settings. This allows the output unit to suggest optimal output settings by referring to the user's past output history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past output history data to a generation AI, causing the generation AI to suggest optimal output settings.

[0053] The tallying unit can weight the scores taking into account the difficulty of each question when tallying the scores. For example, the tallying unit can assign a high weight to a question of high difficulty. Furthermore, the tallying unit can assign a low weight to a question of low difficulty. For example, the tallying unit can assign a low weight to a question of low difficulty. Furthermore, the tallying unit can adjust the weighting of the scores according to the difficulty of each question. For example, the tallying unit can adjust the weighting of the scores according to the difficulty of each question. In this way, the tallying unit can weight the scores taking into account the difficulty of each question. Some or all of the above-mentioned processing in the tallying unit may be performed using, for example, AI, or may be performed without using AI. For example, the tallying unit can input difficulty data of the questions to a generation AI and have the generation AI weight the scores.

[0054] The tallying unit can improve the accuracy of the tallying by referring to the user's past performance data during tallying. For example, the tallying unit can adjust parameters of the tallying algorithm based on the user's past performance data. The tallying unit can also improve the accuracy of the tallying for a specific problem by referring to the user's past performance data. For example, the tallying unit can improve the accuracy of the tallying for a specific problem by referring to the user's past performance data. The tallying unit can also improve the reliability of the tallying results based on the user's past performance data. For example, the tallying unit can improve the reliability of the tallying results based on the user's past performance data. This allows the tallying unit to improve the accuracy of the tallying by referring to the user's past performance data. Some or all of the above-described processing in the tallying unit may be performed using, for example, AI, or may be performed without using AI. For example, the tallying unit can input the user's past performance data into a generation AI, which can improve the accuracy of the tallying.

[0055] The tallying unit can apply different tallying formats depending on the user's learning style when tallying the data. For example, the tallying unit can provide a tallying format that makes extensive use of graphs and diagrams to a user with a visual learning style. The tallying unit can also provide audio tallying results to a user with an auditory learning style. For example, the tallying unit can provide audio tallying results to a user with an auditory learning style. The tallying unit can also provide a tallying format that suggests specific actions to a user with a tactile learning style. For example, the tallying unit can provide a tallying format that suggests specific actions to a user with a tactile learning style. This allows the tallying unit to apply different tallying formats depending on the user's learning style. Some or all of the above-described processing in the tallying unit may be performed using, or without, AI. For example, the tallying unit can input the user's learning style data into a generation AI and have the generation AI apply different tallying formats.

[0056] When performing the calculations, the calculation unit can use a calculation method specific to a region, taking into account the user's geographical location information. For example, if the user is in a specific region, the calculation unit can use a calculation method tailored to the educational curriculum of that region. Furthermore, if the user is in a specific cultural sphere, the calculation unit can use a calculation method tailored to the culture. For example, if the user is in a specific cultural sphere, the calculation unit can use a calculation method tailored to the culture. Furthermore, if the user is in a specific country, the calculation unit can use a calculation method tailored to the education system of that country. For example, if the user is in a specific country, the calculation unit can use a calculation method tailored to the education system of that country. This allows the calculation unit to use a calculation method specific to a region, taking into account the user's geographical location information. Some or all of the above-described processing in the calculation unit may be performed using AI, for example, or may be performed without using AI. For example, the calculation unit can input the user's geographical location information to the generation AI, causing the generation AI to use a calculation method specific to the region.

[0057] The visualization unit can adjust the level of detail of the display based on the importance of each question during visualization. For example, the visualization unit can provide a detailed display for important questions. Furthermore, the visualization unit can provide a concise display for questions of low importance. For example, the visualization unit can provide a concise display for questions of low importance. Furthermore, the visualization unit can adjust the level of detail of the display according to the importance of each question. For example, the visualization unit can adjust the level of detail of the display according to the importance of each question. In this way, the visualization unit can adjust the level of detail of the display based on the importance of each question. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input question importance data to a generation AI and have the generation AI adjust the level of detail of the display.

[0058] During visualization, the visualization unit can provide an individually customized display by referring to the user's past performance data. For example, the visualization unit can provide a detailed display for a specific problem based on the user's past performance data. The visualization unit can also provide a display including words of encouragement by referring to the user's past performance data. For example, the visualization unit can provide a display including words of encouragement by referring to the user's past performance data. The visualization unit can also provide a visually easy-to-understand display based on the user's past performance data. For example, the visualization unit can provide a visually easy-to-understand display based on the user's past performance data. This allows the visualization unit to provide an individually customized display by referring to the user's past performance data. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input the user's past performance data to a generation AI and cause the generation AI to provide an individually customized display.

[0059] The visualization unit can apply different display formats depending on the user's learning style when visualizing. For example, the visualization unit can provide a display format that makes extensive use of graphs and diagrams to a user with a visual learning style. The visualization unit can also provide an audio display to a user with an auditory learning style. For example, the visualization unit can provide an audio display to a user with an auditory learning style. The visualization unit can also provide a display format that suggests specific actions to a user with a tactile learning style. For example, the visualization unit can provide a display format that suggests specific actions to a user with a tactile learning style. This allows the visualization unit to apply different display formats depending on the user's learning style. Some or all of the above-described processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit can input the user's learning style data to a generation AI and cause the generation AI to apply different display formats.

[0060] When performing visualization, the visualization unit can use a region-specific display method by taking into account the user's geographical location information. For example, if the user is in a specific region, the visualization unit can use a display method tailored to the educational curriculum of that region. Furthermore, if the user is in a specific cultural sphere, the visualization unit can use a display method tailored to the culture. For example, if the user is in a specific cultural sphere, the visualization unit can use a display method tailored to the culture. Furthermore, if the user is in a specific country, the visualization unit can use a display method tailored to the education system of that country. For example, if the user is in a specific country, the visualization unit can use a display method tailored to the education system of that country. This allows the visualization unit to use a region-specific display method by taking into account the user's geographical location information. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input the user's geographical location information to the generation AI and cause the generation AI to use a region-specific display method.

[0061] When providing advice, the advice unit can adjust the level of detail of the advice based on the importance of each problem. For example, the advice unit can provide detailed advice for important problems. Furthermore, the advice unit can provide concise advice for low-importance problems. For example, the advice unit can provide concise advice for low-importance problems. Furthermore, the advice unit can adjust the length and content of the advice based on the importance of each problem. For example, the advice unit can adjust the length and content of the advice based on the importance of each problem. This allows the advice unit to adjust the level of detail of the advice based on the importance of each problem. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input problem importance data to a generation AI and have the generation AI adjust the level of detail of the advice.

[0062] When giving advice, the advice unit can provide individually customized advice by referring to the user's past performance data. For example, the advice unit can provide specific advice for a problem that the user answered incorrectly in the past. The advice unit can also provide advice including encouraging words based on the user's past performance data. For example, the advice unit can provide advice including encouraging words based on the user's past performance data. The advice unit can also provide detailed advice for a specific problem by referring to the user's past performance data. For example, the advice unit can provide detailed advice for a specific problem by referring to the user's past performance data. This allows the advice unit to provide individually customized advice by referring to the user's past performance data. Some or all of the above-described processing in the advice unit may be performed using, or without, an AI. For example, the advice unit can input the user's past performance data into a generation AI and cause the generation AI to provide individually customized advice.

[0063] When providing advice, the advice unit can apply different advice formats depending on the user's learning style. For example, the advice unit can provide advice including diagrams and tables to a user with a visual learning style. The advice unit can also provide audio advice to a user with an auditory learning style. For example, the advice unit can provide audio advice to a user with an auditory learning style. The advice unit can also provide advice suggesting specific actions to a user with a tactile learning style. For example, the advice unit can provide advice suggesting specific actions to a user with a tactile learning style. This allows the advice unit to apply different advice formats depending on the user's learning style. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the user's learning style data to a generation AI and cause the generation AI to apply different advice formats.

[0064] When providing advice, the advice unit can provide region-specific advice taking into account the user's geographical location information. For example, if the user is in a specific region, the advice unit can provide advice tailored to the educational curriculum of that region. Furthermore, if the user is in a specific cultural sphere, the advice unit can provide advice tailored to that culture. For example, if the user is in a specific cultural sphere, the advice unit can provide advice tailored to that culture. Furthermore, if the user is in a specific country, the advice unit can provide advice tailored to the country's educational system. For example, if the user is in a specific country, the advice unit can provide advice tailored to the country's educational system. This allows the advice unit to provide region-specific advice taking into account the user's geographical location information. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the user's geographical location information to a generation AI and cause the generation AI to provide region-specific advice.

[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 scanning unit can detect the condition of the paper (e.g., creases or stains) during scanning and make corrections to improve scan quality. For example, it can detect folded parts and correct them using image processing technology. It can also detect stains and blemishes and remove them from the scanned image. It can also detect paper distortion and correct the scanned image to obtain accurate data. This allows the scanning unit to detect the condition of the paper and make corrections to improve scan quality. Some or all of the above-mentioned processing in the scanning unit may be performed using, for example, AI, or may be performed without using AI. For example, the scanning unit can input paper condition data into a generation AI and have the generation AI correct the scan quality.

[0067] The output unit can customize the printout format according to the user's preferences at the time of output. For example, if the user prefers a simple format, a simple layout can be printed out. If the user prefers a detailed format, a layout including detailed information can be printed out. Furthermore, if the user prefers a visual format, a layout making extensive use of graphs and diagrams can be printed out. This allows the output unit to customize the printout format according to the user's preferences. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user preference data into a generation AI and have the generation AI customize the printout format.

[0068] The visualization unit can adjust the level of detail of the display based on the importance of each question during visualization. For example, important questions can be displayed in detail. Meanwhile, questions of low importance can be displayed in a concise manner. Furthermore, the level of detail of the display can be adjusted according to the importance of each question. This allows the visualization unit to adjust the level of detail of the display based on the importance of each question. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input question importance data to a generation AI and have the generation AI adjust the level of detail of the display.

[0069] The scanning unit can automatically adjust optimal scan settings depending on the type and format of the test paper when scanning. For example, in the case of a multiple-choice test paper, the resolution can be increased to accurately read the position of the marks. In addition, in the case of a handwritten test paper, appropriate scan settings can be set to improve the accuracy of handwriting recognition. Furthermore, in the case of a multi-page test paper, the page order can be automatically recognized and scanned. This allows the scanning unit to automatically adjust optimal scan settings depending on the type and format of the test paper. Some or all of the above-mentioned processing in the scanning unit may be performed using, for example, AI, or may be performed without using AI. For example, the scanning unit can input the type and format of the test paper into a generation AI, which can then automatically adjust optimal scan settings.

[0070] During analysis, the analysis unit can apply different analysis algorithms depending on the format of the test paper. For example, an algorithm that analyzes mark positions can be applied to a multiple-choice test paper. A handwriting recognition algorithm can be applied to a handwritten test paper. Furthermore, an algorithm that analyzes options can be applied to a multiple-choice test paper. This allows the analysis unit to apply different analysis algorithms depending on the format of the test paper. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input test paper format data into a generation AI, which can then apply the optimal analysis algorithm.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The scanning unit scans the test paper to obtain image data. For example, the scanning unit can use a high-resolution scanner to scan the test paper and generate image data. Alternatively, the scanning unit can use a smartphone camera to take a photo of the test paper and obtain image data. Furthermore, the scanning unit can use OCR technology to convert handwritten answers into digital data. Step 2: The analysis unit analyzes the image data acquired by the scanning unit and determines whether each question is correct or incorrect. For example, the analysis unit uses an image processing algorithm to analyze the mark positions on a multiple-choice test sheet and determine whether the answers are correct or incorrect. The analysis unit can also analyze handwritten answers and determine whether they are correct or incorrect using handwriting recognition technology. Furthermore, the analysis unit can use AI to extract text data from the image data and determine whether each question is correct or incorrect. Step 3: The comment generation unit generates comments based on the correctness of each question determined by the analysis unit. For example, the comment generation unit uses natural language processing technology to generate comments such as "Good job" if the answer is correct and "Let's review it again" if the answer is incorrect. The comment generation unit can also use a template-based generation method to generate comments based on the correctness of each question. Furthermore, the comment generation unit can use AI to generate appropriate comments based on the correctness of each question. Step 4: The output unit prints out the comments generated by the comment generation unit and the scoring results determined by the analysis unit. For example, the output unit uses a printer to print out the scoring results, including whether each question is correct or incorrect and the comments. The output unit can also save the scoring results in digital format and provide them to the user via email or a cloud service. Furthermore, the output unit can display the scoring results to the user via a web application or a mobile application. Step 5: The calculation unit compiles the grades obtained by the analysis unit and compiles grades by subject or unit. For example, the calculation unit stores the grades for each question in a database and compiles grades by subject or unit. The calculation unit can also normalize the grade data to make it easier to compare across different tests. Furthermore, the calculation unit can use AI to analyze the grade data and automatically compile grades by subject or unit. Step 6: The visualization unit displays the weak and strong units in a graph or table based on the grades compiled by the compilation unit. For example, the visualization unit uses a bar graph or pie chart to visually display the grades for each unit. The visualization unit can also visually display the distribution of grades using a heat map. Furthermore, the visualization unit can use AI to analyze the grade data and automatically visualize the weak and strong units. Step 7: The Advice Unit provides advice on how to proceed with learning based on the data visualized by the Visualization Unit. For example, the Advice Unit may provide advice such as "Let's focus on reviewing this unit" for weaker units. The Advice Unit may also provide advice such as "Let's study this unit in more depth" for stronger units. Furthermore, the Advice Unit can use AI to analyze the grade data and propose individual learning plans.

[0073] (Example 2) An automatic marking system according to an embodiment of the present invention scans test papers, automatically marks them, and prints them out with comments. This system also aggregates scores by subject and unit, visualizes weak and strong units, and provides advice on how to proceed with study. Specifically, it consists of the following steps: First, the test paper is scanned. Next, AI analyzes the scanned data and determines whether each question is correct. Then, the AI ​​automatically generates comments and prints them out along with the grading results. Furthermore, grades are aggregated by subject and unit, visualizes weak and strong units. Finally, the AI ​​provides advice on how to proceed with study. First, the test paper is scanned. In this process, the scanner acquires image data of the test paper. Next, the AI ​​analyzes the scanned data. The AI ​​analyzes the image data and determines whether each question is correct. For example, in a multiple-choice test, the position of the marks is analyzed to determine whether the question is correct. The AI ​​then automatically generates comments. The AI ​​generates appropriate comments based on the correctness of each question. For example, if the answer is correct, the system generates a comment such as "Good job!", and if the answer is incorrect, the system generates a comment such as "Let's review it again." Next, the system prints out the grading results and the comments. The printed results include the correct / incorrect status of each question and the comments. Furthermore, the system aggregates grades by subject and unit. The AI ​​aggregates the grades for each question and summarizes the grades by subject and unit. Finally, it visualizes the weak and strong units. Based on the aggregated grades, the AI ​​displays the weak and strong units in graphs and tables. This allows users to see at a glance their strong and weak areas. Furthermore, the AI ​​provides advice on how to proceed with their studies. For example, for weak units, the system provides advice such as "You should focus on reviewing this unit." This allows the automatic grading system to scan test papers, automatically grade them, and print them out with comments. Furthermore, by aggregating grades by subject and unit and visualizing the strong and weak units, the system can provide users with appropriate advice on how to proceed with their studies.

[0074] The automatic marking system according to the embodiment includes a scanning unit, an analysis unit, a comment generation unit, an output unit, a tallying unit, a visualization unit, and an advice unit. The scanning unit scans a test paper to acquire image data. For example, the scanning unit can use a high-resolution scanner to scan the test paper and generate image data. The scanning unit can also use a smartphone camera to photograph the test paper and acquire image data. The scanning unit can also convert handwritten answers into digital data using OCR technology. The analysis unit analyzes the image data acquired by the scanning unit and determines whether each question is correct. For example, the analysis unit can use an image processing algorithm to analyze the mark positions in a multiple-choice test and determine whether the answer is correct. The analysis unit can also analyze handwritten answers and determine whether the answer is correct using handwriting recognition technology. The analysis unit can also use AI to extract text data from the image data and determine whether each question is correct. The comment generation unit generates comments based on the correctness of each question determined by the analysis unit. For example, the comment generation unit uses natural language processing technology to generate comments such as "Good job" for correct answers and "Let's review it again" for incorrect answers. The comment generation unit can also use a template-based generation method to generate comments based on the correctness of each question. Furthermore, the comment generation unit can use AI to generate appropriate comments based on the correctness of each question. The output unit prints out the comments generated by the comment generation unit and the grading results determined by the analysis unit. For example, the output unit uses a printer to print the grading results, including the correctness of each question and comments. The output unit can also save the grading results in digital format and provide them to users via email or a cloud service. Furthermore, the output unit can display the grading results to users via a web application or a mobile application. The compilation unit tallys the grades obtained by the analysis unit and compiles grades by subject or unit. For example, the compilation unit stores the grades for each question in a database and tallys grades by subject or unit.The tallying unit can also normalize the grade data to facilitate comparison between different tests. Furthermore, the tallying unit can use AI to analyze the grade data and automatically tally grades for each subject or unit. The visualization unit displays weak and strong units in graphs and tables based on the grades tallied by the tallying unit. For example, the visualization unit can visually display grades for each unit using bar graphs or pie charts. The visualization unit can also visually display the distribution of grades using heat maps. Furthermore, the visualization unit can analyze the grade data using AI and automatically visualize weak and strong units. The advice unit provides advice on how to proceed with studies based on the data visualized by the visualization unit. For example, the advice unit can provide advice such as "Focus on reviewing this unit" for weak units. Furthermore, the advice unit can provide advice such as "Study this unit in more depth" for strong units. Furthermore, the advice unit can analyze the grade data and propose individual study plans using AI. As a result, the automatic marking system according to the embodiment can scan test papers, automatically mark them, and print them out with comments. Furthermore, by tallying up grades by subject and unit, and visualizing weak and strong units, the system can provide appropriate advice to users on how to proceed with their studies.

[0075] The scanning unit can acquire image data of the test paper. For example, the scanning unit can scan the test paper with a scanner and save the image data. The scanning unit can also capture a photo of the test paper using a smartphone camera and acquire the image data. For example, the scanning unit can capture a photo of the test paper using a smartphone camera and acquire the image data using a dedicated app. The scanning unit can also write a handwritten answer sheet with a dedicated digital pen, which converts the answer sheet into digital data in real time. For example, the scanning unit can detect the movement of the digital pen with a sensor and save it as character data. This allows the scanning unit to accurately acquire image data of the test paper. Some or all of the above-mentioned processing in the scanning unit may be performed using, for example, AI, or may be performed without AI. For example, the scanning unit can input the image data acquired by scanning the test paper into a generation AI and have the generation AI generate text data from the image data.

[0076] The analysis unit can analyze the image data and determine whether each question is correct. For example, the analysis unit can use an image processing algorithm to analyze the mark positions on a multiple-choice test and determine whether the answer is correct. The analysis unit can also analyze handwritten answers and determine whether the answer is correct using handwritten character recognition technology. For example, the analysis unit can use handwritten character recognition technology to convert the characters on a handwritten answer into digital data and determine whether the answer is correct. The analysis unit can also use AI to extract text data from the image data and determine whether each question is correct. For example, the analysis unit can use AI to analyze the image data and determine whether each question is correct. This allows the analysis unit to accurately determine whether each question is correct. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input the image data to a generation AI and have the generation AI determine whether the answer is correct.

[0077] The comment generation unit can generate comments based on the correctness of each question. For example, the comment generation unit can use natural language processing technology to generate comments such as "Good job" for a correct answer and "Let's review it again" for an incorrect answer. The comment generation unit can also use a template-based generation method to generate comments based on the correctness of each question. For example, the comment generation unit can use the template-based generation method to generate comments such as "Great" for a correct answer and "Try harder next time" for an incorrect answer. The comment generation unit can also use AI to generate appropriate comments based on the correctness of each question. For example, the comment generation unit can use AI to generate comments including individual feedback based on the correctness of each question. This allows the comment generation unit to generate appropriate comments based on the correctness of each question. Some or all of the above-described processing in the comment generation unit may be performed using AI, or may be performed without AI. For example, the comment generation unit can input correct / incorrect data to a generation AI and have the generation AI generate comments.

[0078] The output unit can print out comments along with the scoring results. The output unit can print the scoring results, including the correct / incorrect answers and comments for each question, using, for example, a printer. The output unit can also save the scoring results in digital format and provide them to the user via email or a cloud service. For example, the output unit can save the scoring results in PDF format and send them to the user via email. The output unit can also display the scoring results to the user via a web application or a mobile application. For example, the output unit can allow the user to check the scoring results online via a web application. This allows the output unit to print out the scoring results and comments. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the scoring results and comments to a generation AI, which can then generate a printout format.

[0079] The tallying unit can tally the grades for each question and compile grades by subject or unit. The tallying unit can, for example, store the grades for each question in a database and tally the grades by subject or unit. The tallying unit can also normalize the grade data to facilitate comparison between different tests. For example, the tallying unit can normalize the grade data to uniformly compare grades for different tests. The tallying unit can also use AI to analyze the grade data and automatically tally the grades for each subject or unit. For example, the tallying unit can use AI to analyze the grade data and automatically tally the grades for each subject or unit. This allows the tallying unit to tally the grades for each question and compile grades by subject or unit. Some or all of the above-mentioned processing in the tallying unit may be performed using AI, for example, or may be performed without using AI. For example, the tallying unit can input the grade data to a generation AI and have the generation AI tally the grades.

[0080] The visualization unit can display weak and strong units in a graph or table based on the aggregated grades. The visualization unit can visually display the grades for each unit using, for example, a bar graph or a pie chart. The visualization unit can also visually display the distribution of grades using a heat map. For example, the visualization unit can visually display the distribution of grades for each unit using a heat map. The visualization unit can also use AI to analyze grade data and automatically visualize weak and strong units. For example, the visualization unit can use AI to analyze grade data and automatically visualize weak and strong units. In this way, the visualization unit can display weak and strong units in a graph or table based on the aggregated grades. Some or all of the above-mentioned processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit can input grade data to a generation AI and have the generation AI visualize the grades.

[0081] The advice unit can provide advice on how to proceed with studies based on the visualized data. For example, the advice unit can provide advice such as "Let's review this unit intensively" for a unit that the student is weak at. The advice unit can also provide advice such as "Let's study this unit more in depth" for a unit that the student is strong at. For example, the advice unit can provide advice such as "Let's study this unit more in depth" for a unit that the student is strong at. The advice unit can also use AI to analyze the grade data and propose an individual study plan. For example, the advice unit can use AI to analyze the grade data and propose an individual study plan. This allows the advice unit to provide advice on how to proceed with studies based on the visualized data. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the grade data into a generation AI and have the generation AI provide advice on how to proceed with studies.

[0082] The scanning unit can estimate the user's emotions and adjust the timing of scanning based on the estimated user's emotions. For example, if the user is feeling stressed, the scanning unit can delay the timing of scanning to provide time for relaxation. Furthermore, if the user is relaxed, the scanning unit can speed up the timing of scanning to efficiently proceed with work. For example, if the user is relaxed, the scanning unit can speed up the timing of scanning to efficiently proceed with work. Furthermore, if the user is in a hurry, the scanning unit can quickly perform scanning to quickly provide results. For example, if the user is in a hurry, the scanning unit can quickly perform scanning to quickly provide results. This allows the scanning unit to adjust the timing of scanning according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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. Some or all of the above-mentioned processing in the scanning unit may be performed using, for example, AI, or without AI. For example, the scanning unit can input the user's emotional data into the generation AI, which can then adjust the timing of the scan.

[0083] The scanning unit can automatically adjust optimal scan settings depending on the type and format of the test paper when scanning. For example, in the case of a multiple-choice test paper, the scanning unit can increase the resolution to accurately read the position of the marks. Furthermore, in the case of a handwritten test paper, the scanning unit can set appropriate scan settings to improve the accuracy of handwritten character recognition. For example, in the case of a handwritten test paper, the scanning unit can set appropriate scan settings to improve the accuracy of handwritten character recognition. Furthermore, in the case of a multi-page test paper, the scanning unit can automatically recognize the page order and scan the test paper. For example, in the case of a multi-page test paper, the scanning unit can automatically recognize the page order and scan the test paper. This allows the scanning unit to automatically adjust optimal scan settings depending on the type and format of the test paper. Some or all of the above-mentioned processing in the scanning unit may be performed using, or without, AI. For example, the scanning unit can input the type and format of the test paper into a generation AI, causing the generation AI to automatically adjust optimal scan settings.

[0084] The scanning unit can detect the condition of the paper (e.g., creases or stains) during scanning and make corrections to improve scan quality. For example, the scanning unit can detect folded portions and make corrections using image processing technology. The scanning unit can also detect stains or blemishes and remove them from the scanned image. For example, the scanning unit can detect stains or blemishes and remove them from the scanned image. The scanning unit can also detect paper distortion and correct the scanned image to obtain accurate data. For example, the scanning unit can detect paper distortion and correct the scanned image to obtain accurate data. This allows the scanning unit to detect the condition of the paper and make corrections to improve scan quality. Some or all of the above-described processing in the scanning unit may be performed using, or without, AI. For example, the scanning unit can input paper condition data to a generation AI and have the generation AI correct the scan quality.

[0085] The scanning unit can estimate the user's emotions and adjust the scanning resolution based on the estimated user's emotions. For example, if the user is relaxed, the scanning unit can perform a scan at standard resolution. Furthermore, if the user is in a hurry, the scanning unit can perform a scan at low resolution to quickly provide results. For example, if the user is in a hurry, the scanning unit can perform a scan at low resolution to quickly provide results. Furthermore, if the user requires detailed results, the scanning unit can perform a scan at high resolution to provide highly accurate data. For example, if the user requires detailed results, the scanning unit can perform a scan at high resolution to provide highly accurate data. This allows the scanning unit to adjust the scanning resolution according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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. Some or all of the above-described processing in the scanning unit can be performed using, for example, AI, or without AI. For example, the scanning unit can input the user's emotional data into the generation AI, which can then adjust the resolution of the scan.

[0086] The scanning unit can select optimal scan settings during scanning by taking into account the user's geographical location information. For example, if the user is in a high-humidity area, the scanning unit can adjust the scan settings by taking into account deformation of paper due to humidity. Furthermore, if the user is in a high-temperature area, the scanning unit can adjust the scan settings by taking into account deformation of paper due to heat. For example, if the user is in a high-temperature area, the scanning unit can adjust the scan settings by taking into account deformation of paper due to heat. Furthermore, if the user is in a low-temperature area, the scanning unit can adjust the scan settings by taking into account hardening of paper. For example, if the user is in a low-temperature area, the scanning unit can adjust the scan settings by taking into account hardening of paper. This allows the scanning unit to select optimal scan settings by taking into account the user's geographical location information. Some or all of the above-described processing in the scanning unit may be performed using, for example, AI, or may be performed without using AI. For example, the scanning unit can input the user's geographical location information into the generation AI, causing the generation AI to select optimal scan settings.

[0087] When scanning, the scanning unit can suggest optimal scan settings by referring to the user's past scan history. For example, if the user previously scanned at high resolution, the scanning unit can suggest similar settings. Furthermore, if the user previously scanned at low resolution, the scanning unit can suggest similar settings. For example, if the user previously scanned at low resolution, the scanning unit can suggest similar settings. Furthermore, if the user previously scanned in a specific format, the scanning unit can suggest similar settings. For example, if the user previously scanned in a specific format, the scanning unit can suggest similar settings. This allows the scanning unit to suggest optimal scan settings by referring to the user's past scan history. Some or all of the above-described processing in the scanning unit may be performed using, or without, AI. For example, the scanning unit can input the user's past scan history into a generation AI, causing the generation AI to suggest optimal scan settings.

[0088] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user's emotions. For example, if the user is stressed, the analysis unit can start the analysis with easy questions. Furthermore, if the user is relaxed, the analysis unit can start the analysis with more difficult questions. For example, if the user is relaxed, the analysis unit can start the analysis with more difficult questions. Furthermore, if the user is in a hurry, the analysis unit can start the analysis with more important questions. This allows the analysis unit to determine the analysis priority according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, 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. Some or all of the above-described processing in the analysis unit may be performed using AI, or may be performed without AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI determine the analysis priority.

[0089] During analysis, the analysis unit can apply different analysis algorithms depending on the format of the test paper. For example, the analysis unit can apply an algorithm that analyzes mark positions to a multiple-choice test paper. The analysis unit can also apply a handwriting recognition algorithm to a handwritten test paper. For example, the analysis unit can apply a handwriting recognition algorithm to a handwritten test paper. The analysis unit can also apply an option analysis algorithm to a multiple-choice test paper. For example, the analysis unit can apply an option analysis algorithm to a multiple-choice test paper. This allows the analysis unit to apply different analysis algorithms depending on the format of the test paper. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input test paper format data to a generation AI, causing the generation AI to apply the optimal analysis algorithm.

[0090] During analysis, the analysis unit can improve the accuracy of the analysis by taking into account the difficulty of each problem. For example, the analysis unit can perform a more detailed analysis on a high-difficulty problem. Furthermore, the analysis unit can perform a quick analysis on a low-difficulty problem. For example, the analysis unit can perform a quick analysis on a low-difficulty problem. Furthermore, the analysis unit can adjust parameters of the analysis algorithm according to the difficulty of each problem. For example, the analysis unit can adjust parameters of the analysis algorithm according to the difficulty of each problem. This allows the analysis unit to improve the accuracy of the analysis by taking into account the difficulty of each problem. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input difficulty data of the problem to a generation AI, and the generation AI can improve the accuracy of the analysis.

[0091] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method including detailed information. For example, if the user is relaxed, the analysis unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. For example, if the user is in a hurry, the analysis unit can provide a display method that focuses on the main points. This allows the analysis unit to adjust the display method of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method of the analysis results.

[0092] During analysis, the analysis unit can improve the accuracy of the analysis by referring to the user's past performance data. The analysis unit can, for example, adjust parameters of the analysis algorithm based on the user's past performance data. The analysis unit can also improve the analysis accuracy for a specific problem by referring to the user's past performance data. For example, the analysis unit can improve the analysis accuracy for a specific problem by referring to the user's past performance data. The analysis unit can also improve the reliability of the analysis results based on the user's past performance data. For example, the analysis unit can improve the reliability of the analysis results based on the user's past performance data. This allows the analysis unit to improve the accuracy of the analysis by referring to the user's past performance data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the user's past performance data into a generation AI, and the generation AI can improve the accuracy of the analysis.

[0093] During analysis, the analysis unit can determine the priority of analysis based on the submission date of the test paper. For example, the analysis unit can prioritize analysis of test papers with an upcoming submission deadline. The analysis unit can also postpone analysis of test papers with a more distant submission deadline. For example, the analysis unit can postpone analysis of test papers with a more distant submission deadline. The analysis unit can also adjust the analysis schedule based on the submission date. For example, the analysis unit can adjust the analysis schedule based on the submission date. This allows the analysis unit to determine the priority of analysis based on the submission date of the test paper. Some or all of the above-mentioned processing in the analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the analysis unit can input submission date data into a generation AI and have the generation AI determine the priority of analysis.

[0094] The comment generation unit can estimate the user's emotions and adjust the way the comment is expressed based on the estimated user's emotions. For example, if the user is relaxed, the comment generation unit can use more positive expressions. Furthermore, if the user is feeling stressed, the comment generation unit can include more encouraging words. For example, if the user is feeling stressed, the comment generation unit can include more encouraging words. Furthermore, if the user is in a hurry, the comment generation unit can generate comments that are concise and to the point. For example, if the user is in a hurry, the comment generation unit can generate comments that are concise and to the point. This allows the comment generation unit to adjust the way the comment is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-described processing in the comment generation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the comment generation unit can input the user's emotional data into the generation AI, and have the generation AI adjust the way the comment is expressed.

[0095] When generating comments, the comment generation unit can adjust the level of detail of the comments based on the importance of each question. For example, the comment generation unit can generate detailed comments for important questions. Furthermore, the comment generation unit can generate concise comments for questions of low importance. For example, the comment generation unit can generate concise comments for questions of low importance. Furthermore, the comment generation unit can adjust the length and content of the comments according to the importance of each question. For example, the comment generation unit can adjust the length and content of the comments according to the importance of each question. This allows the comment generation unit to adjust the level of detail of the comments based on the importance of each question. Some or all of the above-described processing in the comment generation unit may be performed using, or without, AI. For example, the comment generation unit can input question importance data into a generation AI and have the generation AI adjust the level of detail of the comments.

[0096] When generating a comment, the comment generation unit can generate an individually customized comment by referring to the user's past answer history. For example, the comment generation unit can generate a comment including specific advice for a question that the user answered incorrectly in the past. The comment generation unit can also generate a comment including words of encouragement based on the user's past answer history. For example, the comment generation unit can generate a comment including words of encouragement based on the user's past answer history. The comment generation unit can also generate a detailed comment for a specific question by referring to the user's past answer history. For example, the comment generation unit can generate a detailed comment for a specific question by referring to the user's past answer history. This allows the comment generation unit to generate an individually customized comment by referring to the user's past answer history. Some or all of the above-described processing in the comment generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the comment generation unit can input the user's past answer history data into a generation AI and cause the generation AI to generate an individually customized comment.

[0097] The comment generation unit can estimate the user's emotions and adjust the length of the comment based on the estimated user's emotions. For example, the comment generation unit can generate a detailed comment when the user is relaxed. Furthermore, the comment generation unit can generate a concise comment when the user is in a hurry. For example, the comment generation unit can generate a concise comment when the user is in a hurry. Furthermore, the comment generation unit can generate a short comment including words of encouragement when the user is feeling stressed. For example, the comment generation unit can generate a short comment including words of encouragement when the user is feeling stressed. This allows the comment generation unit to adjust the length of the comment according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, 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. Some or all of the above-mentioned processing in the comment generation unit may be performed using AI, for example, or without AI. For example, the comment generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the comment.

[0098] The comment generation unit can apply different comment formats depending on the user's learning style when generating comments. For example, the comment generation unit can generate comments including diagrams and tables for a user with a visual learning style. The comment generation unit can also generate audio comments for a user with an auditory learning style. For example, the comment generation unit can generate audio comments for a user with an auditory learning style. The comment generation unit can also generate comments suggesting specific actions for a user with a tactile learning style. For example, the comment generation unit can generate comments suggesting specific actions for a user with a tactile learning style. This allows the comment generation unit to apply different comment formats depending on the user's learning style. Some or all of the above-described processing in the comment generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the comment generation unit can input the user's learning style data into a generation AI and cause the generation AI to apply different comment formats.

[0099] When generating a comment, the comment generation unit can use expressions specific to the region by taking into account the user's geographical location information. For example, if the user is in a specific region, the comment generation unit can generate a comment using a dialect of that region. Furthermore, if the user is in a specific cultural sphere, the comment generation unit can use expressions that are tailored to that culture. For example, if the user is in a specific cultural sphere, the comment generation unit can use expressions that are tailored to that culture. Furthermore, if the user is in a specific country, the comment generation unit can generate a comment in the language of that country. For example, if the user is in a specific country, the comment generation unit can generate a comment in the language of that country. This allows the comment generation unit to use expressions specific to the region by taking into account the user's geographical location information. Some or all of the above-described processing in the comment generation unit may be performed using AI, for example, or may be performed without using AI. For example, the comment generation unit can input the user's geographical location information to a generation AI and cause the generation AI to use expressions specific to the region.

[0100] The output unit can estimate the user's emotion and adjust the timing of the output based on the estimated user's emotion. For example, when the user is relaxed, the output unit can advance the timing of the output to allow the user to work efficiently. Furthermore, when the user is feeling stressed, the output unit can delay the timing of the output to provide the user with time to relax. For example, when the user is feeling stressed, the output unit can delay the timing of the output to provide the user with time to relax. Furthermore, when the user is in a hurry, the output unit can immediately timing the output to provide a result quickly. For example, when the user is in a hurry, the output unit can immediately timing the output to provide a result quickly. This allows the output unit to adjust the timing of the output according to the user's emotion. 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. Some or all of the above-mentioned processing in the output unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the output unit can input the user's emotional data into the generation AI, and have the generation AI adjust the timing of the output.

[0101] The output unit can customize the printout format according to the user's preferences at the time of output. For example, if the user prefers a simple format, the output unit can print out a simple layout. Furthermore, if the user prefers a detailed format, the output unit can print out a layout including detailed information. For example, if the user prefers a detailed format, the output unit can print out a layout including detailed information. Furthermore, if the user prefers a visual format, the output unit can print out a layout that makes extensive use of graphs and diagrams. For example, if the user prefers a visual format, the output unit can print out a layout that makes extensive use of graphs and diagrams. This allows the output unit to customize the printout format according to the user's preferences. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user preference data into a generation AI and have the generation AI customize the printout format.

[0102] The output unit can automatically adjust optimal print settings according to the type and size of paper at the time of output. For example, the output unit can apply standard print settings to A4-sized paper. Furthermore, the output unit can apply print settings using large fonts and graphics to A3-sized paper. For example, the output unit can apply print settings using large fonts and graphics to A3-sized paper. Furthermore, the output unit can apply print settings suited to the characteristics of special paper. For example, the output unit can apply print settings suited to the characteristics of special paper. This allows the output unit to automatically adjust optimal print settings according to the type and size of paper. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input paper type and size data to a generation AI, causing the generation AI to automatically adjust optimal print settings.

[0103] The output unit can estimate the user's emotions and adjust the order of output based on the estimated user's emotions. For example, when the user is relaxed, the output unit can output important information first and detailed information later. Furthermore, when the user is in a hurry, the output unit can output information that emphasizes the main points first and detailed information later. For example, when the user is in a hurry, the output unit can output information that emphasizes the main points first and detailed information later. Furthermore, when the user is feeling stressed, the output unit can output information that includes encouraging words first and detailed information later. For example, when the user is feeling stressed, the output unit can output information that includes encouraging words first and detailed information later. This allows the output unit to adjust the order of output according to the user's emotions. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the output unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the output unit can input the user's emotional data into the generation AI, and have the generation AI adjust the order of output.

[0104] The output unit can select the optimal output format at the time of output, taking into account the user's device information. For example, if the user is using a smartphone, the output unit can provide an output format that matches the screen size. Furthermore, if the user is using a tablet, the output unit can provide an output format optimized for a large screen. For example, if the user is using a tablet, the output unit can provide an output format optimized for a large screen. Furthermore, if the user is using a personal computer, the output unit can provide a high-resolution output format. For example, if the user is using a personal computer, the output unit can provide a high-resolution output format. This allows the output unit to select the optimal output format taking into account the user's device information. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's device information to a generation AI, causing the generation AI to select the optimal output format.

[0105] At the time of output, the output unit can suggest optimal output settings by referring to the user's past output history. For example, the output unit can suggest similar settings based on an output format used by the user in the past. The output unit can also suggest an optimal format from the user's past output history. For example, the output unit can suggest an optimal format from the user's past output history. The output unit can also analyze the user's past output history and suggest the most efficient output settings. For example, the output unit can analyze the user's past output history and suggest the most efficient output settings. This allows the output unit to suggest optimal output settings by referring to the user's past output history. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input the user's past output history data to a generation AI, causing the generation AI to suggest optimal output settings.

[0106] The tallying unit can estimate the user's emotions and determine the priorities of the tallying based on the estimated user's emotions. For example, if the user is feeling stressed, the tallying unit can start tallying from easy questions. Furthermore, if the user is relaxed, the tallying unit can start tallying from more difficult questions. For example, if the user is relaxed, the tallying unit can start tallying from more difficult questions. Furthermore, if the user is in a hurry, the tallying unit can start tallying from more important questions. For example, if the user is in a hurry, the tallying unit can start tallying from more important questions. This allows the tallying unit to determine the priorities of the tallying based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the tallying unit may be performed using AI, or may be performed without AI. For example, the tallying unit can input the user's emotion data into the generation AI and have the generation AI determine the priorities of the tallying.

[0107] The tallying unit can weight the scores taking into account the difficulty of each question when tallying the scores. For example, the tallying unit can assign a high weight to a question of high difficulty. Furthermore, the tallying unit can assign a low weight to a question of low difficulty. For example, the tallying unit can assign a low weight to a question of low difficulty. Furthermore, the tallying unit can adjust the weighting of the scores according to the difficulty of each question. For example, the tallying unit can adjust the weighting of the scores according to the difficulty of each question. In this way, the tallying unit can weight the scores taking into account the difficulty of each question. Some or all of the above-mentioned processing in the tallying unit may be performed using, for example, AI, or may be performed without using AI. For example, the tallying unit can input difficulty data of the questions to a generation AI and have the generation AI weight the scores.

[0108] The tallying unit can improve the accuracy of the tallying by referring to the user's past performance data during tallying. For example, the tallying unit can adjust parameters of the tallying algorithm based on the user's past performance data. The tallying unit can also improve the accuracy of the tallying for a specific problem by referring to the user's past performance data. For example, the tallying unit can improve the accuracy of the tallying for a specific problem by referring to the user's past performance data. The tallying unit can also improve the reliability of the tallying results based on the user's past performance data. For example, the tallying unit can improve the reliability of the tallying results based on the user's past performance data. This allows the tallying unit to improve the accuracy of the tallying by referring to the user's past performance data. Some or all of the above-described processing in the tallying unit may be performed using, for example, AI, or may be performed without using AI. For example, the tallying unit can input the user's past performance data into a generation AI, which can improve the accuracy of the tallying.

[0109] The tallying unit can estimate the user's emotions and adjust the display method of the tally results based on the estimated user's emotions. For example, if the user is nervous, the tallying unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the tallying unit can provide a display method including detailed information. For example, if the user is relaxed, the tallying unit can provide a display method including detailed information. Furthermore, if the user is in a hurry, the tallying unit can provide a display method that focuses on the main points. For example, if the user is in a hurry, the tallying unit can provide a display method that focuses on the main points. This allows the tallying unit to adjust the display method of the tally results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the tallying unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the tallying unit can input the user's emotion data into the generation AI, which can then adjust the display method of the tally results.

[0110] The tallying unit can apply different tallying formats depending on the user's learning style when tallying the data. For example, the tallying unit can provide a tallying format that makes extensive use of graphs and diagrams to a user with a visual learning style. The tallying unit can also provide audio tallying results to a user with an auditory learning style. For example, the tallying unit can provide audio tallying results to a user with an auditory learning style. The tallying unit can also provide a tallying format that suggests specific actions to a user with a tactile learning style. For example, the tallying unit can provide a tallying format that suggests specific actions to a user with a tactile learning style. This allows the tallying unit to apply different tallying formats depending on the user's learning style. Some or all of the above-described processing in the tallying unit may be performed using, or without, AI. For example, the tallying unit can input the user's learning style data into a generation AI and have the generation AI apply different tallying formats.

[0111] When performing the calculations, the calculation unit can use a calculation method specific to a region, taking into account the user's geographical location information. For example, if the user is in a specific region, the calculation unit can use a calculation method tailored to the educational curriculum of that region. Furthermore, if the user is in a specific cultural sphere, the calculation unit can use a calculation method tailored to the culture. For example, if the user is in a specific cultural sphere, the calculation unit can use a calculation method tailored to the culture. Furthermore, if the user is in a specific country, the calculation unit can use a calculation method tailored to the education system of that country. For example, if the user is in a specific country, the calculation unit can use a calculation method tailored to the education system of that country. This allows the calculation unit to use a calculation method specific to a region, taking into account the user's geographical location information. Some or all of the above-described processing in the calculation unit may be performed using AI, for example, or may be performed without using AI. For example, the calculation unit can input the user's geographical location information to the generation AI, causing the generation AI to use a calculation method specific to the region.

[0112] The visualization unit can estimate the user's emotions and adjust the display method of the visualization based on the estimated user's emotions. For example, when the user is nervous, the visualization unit can provide a simple, highly visible display method. Furthermore, when the user is relaxed, the visualization unit can provide a display method including detailed information. For example, when the user is relaxed, the visualization unit can provide a display method including detailed information. Furthermore, when the user is in a hurry, the visualization unit can provide a display method that focuses on the main points. For example, when the user is in a hurry, the visualization unit can provide a display method that focuses on the main points. This allows the visualization unit to adjust the display method of the visualization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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. Some or all of the above-mentioned processing in the visualization unit may be performed using AI, for example, or without AI. For example, the visualization unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method of the visualization.

[0113] The visualization unit can adjust the level of detail of the display based on the importance of each question during visualization. For example, the visualization unit can provide a detailed display for important questions. Furthermore, the visualization unit can provide a concise display for questions of low importance. For example, the visualization unit can provide a concise display for questions of low importance. Furthermore, the visualization unit can adjust the level of detail of the display according to the importance of each question. For example, the visualization unit can adjust the level of detail of the display according to the importance of each question. In this way, the visualization unit can adjust the level of detail of the display based on the importance of each question. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input question importance data to a generation AI and have the generation AI adjust the level of detail of the display.

[0114] During visualization, the visualization unit can provide an individually customized display by referring to the user's past performance data. For example, the visualization unit can provide a detailed display for a specific problem based on the user's past performance data. The visualization unit can also provide a display including words of encouragement by referring to the user's past performance data. For example, the visualization unit can provide a display including words of encouragement by referring to the user's past performance data. The visualization unit can also provide a visually easy-to-understand display based on the user's past performance data. For example, the visualization unit can provide a visually easy-to-understand display based on the user's past performance data. This allows the visualization unit to provide an individually customized display by referring to the user's past performance data. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input the user's past performance data to a generation AI and cause the generation AI to provide an individually customized display.

[0115] The visualization unit can estimate the user's emotions and adjust the order of visualization based on the estimated user's emotions. For example, when the user is relaxed, the visualization unit can display important information first and detailed information later. Furthermore, when the user is in a hurry, the visualization unit can display key information first and detailed information later. For example, when the user is in a hurry, the visualization unit can display key information first and detailed information later. Furthermore, when the user is feeling stressed, the visualization unit can display information including encouraging words first and detailed information later. For example, when the user is feeling stressed, the visualization unit can display information including encouraging words first and detailed information later. This allows the visualization unit to adjust the order of visualization according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-mentioned processing in the visualization unit may be performed using, for example, an AI or without an AI. For example, the visualization unit can input the user's emotional data into the generation AI, and have the generation AI adjust the order of visualization.

[0116] The visualization unit can apply different display formats depending on the user's learning style when visualizing. For example, the visualization unit can provide a display format that makes extensive use of graphs and diagrams to a user with a visual learning style. The visualization unit can also provide an audio display to a user with an auditory learning style. For example, the visualization unit can provide an audio display to a user with an auditory learning style. The visualization unit can also provide a display format that suggests specific actions to a user with a tactile learning style. For example, the visualization unit can provide a display format that suggests specific actions to a user with a tactile learning style. This allows the visualization unit to apply different display formats depending on the user's learning style. Some or all of the above-described processing in the visualization unit may be performed using, for example, AI, or may be performed without using AI. For example, the visualization unit can input the user's learning style data to a generation AI and cause the generation AI to apply different display formats.

[0117] When performing visualization, the visualization unit can use a region-specific display method by taking into account the user's geographical location information. For example, if the user is in a specific region, the visualization unit can use a display method tailored to the educational curriculum of that region. Furthermore, if the user is in a specific cultural sphere, the visualization unit can use a display method tailored to the culture. For example, if the user is in a specific cultural sphere, the visualization unit can use a display method tailored to the culture. Furthermore, if the user is in a specific country, the visualization unit can use a display method tailored to the education system of that country. For example, if the user is in a specific country, the visualization unit can use a display method tailored to the education system of that country. This allows the visualization unit to use a region-specific display method by taking into account the user's geographical location information. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input the user's geographical location information to the generation AI and cause the generation AI to use a region-specific display method.

[0118] The advice unit can estimate the user's emotions and adjust the way the advice is expressed based on the estimated user's emotions. For example, if the user is relaxed, the advice unit can use more positive expressions. Furthermore, if the user is feeling stressed, the advice unit can include more encouraging words. For example, if the user is feeling stressed, the advice unit can include more encouraging words. Furthermore, if the user is in a hurry, the advice unit can provide concise and to-the-point advice. For example, if the user is in a hurry, the advice unit can provide concise and to-the-point advice. This allows the advice unit to adjust the way the advice is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-mentioned processing in the advice unit may be performed using an AI, for example, or without an AI. For example, the advice unit can input the user's emotion data into the generation AI and have the generation AI adjust the way the advice is expressed.

[0119] When providing advice, the advice unit can adjust the level of detail of the advice based on the importance of each problem. For example, the advice unit can provide detailed advice for important problems. Furthermore, the advice unit can provide concise advice for low-importance problems. For example, the advice unit can provide concise advice for low-importance problems. Furthermore, the advice unit can adjust the length and content of the advice based on the importance of each problem. For example, the advice unit can adjust the length and content of the advice based on the importance of each problem. This allows the advice unit to adjust the level of detail of the advice based on the importance of each problem. Some or all of the above-described processing in the advice unit may be performed using, or without, AI. For example, the advice unit can input problem importance data to a generation AI and have the generation AI adjust the level of detail of the advice.

[0120] When giving advice, the advice unit can provide individually customized advice by referring to the user's past performance data. For example, the advice unit can provide specific advice for a problem that the user answered incorrectly in the past. The advice unit can also provide advice including encouraging words based on the user's past performance data. For example, the advice unit can provide advice including encouraging words based on the user's past performance data. The advice unit can also provide detailed advice for a specific problem by referring to the user's past performance data. For example, the advice unit can provide detailed advice for a specific problem by referring to the user's past performance data. This allows the advice unit to provide individually customized advice by referring to the user's past performance data. Some or all of the above-described processing in the advice unit may be performed using, or without, an AI. For example, the advice unit can input the user's past performance data into a generation AI and cause the generation AI to provide individually customized advice.

[0121] The advice unit can estimate the user's emotions and adjust the length of the advice based on the estimated user's emotions. For example, the advice unit can provide detailed advice when the user is relaxed. Furthermore, the advice unit can provide concise advice when the user is in a hurry. For example, the advice unit can provide concise advice when the user is in a hurry. Furthermore, the advice unit can provide short advice including encouraging words when the user is feeling stressed. For example, the advice unit can provide short advice including encouraging words when the user is feeling stressed. This allows the advice unit to adjust the length of the advice according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, 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. Some or all of the above-mentioned processing in the advice unit may be performed using an AI, for example, or without an AI. For example, the advice unit can input the user's emotion data into the generation AI and have the generation AI adjust the length of the advice.

[0122] When providing advice, the advice unit can apply different advice formats depending on the user's learning style. For example, the advice unit can provide advice including diagrams and tables to a user with a visual learning style. The advice unit can also provide audio advice to a user with an auditory learning style. For example, the advice unit can provide audio advice to a user with an auditory learning style. The advice unit can also provide advice suggesting specific actions to a user with a tactile learning style. For example, the advice unit can provide advice suggesting specific actions to a user with a tactile learning style. This allows the advice unit to apply different advice formats depending on the user's learning style. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the user's learning style data to a generation AI and cause the generation AI to apply different advice formats.

[0123] When providing advice, the advice unit can provide region-specific advice taking into account the user's geographical location information. For example, if the user is in a specific region, the advice unit can provide advice tailored to the educational curriculum of that region. Furthermore, if the user is in a specific cultural sphere, the advice unit can provide advice tailored to that culture. For example, if the user is in a specific cultural sphere, the advice unit can provide advice tailored to that culture. Furthermore, if the user is in a specific country, the advice unit can provide advice tailored to the country's educational system. For example, if the user is in a specific country, the advice unit can provide advice tailored to the country's educational system. This allows the advice unit to provide region-specific advice taking into account the user's geographical location information. Some or all of the above-described processing in the advice unit may be performed using AI, for example, or may be performed without using AI. For example, the advice unit can input the user's geographical location information to a generation AI and cause the generation AI to provide region-specific advice. === Hard Collateral 1-1 === Each of the multiple elements, including the scanning unit, analyzing unit, comment generating unit, output unit, tallying unit, visualization unit, and advice unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the scanning unit can capture a photograph of a test paper using the camera 42 of the smart device 14 to acquire image data. The analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data to determine whether each question is correct. The comment generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates comments based on the correctness of each question. The output unit uses the output device 40 of the smart device 14 to print out the grading results and comments. The tallying unit is realized by the specific processing unit 290 of the data processing device 12 and tally grades by subject or unit. The visualization unit is realized by the specific processing unit 290 of the data processing device 12 and displays grades in graphs or tables. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides advice on how to proceed with learning. The scanning unit can estimate the user's emotion and adjust the timing of scanning based on the estimated user's emotion. === Hard Collateral 1-2 === Each of the multiple elements, including the scanning unit, analyzing unit, comment generating unit, output unit, tallying unit, visualization unit, and advising unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the scanning unit can photograph a test paper using the camera 42 of the smart glasses 214 to acquire image data. The analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data to determine whether each question is correct. The comment generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates comments based on the correctness of each question. The output unit can provide the scoring results and comments by voice using the speaker 240 of the smart glasses 214. The tallying unit is realized by the specific processing unit 290 of the data processing device 12 and tally grades by subject or unit. The visualization unit is realized by the specific processing unit 290 of the data processing device 12 and displays grades in graphs or tables. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides advice on how to proceed with learning. The scanning unit can estimate the user's emotion and adjust the timing of scanning based on the estimated user's emotion. === Hard Collateral 1-3 === Each of the multiple elements, including the scanning unit, analyzing unit, comment generating unit, output unit, tallying unit, visualization unit, and advice unit, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the scanning unit can capture a photograph of a test paper using the camera 42 of the headset-type terminal 314 to acquire image data. The analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data to determine whether each question is correct. The comment generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates comments based on the correctness of each question. The output unit can display the grading results and comments using the display 343 of the headset-type terminal 314. The tallying unit is realized by the specific processing unit 290 of the data processing device 12 and tally grades by subject or unit. The visualization unit is realized by the specific processing unit 290 of the data processing device 12 and displays grades in graphs or tables. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides advice on how to proceed with learning. The scanning unit can estimate the user's emotion and adjust the timing of scanning based on the estimated user's emotion. === Hard Collateral 1-4 === Each of the multiple elements, including the scanning unit, analyzing unit, comment generating unit, output unit, tallying unit, visualization unit, and advice unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the scanning unit can photograph a test paper using the camera 42 of the robot 414 to acquire image data. The analyzing unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the image data to determine whether each question is correct. The comment generating unit is realized by the specific processing unit 290 of the data processing device 12 and generates comments based on the correctness of each question. The output unit can provide the scoring results and comments by voice using the speaker 240 of the robot 414. The tallying unit is realized by the specific processing unit 290 of the data processing device 12 and tally grades by subject or unit. The visualization unit is realized by the specific processing unit 290 of the data processing device 12 and displays grades in graphs or tables. The advice unit is realized by the specific processing unit 290 of the data processing device 12 and provides advice on how to proceed with learning. The scanning unit can estimate the user's emotion and adjust the timing of scanning based on the estimated user's emotion.

[0124] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0125] The analysis unit can estimate the user's emotions and determine the analysis priority based on the estimated user emotions. For example, if the user is feeling stressed, the analysis can begin with easy questions. If the user is relaxed, the analysis can begin with more difficult questions. If the user is in a hurry, the analysis can begin with important questions. This allows the analysis unit to determine the analysis priority according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the user's emotion data into the generation AI and have the generation AI determine the analysis priority.

[0126] The scanning unit can detect the condition of the paper (e.g., creases or stains) during scanning and make corrections to improve scan quality. For example, it can detect folded parts and correct them using image processing technology. It can also detect stains and blemishes and remove them from the scanned image. It can also detect paper distortion and correct the scanned image to obtain accurate data. This allows the scanning unit to detect the condition of the paper and make corrections to improve scan quality. Some or all of the above-mentioned processing in the scanning unit may be performed using, for example, AI, or may be performed without using AI. For example, the scanning unit can input paper condition data into a generation AI and have the generation AI correct the scan quality.

[0127] The comment generation unit can estimate the user's emotions and adjust the way the comment is expressed based on the estimated user's emotions. For example, if the user is relaxed, the comment can use a lot of positive expressions. If the user is stressed, the comment can include many encouraging words. If the user is in a hurry, the comment can be generated to be concise and to the point. This allows the comment generation unit to adjust the way the comment is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-described processing in the comment generation unit can be performed using, for example, AI, or without AI. For example, the comment generation unit can input the user's emotion data into the generation AI and have the generation AI adjust the way the comment is expressed.

[0128] The output unit can customize the printout format according to the user's preferences at the time of output. For example, if the user prefers a simple format, a simple layout can be printed out. If the user prefers a detailed format, a layout including detailed information can be printed out. Furthermore, if the user prefers a visual format, a layout making extensive use of graphs and diagrams can be printed out. This allows the output unit to customize the printout format according to the user's preferences. Some or all of the above-described processing in the output unit may be performed using, for example, AI, or may be performed without using AI. For example, the output unit can input user preference data into a generation AI and have the generation AI customize the printout format.

[0129] The tallying unit can estimate the user's emotions and determine the priorities of the tallying based on the estimated user's emotions. For example, if the user is feeling stressed, the tallying unit can start with easy questions. If the user is relaxed, the tallying unit can start with more difficult questions. If the user is in a hurry, the tallying unit can start with important questions. This allows the tallying unit to determine the priorities of the tallying according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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. Some or all of the above-described processing in the tallying unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the tallying unit can input the user's emotion data into the generation AI, and have the generation AI determine the priorities of the tallying.

[0130] The visualization unit can adjust the level of detail of the display based on the importance of each question during visualization. For example, important questions can be displayed in detail. Meanwhile, questions of low importance can be displayed in a concise manner. Furthermore, the level of detail of the display can be adjusted according to the importance of each question. This allows the visualization unit to adjust the level of detail of the display based on the importance of each question. Some or all of the above-described processing in the visualization unit may be performed using AI, for example, or may be performed without using AI. For example, the visualization unit can input question importance data to a generation AI and have the generation AI adjust the level of detail of the display.

[0131] The advice unit can estimate the user's emotions and adjust the way the advice is expressed based on the estimated user's emotions. For example, if the user is relaxed, the advice unit can use a lot of positive expressions. If the user is stressed, the advice unit can include many encouraging words. If the user is in a hurry, the advice unit can provide concise and to-the-point advice. This allows the advice unit to adjust the way the advice is expressed depending on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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 these examples. Some or all of the above-mentioned processing in the advice unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the advice unit can input the user's emotion data into the generation AI and have the generation AI adjust the way the advice is expressed.

[0132] The scanning unit can automatically adjust optimal scan settings depending on the type and format of the test paper when scanning. For example, in the case of a multiple-choice test paper, the resolution can be increased to accurately read the position of the marks. In addition, in the case of a handwritten test paper, appropriate scan settings can be set to improve the accuracy of handwriting recognition. Furthermore, in the case of a multi-page test paper, the page order can be automatically recognized and scanned. This allows the scanning unit to automatically adjust optimal scan settings depending on the type and format of the test paper. Some or all of the above-mentioned processing in the scanning unit may be performed using, for example, AI, or may be performed without using AI. For example, the scanning unit can input the type and format of the test paper into a generation AI, which can then automatically adjust optimal scan settings.

[0133] During analysis, the analysis unit can apply different analysis algorithms depending on the format of the test paper. For example, an algorithm that analyzes mark positions can be applied to a multiple-choice test paper. A handwriting recognition algorithm can be applied to a handwritten test paper. Furthermore, an algorithm that analyzes options can be applied to a multiple-choice test paper. This allows the analysis unit to apply different analysis algorithms depending on the format of the test paper. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input test paper format data into a generation AI, which can then apply the optimal analysis algorithm.

[0134] The visualization unit can estimate the user's emotions and adjust the display method of the visualization based on the estimated user's emotions. For example, if the user is nervous, a simple, highly visible display method can be provided. Furthermore, if the user is relaxed, a display method including detailed information can be provided. Furthermore, if the user is in a hurry, a display method that focuses on the main points can be provided. This allows the visualization unit to adjust the display method of the visualization according to the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, 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. Some or all of the above-described processing in the visualization unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the visualization unit can input the user's emotion data into the generation AI and have the generation AI adjust the display method of the visualization.

[0135] The processing flow of the second embodiment will be briefly explained below.

[0136] Step 1: The scanning unit scans the test paper to obtain image data. For example, the scanning unit can use a high-resolution scanner to scan the test paper and generate image data. Alternatively, the scanning unit can use a smartphone camera to take a photo of the test paper and obtain image data. Furthermore, the scanning unit can use OCR technology to convert handwritten answers into digital data. Step 2: The analysis unit analyzes the image data acquired by the scanning unit and determines whether each question is correct or incorrect. For example, the analysis unit uses an image processing algorithm to analyze the mark positions on a multiple-choice test sheet and determine whether the answers are correct or incorrect. The analysis unit can also analyze handwritten answers and determine whether they are correct or incorrect using handwriting recognition technology. Furthermore, the analysis unit can use AI to extract text data from the image data and determine whether each question is correct or incorrect. Step 3: The comment generation unit generates comments based on the correctness of each question determined by the analysis unit. For example, the comment generation unit uses natural language processing technology to generate comments such as "Good job" if the answer is correct and "Let's review it again" if the answer is incorrect. The comment generation unit can also use a template-based generation method to generate comments based on the correctness of each question. Furthermore, the comment generation unit can use AI to generate appropriate comments based on the correctness of each question. Step 4: The output unit prints out the comments generated by the comment generation unit and the scoring results determined by the analysis unit. For example, the output unit uses a printer to print out the scoring results, including whether each question is correct or incorrect and the comments. The output unit can also save the scoring results in digital format and provide them to the user via email or a cloud service. Furthermore, the output unit can display the scoring results to the user via a web application or a mobile application. Step 5: The calculation unit compiles the grades obtained by the analysis unit and compiles grades by subject or unit. For example, the calculation unit stores the grades for each question in a database and compiles grades by subject or unit. The calculation unit can also normalize the grade data to make it easier to compare across different tests. Furthermore, the calculation unit can use AI to analyze the grade data and automatically compile grades by subject or unit. Step 6: The visualization unit displays the weak and strong units in a graph or table based on the grades compiled by the compilation unit. For example, the visualization unit uses a bar graph or pie chart to visually display the grades for each unit. The visualization unit can also visually display the distribution of grades using a heat map. Furthermore, the visualization unit can use AI to analyze the grade data and automatically visualize the weak and strong units. Step 7: The Advice Unit provides advice on how to proceed with learning based on the data visualized by the Visualization Unit. For example, the Advice Unit may provide advice such as "Let's focus on reviewing this unit" for weaker units. The Advice Unit may also provide advice such as "Let's study this unit in more depth" for stronger units. Furthermore, the Advice Unit can use AI to analyze the grade data and propose individual learning plans.

[0137] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0138] 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 engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0139] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0142] 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.

[0143] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0144] 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.

[0145] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0146] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0147] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0148] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0149] 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.

[0150] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0151] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0153] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0154] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0155] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0158] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0160] 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.

[0161] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0164] 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.

[0165] 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.

[0166] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0167] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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.

[0168] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0169] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0170] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0171] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0172] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0173] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0176] 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.

[0177] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0178] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0179] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0180] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0181] 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.

[0182] 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.

[0183] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0184] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0185] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0186] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0187] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0188] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0189] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0190] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0191] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0192] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0193] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0194] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0195] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0196] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0197] 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.

[0198] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0199] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0200] 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.

[0201] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0202] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0203] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0204] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0205] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0206] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0207] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0208] [Explanation of symbols]

[0209] 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 scanning unit for scanning test papers; an analysis unit that analyzes the data scanned by the scanning unit; a comment generation unit that generates a comment based on the data analyzed by the analysis unit; an output unit that prints out the comments generated by the comment generating unit and the scoring results; a counting unit that counts the results obtained by the analysis unit; a visualization unit that visualizes the results tallied by the tallying unit; An advice unit that gives advice on how to proceed with learning based on the data visualized by the visualization unit. A system characterized by:

2. The scanning unit Acquire image data of the test paper 2. The system of claim 1.

3. The analysis unit Analyze image data and determine whether each question is correct or incorrect 2. The system of claim 1.

4. The comment generation unit Generate comments based on correctness of each question 2. The system of claim 1.

5. The output unit Print out the marks and comments 2. The system of claim 1.

6. The aggregation unit Tally the grades for each question and compile the grades by subject and unit.

2. The system of claim 1.

7. The visualization unit Based on the collected grades, weak and strong subjects are displayed in graphs and tables.

2. The system of claim 1.

8. The advice unit Providing advice on how to proceed with learning based on visualized data 2. The system of claim 1.

Images