system

Abstract

The system according to this embodiment aims to efficiently generate text based on each student's learning data, attendance rate, and essay data. [Solution] The system according to the embodiment comprises an acquisition unit, a generation unit, and a provision unit. The acquisition unit communicates with each school's database via an API to acquire each student's learning data, attendance rate, and essay data. The generation unit generates text corresponding to each student based on the data acquired by the acquisition unit. The provision unit provides the text generated by the generation unit in a format that matches each school's format.

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, comprising the steps of: receiving a user utterance; adding the user utterance to a prompt that includes instructions relating to a description of the chatbot's character; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance that responds 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] Conventional technologies presented a challenge in that creating texts based on each student's learning data, attendance rates, and essay data was time-consuming and difficult to do efficiently.

[0005] The system according to this embodiment aims to efficiently generate text based on each student's learning data, attendance rate, and essay data. [Means for solving the problem]

[0006] The system according to this embodiment comprises an acquisition unit, a generation unit, and a provision unit. The acquisition unit connects with each school's database via an API to acquire each student's learning data, attendance rate, and essay data. The generation unit generates text corresponding to each student based on the data acquired by the acquisition unit. The provision unit provides the text generated by the generation unit in a format that matches each school's format. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently generate text based on each student's learning data, attendance rate, and essay data. [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] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or" in this specification.

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

[0017] As shown in Figure 1, the 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 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor 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] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 processing is realized by the processor 28 operating as a specific processing unit 290 according to 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, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The observation writing system according to an embodiment of the present invention is a system that automatically creates drafts and drafts for observation sections in school report cards and recommendation letters. This observation writing system can generate texts appropriate for each student based on data such as each student's learning data, attendance rate, and essays. For example, the observation writing system connects with each school's database via an API to acquire data such as each student's learning data, attendance rate, and essays in real time. Next, based on the acquired data, the generating AI generates texts appropriate for each student. In this process, the generating AI does not need to be prompted each time and can create texts that match each school's format. For example, based on a student's learning data, attendance rate, and essay content, it can generate observations that include the student's learning attitude, grades, and future goals. Furthermore, when creating recommendation letters, it can generate texts that reflect each student's characteristics and strengths. This service allows teachers to create observations and recommendation letters appropriate for each student without much effort. In addition, since the generated texts are adapted to each school's format, it is possible to provide observations and recommendation letters with a consistent feel. Furthermore, the system provides an editing function for the generated text, allowing teachers to review the text and make corrections or additions as needed. This enables the student feedback system to automatically generate texts tailored to each student and provide them in accordance with each school's format.

[0029] The observation writing system according to the embodiment comprises an acquisition unit, a generation unit, and a provision unit. The acquisition unit connects with each school's database via API to acquire each student's learning data, attendance rate, and essay data. For example, the acquisition unit can acquire data from a learning management system or an attendance management system. Examples of API types used include REST API and SOAP API. Learning data includes test results and assignment submission status. Attendance rate is calculated based on attendance days and absence days. Essay data includes essay length and evaluation criteria. The generation unit generates essays corresponding to each student based on the data acquired by the acquisition unit. The generation unit generates essays using a generation AI. For example, the generation AI can use methods such as natural language generation technology or template-based generation. The generation unit analyzes each student's learning data, attendance rate, and essay content, and automatically generates appropriate prompts based on this analysis. The provision unit provides the essays generated by the generation unit in accordance with each school's format. The provision unit pre-registers each school's format and automatically applies the generated essays to that format. For example, the provisioning unit can adjust the document layout, font size, and other elements. Furthermore, the provisioning unit provides an editing function for the generated text, allowing teachers to review the generated text and make corrections or additions as needed. As a result, the observation writing system according to this embodiment can automatically generate text appropriate for each student and provide it in accordance with each school's format.

[0030] The generation unit can analyze each student's learning data, attendance rate, and essay content, and automatically generate corresponding prompts based on this analysis. For example, the generation unit can analyze each student's learning data and automatically generate appropriate prompts. For example, the generation unit can evaluate the student's learning progress based on test results and assignment submission status, and generate prompts based on this. The generation unit can also analyze attendance rates and generate prompts based on attendance days and absence days. Furthermore, the generation unit can analyze essay content and generate prompts based on essay length and evaluation criteria. For example, the generation unit can analyze the essay theme and content and generate prompts based on this. This improves the accuracy of text generation by allowing the generation unit to automatically generate appropriate prompts based on each student's data. Some or all of the above-described processes in the generation unit may be performed using, for example, a generation AI, or without using a generation AI. For example, the generation unit can input each student's learning data, attendance rate, and essay content into a generation AI and have the generation AI generate prompts.

[0031] The service provider can pre-register the format of each school and automatically apply the generated text to that format. For example, the service provider can pre-register the format of each school and automatically apply the generated text to that format. For example, the service provider can register the format of each school's report card or letter of recommendation and apply the generated text to that format. The service provider can adjust the document layout, font size, etc. For example, the service provider can position the generated text appropriately to match the format of a report card. The service provider can also provide the generated text in an appropriate format to match the format of a letter of recommendation. In this way, the service provider can provide consistent text by automatically applying it to each school's format. Some or all of the above processing in the service provider may be performed using, for example, a generation AI, or without a generation AI. For example, the service provider can input the generated text into a generation AI and have the generation AI perform the format application.

[0032] The service provider can provide editing functions for generated text, allowing teachers to review the generated text and make corrections or additions as needed. For example, the service provider can provide a text editor, allowing teachers to edit the generated text. The service provider can also provide a revision history management function, allowing teachers to review the history of revisions and additions they have made. For example, the service provider can highlight revised sections to clearly indicate which parts have been modified. Furthermore, the service provider can provide an editing suggestion function to enable teachers to edit efficiently. For example, the service provider can automatically suggest improvements to the text, allowing teachers to make revisions based on those suggestions. This enables the service provider to provide more appropriate text by allowing teachers to review the generated text and make corrections or additions as needed. Some or all of the above processes in the service provider may be performed using, for example, a generation AI, or not using a generation AI. For example, the service provider can input the generated text into a generation AI and have the generation AI execute editing suggestions.

[0033] The data acquisition unit can analyze each student's past learning data and select an appropriate data acquisition method. For example, the data acquisition unit can analyze each student's past learning patterns and determine the most effective timing for data acquisition. The data acquisition unit can also select a data acquisition method that focuses on a specific subject based on each student's past performance data. Furthermore, the data acquisition unit can consider each student's past attendance rate and select a supplementary data acquisition method for students with high absence rates. In this way, the data acquisition unit can select the optimal data acquisition method by analyzing each student's past learning data. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generative AI, or without a generative AI. For example, the data acquisition unit can input each student's past learning data into a generative AI and have the generative AI select the data acquisition method.

[0034] The acquisition unit can perform filtering based on each student's current learning situation and areas of interest when acquiring data. For example, the acquisition unit can perform filtering based on each student's current learning situation and areas of interest when acquiring data. For example, the acquisition unit can acquire only necessary data based on each student's current learning progress. The acquisition unit can also prioritize acquisition of relevant data based on each student's areas of interest. Furthermore, the acquisition unit can take each student's learning attitude into consideration and acquire detailed data for active students and basic data for passive students. This allows the acquisition unit to acquire only necessary data based on each student's current learning situation and areas of interest. Some or all of the above-mentioned processing in the acquisition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the acquisition unit can input data on each student's learning situation and areas of interest into the generation AI and have the generation AI perform filtering.

[0035] When acquiring data, the acquisition unit can prioritize acquiring highly relevant data by taking into account the geographical location information of each student. For example, when acquiring data, the acquisition unit prioritizes acquiring highly relevant data by taking into account the geographical location information of each student. For example, when acquiring data, the acquisition unit prioritizes acquiring real-time attendance data when each student is at school. Furthermore, when each student is at home, the acquisition unit can prioritize acquiring home learning data. Furthermore, when each student is in a specific area, the acquisition unit can prioritize acquiring learning data related to that area. In this way, the acquisition unit can prioritize acquiring highly relevant data by taking into account the geographical location information of each student. Some or all of the above-mentioned processing in the acquisition unit may be performed using, or without, a generation AI. For example, the acquisition unit can input the geographical location information of each student to the generation AI and cause the generation AI to determine the priority of the data.

[0036] The acquisition unit can analyze each student's social media activity and acquire related data when acquiring data. For example, the acquisition unit can analyze each student's social media activity and acquire related data when acquiring data. For example, the acquisition unit can analyze each student's social media posts and acquire data related to learning. The acquisition unit can also determine the optimal timing for acquiring data by taking into account each student's social media activity time. Furthermore, the acquisition unit can acquire related learning data based on each student's social media interests. In this way, the acquisition unit can acquire related data by analyzing each student's social media activity. Some or all of the above-mentioned processing in the acquisition unit can be performed, for example, using a generation AI or without using a generation AI. For example, the acquisition unit can input each student's social media activity data into a generation AI and cause the generation AI to acquire data.

[0037] The generation unit can adjust the level of detail of the sentences based on the evaluation of each student's learning data when generating the sentences. For example, the generation unit can adjust the level of detail of the sentences based on the evaluation of each student's learning data when generating the sentences. For example, the generation unit generates detailed observations when each student has abundant learning data. The generation unit can also generate concise observations when each student has little learning data. Furthermore, the generation unit can generate detailed observations related to a specific subject when each student's data in that subject is important. This allows the generation unit to generate more appropriate sentences by adjusting the level of detail of the sentences based on the importance of each student's learning data. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input each student's learning data into the generation AI and have the generation AI adjust the level of detail of the sentences.

[0038] The generation unit can apply different generation algorithms depending on the category of each student when generating sentences. For example, the generation unit can apply different generation algorithms depending on the category of each student when generating sentences. For example, the generation unit can generate sentences of an appropriate level of difficulty depending on the grade level of each student. The generation unit can also generate sentences containing technical terms depending on the subject of each student. Furthermore, the generation unit can generate personalized sentences depending on the learning style of each student. In this way, the generation unit can generate more appropriate sentences by applying different generation algorithms depending on the category of each student. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input category data of each student into the generation AI and cause the generation AI to apply the generation algorithm.

[0039] The generation unit can determine the priority of sentences based on the submission time of each student when generating sentences. For example, the generation unit determines the priority of sentences based on the submission time of each student when generating sentences. For example, the generation unit prioritizes generating sentences for students whose submission deadlines are approaching. The generation unit can also postpone generating sentences for students whose submission deadlines are further away. Furthermore, the generation unit can urgently generate sentences for students whose submission deadlines have passed. In this way, the generation unit can efficiently generate sentences by determining the priority of sentences based on the submission time of each student. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input submission time data for each student into the generation AI and have the generation AI determine the priority of sentences.

[0040] The generation unit can adjust the order of sentences based on the relevance of each student when generating sentences. For example, the generation unit adjusts the order of sentences based on the relevance of each student when generating sentences. For example, the generation unit determines the order of sentences based on the relevance of each student's learning data. The generation unit can also determine the order of sentences based on the relevance of each student's attendance rate. Furthermore, the generation unit can determine the order of sentences based on the relevance of each student's essay content. In this way, the generation unit can generate more appropriate sentences by adjusting the order of sentences based on the relevance of each student. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the relevance data of each student into the generation AI and cause the generation AI to adjust the order of the sentences.

[0041] The providing unit can select an appropriate format based on each school's past format data at the time of providing. For example, the providing unit selects the optimal format by referring to each school's past format data at the time of providing. For example, the providing unit selects the optimal format by referring to each school's past report card format. The providing unit can also select the optimal format by referring to each school's past recommendation letter format. Furthermore, the providing unit can select the optimal format by referring to each school's past observation format. In this way, the providing unit can select the optimal format by referring to each school's past format data. Some or all of the above-described processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input each school's past format data into the generation AI and cause the generation AI to select a format.

[0042] The providing unit can customize the text based on the current format of each school at the time of providing. The providing unit, for example, customizes the text based on the current format of each school at the time of providing. For example, the providing unit customizes the text based on the current report card format of each school. The providing unit can also customize the text based on the current recommendation letter format of each school. Furthermore, the providing unit can customize the text based on the current observation format of each school. In this way, the providing unit can provide more appropriate text by customizing the text based on the current format of each school. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the current format data of each school into the generation AI and cause the generation AI to customize the text.

[0043] The providing unit can select an appropriate format based on the geographical location information of each school at the time of providing. For example, the providing unit selects the optimal format by taking into account the geographical location information of each school at the time of providing. For example, if each school is located in an urban area, the providing unit selects a format suitable for the urban area. Furthermore, if each school is located in a suburban area, the providing unit can also select a format suitable for the suburban area. Furthermore, if each school is located in a rural area, the providing unit can also select a format suitable for the rural area. In this way, the providing unit can select the optimal format by taking into account the geographical location information of each school. Some or all of the above-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the geographical location information of each school into the generation AI and cause the generation AI to select a format.

[0044] The providing unit can analyze the social media activity of each school and propose a format at the time of providing the data. For example, the providing unit can analyze the social media activity of each school and propose a format at the time of providing the data. For example, the providing unit can analyze the social media activity of each school and propose an optimal format. The providing unit can also propose a format taking into account the frequency of posts on social media by each school. Furthermore, the providing unit can propose a format based on the number of followers on social media of each school. In this way, the providing unit can propose an optimal format by analyzing the social media activity of each school. Some or all of the above-mentioned processing by the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the social media activity data of each school into the generation AI and have the generation AI execute a format proposal.

[0045] The editing function can suggest an appropriate editing method based on each student's past editing history during editing. For example, the editing function can suggest the optimal editing method by referring to each student's past editing history during editing. For example, the editing function can suggest the optimal editing method based on each student's past editing history. The editing function can also analyze each student's past editing patterns and suggest an efficient editing method. Furthermore, the editing function can make similar editing suggestions by referring to each student's past editing content. In this way, the editing function can suggest the optimal editing method by referring to each student's past editing history. Some or all of the above-mentioned processing in the editing function may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the editing function can input each student's past editing history data into a generation AI and have the generation AI execute an editing method suggestion.

[0046] The editing function can propose the optimal editing method by taking into account the device information of each school during editing. For example, the editing function can propose the optimal editing method by taking into account the device information of each school during editing. For example, the editing function can propose an editing method that matches the screen size of the device used by each school. The editing function can also propose an editing method that matches the input method (touch, keyboard, etc.) of the device used by each school. Furthermore, the editing function can propose an efficient editing method based on the performance of the device used by each school. In this way, the editing function can propose the optimal editing method by taking into account the device information of each school. Some or all of the above-mentioned processing in the editing function may be performed using, or without, a generation AI. For example, the editing function can input the device information of each school into the generation AI and have the generation AI execute the suggested editing method.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] When acquiring learning data for each student, the acquisition unit can adjust the data acquisition method taking into account each student's learning style. For example, visual data can be acquired preferentially for students with a visual learning style, and audio data can be acquired preferentially for students with an auditory learning style. In addition, experimental and practical data can be acquired preferentially for students with a practical learning style. This allows the acquisition unit to acquire optimal data according to each student's learning style.

[0049] When analyzing each student's learning data, the generation unit can generate prompts taking into account each student's learning goals. For example, for a student aiming for high grades in a specific subject, the generation unit can generate prompts related to that subject, and for a student aiming to improve their overall grades, the generation unit can generate balanced prompts. In addition, for a student who wants to master a specific skill, the generation unit can generate prompts related to that skill. In this way, the generation unit can generate prompts according to each student's learning goals.

[0050] When providing an editing function for generated text, the provider can make editing suggestions taking into account each student's learning history. For example, for a student who has struggled in a particular subject in the past, specific improvements in that subject can be suggested, and for a student who has achieved excellent grades in the past, suggestions can be made for further improvement. In addition, for a student who has had low attendance rates in the past, suggestions can be made for improving attendance rates. This allows the provider to make appropriate editing suggestions based on each student's learning history.

[0051] When analyzing each student's past learning data, the acquisition unit can adjust the data acquisition method taking into account each student's learning environment. For example, for a student who studies a lot at home, home learning data can be acquired preferentially, and for a student who studies a lot at school, school learning data can be acquired preferentially. In addition, for a student who studies a lot online, online learning data can be acquired preferentially. This allows the acquisition unit to select the optimal data acquisition method according to each student's learning environment.

[0052] When acquiring data, the acquisition unit can adjust the frequency of data acquisition based on each student's current learning situation and areas of interest. For example, for students who have a strong interest in a particular subject, data on that subject can be acquired more frequently, and data acquisition frequency can be reduced for subjects with less interest. In addition, the acquisition unit can increase the data acquisition frequency for students whose learning progress is lagging, and decrease the data acquisition frequency for students whose progress is steady. This allows the acquisition unit to select the optimal data acquisition frequency according to each student's learning situation and areas of interest.

[0053] When acquiring data, the acquisition unit can adjust the data acquisition method taking into account the geographical location information of each student. For example, for students living in urban areas, data related to urban areas can be preferentially acquired, and for students living in suburban areas, data related to suburban areas can be preferentially acquired. Also, for students living in rural areas, data related to rural areas can be preferentially acquired. This allows the acquisition unit to select the optimal data acquisition method according to the geographical location information of each student.

[0054] When acquiring data, the acquisition unit can analyze each student's social media activity and acquire related data. For example, it analyzes each student's social media posts to acquire data related to learning. It can also determine the optimal timing for acquiring data by taking into account the time each student spends active on social media. Furthermore, it can acquire related learning data based on each student's interests on social media. This allows the acquisition unit to acquire related data by analyzing each student's social media activity.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The acquisition unit connects to each school's database via API to acquire each student's learning data, attendance rate, and essay data. For example, the acquisition unit can acquire data from a learning management system or attendance management system. API types used include REST API and SOAP API. Learning data includes test results and assignment submission status. Attendance rate is calculated based on the number of days attended and absent. Essay data includes the length of the essay and evaluation criteria. Step 2: The generation unit generates sentences corresponding to each student based on the data acquired by the acquisition unit. The generation unit generates sentences using a generation AI. For example, the generation AI can use methods such as natural language generation technology or template-based generation. The generation unit analyzes each student's learning data, attendance rate, and essay content, and automatically generates appropriate prompts based on that. Step 3: The provider provides the text generated by the generator in accordance with the format of each school. The provider pre-registers the format of each school and automatically applies the generated text to that format. For example, the provider can adjust the document layout, font size, etc. Furthermore, the provider provides an editing function for the generated text, allowing teachers to review the generated text and make corrections or additions as necessary.

[0057] (Example 2) A comment writing system according to an embodiment of the present invention automatically creates comment sections and comment templates for school report cards and recommendation letters. This comment writing system can generate personalized comments for each student based on data such as each student's learning data, attendance rate, and essays. For example, the comment writing system connects with each school's database via an API to acquire each student's learning data, attendance rate, essays, and other data in real time. Next, a generation AI generates personalized comments for each student based on the acquired data. The generation AI can create personalized comments in accordance with each school's format without requiring prompts. For example, a comment can be generated based on a student's learning data, attendance rate, and essay content, including the student's learning attitude, grades, and future goals. Furthermore, recommendation letters can be generated that reflect each student's unique characteristics and strengths. This service allows teachers to effortlessly create personalized comments and recommendation letters for each student. Furthermore, because the generated comments are tailored to each school's format, consistent comments and recommendation letters can be provided. In addition, an editing function for the generated text is provided, allowing teachers to review the generated text and make corrections or additions as necessary. This allows the observation writing system to automatically generate text that is appropriate for each student and provide it in accordance with the format of each school.

[0058] The observation writing system according to the embodiment includes an acquisition unit, a generation unit, and a provision unit. The acquisition unit connects with each school's database via an API to acquire each student's learning data, attendance rate, and essay data. For example, the acquisition unit can acquire data from a learning management system or attendance management system. APIs such as a REST API or SOAP API are used. The learning data includes test results and assignment submission status. The attendance rate is calculated based on the number of days attended and the number of days absent. The essay data includes the length of the sentence and evaluation criteria. The generation unit generates sentences corresponding to each student based on the data acquired by the acquisition unit. The generation unit generates the sentences using a generation AI. For example, the generation AI can use methods such as natural language generation technology or template-based generation. The generation unit analyzes each student's learning data, attendance rate, and essay content and automatically generates appropriate prompts based on the results. The provision unit provides the sentences generated by the generation unit in accordance with the format of each school. The provision unit pre-registers each school's format and automatically applies the generated sentences to that format. For example, the providing unit can adjust the layout, font size, etc. of the document. Furthermore, the providing unit provides an editing function for the generated text, allowing teachers to check the generated text and make corrections or additions as necessary. In this way, the observation writing system according to the embodiment can automatically generate text appropriate for each student and provide it in accordance with the format of each school.

[0059] The generation unit can analyze each student's learning data, attendance rate, and essay content, and automatically generate corresponding prompts based on the data. The generation unit, for example, analyzes each student's learning data and automatically generates appropriate prompts. For example, the generation unit evaluates the student's learning progress based on test results and assignment submission status, and generates prompts based on the evaluation. The generation unit can also analyze the student's attendance rate and generate prompts based on the number of days attended and the number of days absent. The generation unit can also analyze the content of essays and generate prompts based on the length of the essay and the evaluation criteria. For example, the generation unit analyzes the theme and content of the essay and generates prompts based on the theme and content. This allows the generation unit to automatically generate appropriate prompts based on each student's data, thereby improving the accuracy of sentence generation. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can input each student's learning data, attendance rate, and essay content into the generation AI and have the generation AI generate prompts.

[0060] The providing unit can register the format of each school in advance and automatically apply the generated text to that format. For example, the providing unit can register the format of each school in advance and automatically apply the generated text to that format. For example, the providing unit can register the format of each school's report card and recommendation letter and apply the generated text to that format. The providing unit can adjust the document layout, font size, etc. For example, the providing unit can place the generated text in an appropriate position to match the report card format. The providing unit can also provide the generated text in an appropriate format to match the recommendation letter format. In this way, the providing unit can provide text with a consistent feel by automatically applying it to each school's format. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the generated text into a generation AI and have the generation AI apply the format.

[0061] The providing unit may provide an editing function for the generated text, allowing the teacher to review the generated text and make corrections or additions as necessary. For example, the providing unit may provide an editing function for the generated text, allowing the teacher to review the generated text and make corrections or additions as necessary. For example, the providing unit may provide a text editor, allowing the teacher to edit the generated text. The providing unit may also provide a correction history management function, allowing the teacher to check the history of corrections and additions made by the teacher. For example, the providing unit may highlight corrections to clearly indicate which parts have been corrected. Furthermore, the providing unit may provide an editing suggestion function, allowing the teacher to edit efficiently. For example, the providing unit may automatically suggest improvements to the text, allowing the teacher to make corrections based on the suggestions. This allows the providing unit to provide more appropriate text by allowing the teacher to review the generated text and make corrections or additions as necessary. Some or all of the above-described processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit may input the generated text into the generation AI and cause the generation AI to execute the editing suggestions.

[0062] The acquisition unit can estimate each student's emotion and adjust the timing of data acquisition based on the estimated emotion. For example, the acquisition unit can estimate each student's emotion and adjust the timing of data acquisition based on the estimated emotion. For example, if a student is feeling stressed, the acquisition unit can delay data acquisition and prioritize data in a relaxed state. Furthermore, if a student is concentrating, the acquisition unit can acquire learning data at that timing to more accurately reflect the student's learning situation. Furthermore, if a student is tired, the acquisition unit can temporarily stop data acquisition and acquire data again after the student has rested. This allows the acquisition unit to acquire more accurate data by adjusting the timing of data acquisition according to each student's emotion. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit can be performed using, for example, the generation AI, or without the generation AI. For example, the acquisition unit can input each student's emotional data into the generation AI and have the generation AI adjust the timing of data acquisition.

[0063] The acquisition unit can analyze each student's past learning data and select an appropriate data acquisition method. For example, the acquisition unit analyzes each student's past learning data and selects an appropriate data acquisition method. For example, the acquisition unit analyzes each student's past learning patterns and determines the most effective timing for data acquisition. The acquisition unit can also select a data acquisition method that focuses on a specific subject based on each student's past grade data. Furthermore, the acquisition unit can also select a complementary data acquisition method for students with frequent absences by taking each student's past attendance rate into consideration. In this way, the acquisition unit can select the optimal data acquisition method by analyzing each student's past learning data. Some or all of the above-described processing in the acquisition unit may be performed using, or without, a generation AI. For example, the acquisition unit can input each student's past learning data into the generation AI and have the generation AI select a data acquisition method.

[0064] The acquisition unit can perform filtering based on each student's current learning situation and areas of interest when acquiring data. For example, the acquisition unit can perform filtering based on each student's current learning situation and areas of interest when acquiring data. For example, the acquisition unit can acquire only necessary data based on each student's current learning progress. The acquisition unit can also prioritize acquisition of relevant data based on each student's areas of interest. Furthermore, the acquisition unit can take each student's learning attitude into consideration and acquire detailed data for active students and basic data for passive students. This allows the acquisition unit to acquire only necessary data based on each student's current learning situation and areas of interest. Some or all of the above-mentioned processing in the acquisition unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the acquisition unit can input data on each student's learning situation and areas of interest into the generation AI and have the generation AI perform filtering.

[0065] The acquisition unit can estimate the emotions of each student and determine the priority of data to be acquired based on the estimated emotions. For example, the acquisition unit can estimate the emotions of each student and determine the priority of data to be acquired based on the estimated emotions. For example, if each student is excited, the acquisition unit can prioritize acquiring data related to emotions. Furthermore, if each student is calm, the acquisition unit can prioritize acquiring learning data. Furthermore, if each student is feeling anxious, the acquisition unit can prioritize acquiring data related to attendance rate and health condition. This allows the acquisition unit to prioritize data to be acquired based on each student's emotions, thereby acquiring more appropriate data. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit can be performed using, for example, the generation AI. For example, the acquisition unit can input each student's emotion data into the generation AI and have the generation AI determine the priority of the data.

[0066] When acquiring data, the acquisition unit can prioritize acquiring highly relevant data by taking into account the geographical location information of each student. For example, when acquiring data, the acquisition unit prioritizes acquiring highly relevant data by taking into account the geographical location information of each student. For example, when acquiring data, the acquisition unit prioritizes acquiring real-time attendance data when each student is at school. Furthermore, when each student is at home, the acquisition unit can prioritize acquiring home learning data. Furthermore, when each student is in a specific area, the acquisition unit can prioritize acquiring learning data related to that area. In this way, the acquisition unit can prioritize acquiring highly relevant data by taking into account the geographical location information of each student. Some or all of the above-mentioned processing in the acquisition unit may be performed using, or without, a generation AI. For example, the acquisition unit can input the geographical location information of each student to the generation AI and cause the generation AI to determine the priority of the data.

[0067] The acquisition unit can analyze each student's social media activity and acquire related data when acquiring data. For example, the acquisition unit can analyze each student's social media activity and acquire related data when acquiring data. For example, the acquisition unit can analyze each student's social media posts and acquire data related to learning. The acquisition unit can also determine the optimal timing for acquiring data by taking into account each student's social media activity time. Furthermore, the acquisition unit can acquire related learning data based on each student's social media interests. In this way, the acquisition unit can acquire related data by analyzing each student's social media activity. Some or all of the above-mentioned processing in the acquisition unit can be performed, for example, using a generation AI or without using a generation AI. For example, the acquisition unit can input each student's social media activity data into a generation AI and cause the generation AI to acquire data.

[0068] The generation unit can estimate the emotions of each student and adjust the way the sentences are expressed based on the estimated emotions. For example, the generation unit can estimate the emotions of each student and adjust the way the sentences are expressed based on the estimated emotions. For example, if each student is relaxed, the generation unit can generate sentences using gentle expressions. If each student is nervous, the generation unit can generate sentences including encouraging words. Furthermore, if each student is excited, the generation unit can generate sentences that make extensive use of positive expressions. This allows the generation unit to generate more appropriate sentences by adjusting the way the sentences are expressed based on each student's emotions. Emotion estimation is achieved 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 these examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input emotion data of each student into the generation AI and cause the generation AI to adjust the way the sentences are expressed.

[0069] The generation unit can adjust the level of detail of the sentences based on the evaluation of each student's learning data when generating the sentences. For example, the generation unit can adjust the level of detail of the sentences based on the evaluation of each student's learning data when generating the sentences. For example, the generation unit generates detailed observations when each student has abundant learning data. The generation unit can also generate concise observations when each student has little learning data. Furthermore, the generation unit can generate detailed observations related to a specific subject when each student's data in that subject is important. This allows the generation unit to generate more appropriate sentences by adjusting the level of detail of the sentences based on the importance of each student's learning data. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input each student's learning data into the generation AI and have the generation AI adjust the level of detail of the sentences.

[0070] The generation unit can apply different generation algorithms depending on the category of each student when generating sentences. For example, the generation unit can apply different generation algorithms depending on the category of each student when generating sentences. For example, the generation unit can generate sentences of an appropriate level of difficulty depending on the grade level of each student. The generation unit can also generate sentences containing technical terms depending on the subject of each student. Furthermore, the generation unit can generate personalized sentences depending on the learning style of each student. In this way, the generation unit can generate more appropriate sentences by applying different generation algorithms depending on the category of each student. Some or all of the above-described processing in the generation unit can be performed using, or without, a generation AI. For example, the generation unit can input category data of each student into the generation AI and cause the generation AI to apply the generation algorithm.

[0071] The generation unit can estimate the emotion of each student and adjust the length of the sentences based on the estimated emotion. For example, the generation unit can estimate the emotion of each student and adjust the length of the sentences based on the estimated emotion. For example, if each student is relaxed, the generation unit can generate longer sentences. If each student is nervous, the generation unit can also generate short, concise sentences. If each student is excited, the generation unit can also generate sentences that include detailed explanations. This allows the generation unit to generate more appropriate sentences by adjusting the length of the sentences according to each student's emotion. 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 generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input emotion data of each student into the generation AI and have the generation AI adjust the length of the sentences.

[0072] The generation unit can determine the priority of sentences based on the submission time of each student when generating sentences. For example, the generation unit determines the priority of sentences based on the submission time of each student when generating sentences. For example, the generation unit prioritizes generating sentences for students whose submission deadlines are approaching. The generation unit can also postpone generating sentences for students whose submission deadlines are further away. Furthermore, the generation unit can urgently generate sentences for students whose submission deadlines have passed. In this way, the generation unit can efficiently generate sentences by determining the priority of sentences based on the submission time of each student. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input submission time data for each student into the generation AI and have the generation AI determine the priority of sentences.

[0073] The generation unit can adjust the order of sentences based on the relevance of each student when generating sentences. For example, the generation unit adjusts the order of sentences based on the relevance of each student when generating sentences. For example, the generation unit determines the order of sentences based on the relevance of each student's learning data. The generation unit can also determine the order of sentences based on the relevance of each student's attendance rate. Furthermore, the generation unit can determine the order of sentences based on the relevance of each student's essay content. In this way, the generation unit can generate more appropriate sentences by adjusting the order of sentences based on the relevance of each student. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, a generation AI. For example, the generation unit can input the relevance data of each student into the generation AI and cause the generation AI to adjust the order of the sentences.

[0074] The providing unit can estimate the emotions of each student and adjust the display method of the provided text based on the estimated emotions. For example, the providing unit can estimate the emotions of each student and adjust the display method of the provided text based on the estimated emotions. For example, if each student is nervous, the providing unit can provide a simple, highly visible display method. If each student is relaxed, the providing unit can also provide a display method that includes detailed information. Furthermore, if each student is in a hurry, the providing unit can also provide a display method that focuses on the main points. This allows the providing unit to adjust the display method of the provided text according to each student's emotions, enabling more appropriate display. Emotion estimation is achieved 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 providing unit can be performed using, for example, the generation AI. For example, the providing unit can input each student's emotion data into the generation AI and have the generation AI adjust the display method.

[0075] The providing unit can select an appropriate format based on each school's past format data at the time of providing. For example, the providing unit selects the optimal format by referring to each school's past format data at the time of providing. For example, the providing unit selects the optimal format by referring to each school's past report card format. The providing unit can also select the optimal format by referring to each school's past recommendation letter format. Furthermore, the providing unit can select the optimal format by referring to each school's past observation format. In this way, the providing unit can select the optimal format by referring to each school's past format data. Some or all of the above-described processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input each school's past format data into the generation AI and cause the generation AI to select a format.

[0076] The providing unit can customize the text based on the current format of each school at the time of providing. The providing unit, for example, customizes the text based on the current format of each school at the time of providing. For example, the providing unit customizes the text based on the current report card format of each school. The providing unit can also customize the text based on the current recommendation letter format of each school. Furthermore, the providing unit can customize the text based on the current observation format of each school. In this way, the providing unit can provide more appropriate text by customizing the text based on the current format of each school. Some or all of the above-mentioned processing in the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the current format data of each school into the generation AI and cause the generation AI to customize the text.

[0077] The providing unit can estimate the emotions of each student and determine the priority of sentences to be provided based on the estimated emotions. For example, the providing unit can estimate the emotions of each student and determine the priority of sentences to be provided based on the estimated emotions. For example, if each student is nervous, the providing unit can prioritize providing sentences to help them relax. Furthermore, if each student is relaxed, the providing unit can prioritize providing sentences containing detailed information. Furthermore, if each student is in a hurry, the providing unit can prioritize providing sentences that focus on the main points. In this way, the providing unit can prioritize the sentences to be provided based on each student's emotions, thereby providing more appropriate sentences. 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 providing unit can be performed, for example, using the generation AI, or without using the generation AI. For example, the providing unit can input each student's emotional data into the generating AI and have the generating AI determine the priority of sentences.

[0078] The providing unit can select an appropriate format based on the geographical location information of each school at the time of providing. For example, the providing unit selects the optimal format by taking into account the geographical location information of each school at the time of providing. For example, if each school is located in an urban area, the providing unit selects a format suitable for the urban area. Furthermore, if each school is located in a suburban area, the providing unit can also select a format suitable for the suburban area. Furthermore, if each school is located in a rural area, the providing unit can also select a format suitable for the rural area. In this way, the providing unit can select the optimal format by taking into account the geographical location information of each school. Some or all of the above-described processing in the providing unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the providing unit can input the geographical location information of each school into the generation AI and cause the generation AI to select a format.

[0079] The providing unit can analyze the social media activity of each school and propose a format at the time of providing the data. For example, the providing unit can analyze the social media activity of each school and propose a format at the time of providing the data. For example, the providing unit can analyze the social media activity of each school and propose an optimal format. The providing unit can also propose a format taking into account the frequency of posts on social media by each school. Furthermore, the providing unit can propose a format based on the number of followers on social media of each school. In this way, the providing unit can propose an optimal format by analyzing the social media activity of each school. Some or all of the above-mentioned processing by the providing unit may be performed using, or without, a generation AI. For example, the providing unit can input the social media activity data of each school into the generation AI and have the generation AI execute a format proposal.

[0080] The editing function can estimate the emotions of each student and make editing suggestions based on the estimated emotions. For example, the editing function can estimate the emotions of each student and make editing suggestions based on the estimated emotions. For example, if each student is relaxed, the editing function can make detailed editing suggestions. If each student is nervous, the editing function can also make concise editing suggestions. Furthermore, if each student is excited, the editing function can make editing suggestions that use a lot of positive expressions. This allows the editing function to make editing suggestions based on each student's emotions, enabling more appropriate editing. Emotion estimation is realized using the emotion estimation function, for example, with 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 editing function can be performed using, for example, the generation AI. For example, the editing function can input each student's emotion data into the generation AI and have the generation AI execute editing suggestions.

[0081] The editing function can suggest an appropriate editing method based on each student's past editing history during editing. For example, the editing function can suggest the optimal editing method by referring to each student's past editing history during editing. For example, the editing function can suggest the optimal editing method based on each student's past editing history. The editing function can also analyze each student's past editing patterns and suggest an efficient editing method. Furthermore, the editing function can make similar editing suggestions by referring to each student's past editing content. In this way, the editing function can suggest the optimal editing method by referring to each student's past editing history. Some or all of the above-mentioned processing in the editing function may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the editing function can input each student's past editing history data into a generation AI and have the generation AI execute an editing method suggestion.

[0082] The editing function can estimate each student's emotions and determine editing priorities based on the estimated emotions. For example, the editing function can estimate each student's emotions and determine editing priorities based on the estimated emotions. For example, if each student is nervous, the editing function can prioritize editing to relax them. Furthermore, if each student is relaxed, the editing function can prioritize detailed editing. Furthermore, if each student is in a hurry, the editing function can prioritize concise editing. This allows the editing function to determine editing priorities based on each student's emotions, enabling more appropriate editing. Emotion estimation is achieved using the emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the editing function can be performed using, for example, the generation AI, or without the generation AI. For example, the editing function can input each student's emotion data into the generation AI and have the generation AI determine the editing priorities.

[0083] The editing function can propose the optimal editing method by taking into account the device information of each school during editing. For example, the editing function can propose the optimal editing method by taking into account the device information of each school during editing. For example, the editing function can propose an editing method that matches the screen size of the device used by each school. The editing function can also propose an editing method that matches the input method (touch, keyboard, etc.) of the device used by each school. Furthermore, the editing function can propose an efficient editing method based on the performance of the device used by each school. In this way, the editing function can propose the optimal editing method by taking into account the device information of each school. Some or all of the above-mentioned processing in the editing function may be performed using, or without, a generation AI. For example, the editing function can input the device information of each school into the generation AI and have the generation AI execute the suggested editing method. === Hard Collateral 1-1 === Each of the multiple elements including the acquisition unit, generation unit, and provision unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit connects with each school's database via an API via the communication I / F 44 of the smart device 14 to acquire learning data, attendance rate, and essay data. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates sentences corresponding to each student using a generation AI based on the acquired data. The provision unit is realized by the control unit 46A of the smart device 14 and provides the generated sentences in accordance with the format of each school, and provides editing functions as needed. === Hard Collateral 1-2 === Each of the multiple elements, including the acquisition unit, generation unit, and provision 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 acquisition unit connects with each school's database via an API via the communication I / F 44 of the smart glasses 214 to acquire learning data, attendance rate, and essay data. The generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates sentences corresponding to each student using a generation AI based on the acquired data. The provision unit is realized by the control unit 46A of the smart glasses 214 and provides the generated sentences in accordance with each school's format and provides editing functions as needed. === Hard Collateral 1-3 === Each of the multiple elements including the acquisition unit, generation unit, and provision unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the acquisition unit connects with each school's database via an API via the communication I / F 44 of the headset type terminal 314 to acquire learning data, attendance rate, and essay data. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates sentences corresponding to each student using a generation AI based on the acquired data. The provision unit is realized by the control unit 46A of the headset type terminal 314, and provides the generated sentences in accordance with the format of each school, and provides editing functions as needed. === Hard Collateral 1-4 === Each of the multiple elements including the acquisition unit, generation unit, and provision unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the acquisition unit connects with each school's database via an API via the robot 414's communication I / F 44 to acquire learning data, attendance rate, and essay data. The generation unit is realized by the specific processing unit 290 of the data processing device 12, and generates sentences corresponding to each student using a generation AI based on the acquired data. The provision unit is realized by the control unit 46A of the robot 414, and provides the generated sentences in accordance with each school's format, and provides editing functions as needed.

[0084] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0085] When acquiring learning data for each student, the acquisition unit can adjust the data acquisition method taking into account each student's learning style. For example, visual data can be acquired preferentially for students with a visual learning style, and audio data can be acquired preferentially for students with an auditory learning style. In addition, experimental and practical data can be acquired preferentially for students with a practical learning style. This allows the acquisition unit to acquire optimal data according to each student's learning style.

[0086] When analyzing each student's learning data, the generation unit can generate prompts taking into account each student's learning goals. For example, for a student aiming for high grades in a specific subject, the generation unit can generate prompts related to that subject, and for a student aiming to improve their overall grades, the generation unit can generate balanced prompts. In addition, for a student who wants to master a specific skill, the generation unit can generate prompts related to that skill. In this way, the generation unit can generate prompts according to each student's learning goals.

[0087] When providing the generated sentences, the providing unit can adjust the content of the sentences taking into consideration the learning progress of each student. For example, sentences containing many encouraging words can be provided to students whose learning progress is lagging, and sentences encouraging further challenges can be provided to students whose learning progress is going well. In addition, sentences containing many praising words can be provided to students whose learning progress is very good. In this way, the providing unit can provide appropriate sentences according to the learning progress of each student.

[0088] When providing an editing function for generated text, the provider can make editing suggestions taking into account each student's learning history. For example, for a student who has struggled in a particular subject in the past, specific improvements in that subject can be suggested, and for a student who has achieved excellent grades in the past, suggestions can be made for further improvement. In addition, for a student who has had low attendance rates in the past, suggestions can be made for improving attendance rates. This allows the provider to make appropriate editing suggestions based on each student's learning history.

[0089] The acquisition unit can estimate the emotions of each student and adjust the data acquisition method based on the estimated emotions. For example, if a student is feeling stressed, it can prioritize acquiring data in a relaxing environment, and if a student is concentrating, it can prioritize acquiring learning data. Also, if a student is tired, it can acquire data after a break. This allows the acquisition unit to select the optimal data acquisition method according to the emotions of each student.

[0090] When analyzing each student's past learning data, the acquisition unit can adjust the data acquisition method taking into account each student's learning environment. For example, for a student who studies a lot at home, home learning data can be acquired preferentially, and for a student who studies a lot at school, school learning data can be acquired preferentially. In addition, for a student who studies a lot online, online learning data can be acquired preferentially. This allows the acquisition unit to select the optimal data acquisition method according to each student's learning environment.

[0091] When acquiring data, the acquisition unit can adjust the frequency of data acquisition based on each student's current learning situation and areas of interest. For example, for students who have a strong interest in a particular subject, data on that subject can be acquired more frequently, and data acquisition frequency can be reduced for subjects with less interest. In addition, the acquisition unit can increase the data acquisition frequency for students whose learning progress is lagging, and decrease the data acquisition frequency for students whose progress is steady. This allows the acquisition unit to select the optimal data acquisition frequency according to each student's learning situation and areas of interest.

[0092] The acquisition unit can estimate the emotions of each student and customize the data acquisition method based on the estimated emotions. For example, if a student is relaxed, detailed data can be acquired, and if a student is nervous, brief data can be acquired. Also, if a student is excited, positive data can be acquired preferentially. This allows the acquisition unit to select the optimal data acquisition method according to the emotions of each student.

[0093] When acquiring data, the acquisition unit can adjust the data acquisition method taking into account the geographical location information of each student. For example, for students living in urban areas, data related to urban areas can be preferentially acquired, and for students living in suburban areas, data related to suburban areas can be preferentially acquired. Also, for students living in rural areas, data related to rural areas can be preferentially acquired. This allows the acquisition unit to select the optimal data acquisition method according to the geographical location information of each student.

[0094] When acquiring data, the acquisition unit can analyze each student's social media activity and acquire related data. For example, it analyzes each student's social media posts to acquire data related to learning. It can also determine the optimal timing for acquiring data by taking into account the time each student spends active on social media. Furthermore, it can acquire related learning data based on each student's interests on social media. This allows the acquisition unit to acquire related data by analyzing each student's social media activity.

[0095] The processing flow of the second embodiment will be briefly explained below.

[0096] Step 1: The acquisition unit connects to each school's database via API to acquire each student's learning data, attendance rate, and essay data. For example, the acquisition unit can acquire data from a learning management system or attendance management system. API types used include REST API and SOAP API. Learning data includes test results and assignment submission status. Attendance rate is calculated based on the number of days attended and absent. Essay data includes the length of the essay and evaluation criteria. Step 2: The generation unit generates sentences corresponding to each student based on the data acquired by the acquisition unit. The generation unit generates sentences using a generation AI. For example, the generation AI can use methods such as natural language generation technology or template-based generation. The generation unit analyzes each student's learning data, attendance rate, and essay content, and automatically generates appropriate prompts based on that. Step 3: The provider provides the text generated by the generator in accordance with the format of each school. The provider pre-registers the format of each school and automatically applies the generated text to that format. For example, the provider can adjust the document layout, font size, etc. Furthermore, the provider provides an editing function for the generated text, allowing teachers to review the generated text and make corrections or additions as necessary.

[0097] 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.

[0098] 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.

[0099] 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.

[0100] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0101] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0102] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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).

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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).

[0154] 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.

[0155] 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."

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0167] 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.

[0168] [Explanation of symbols]

[0169] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. The acquisition part connects with each school's database via API to acquire each student's learning data, attendance rate, and essay data. a generation unit that generates sentences corresponding to each student based on the data acquired by the acquisition unit; a providing unit that provides the text generated by the generating unit in accordance with the format of each school. A system characterized by:

2. The generation unit Analyzes each student's learning data, attendance rate, and written content, and automatically generates corresponding prompts based on that data. The system of claim 1 .

3. The providing unit Register the format of each school in advance and automatically apply the generated text to that format. The system of claim 1 .

4. The providing unit Provide an editing function for the generated text, allowing teachers to review the generated text and make corrections or additions as necessary. The system of claim 1 .

5. The acquisition unit Estimate each student's emotions and adjust the timing of data acquisition based on the estimated emotions. The system of claim 1 .

6. The acquisition unit Analyze each student's past learning data and select the appropriate data acquisition method The system of claim 1 .

7. The acquisition unit As data is acquired, it is filtered based on each student's current learning status and areas of interest. The system of claim 1 .

8. The acquisition unit Estimate each student's emotions and prioritize the data to be acquired based on the estimated emotions. The system of claim 1 .

Images