system

Abstract

We will provide appropriate learning plans for children from low-income families and provide a system that eliminates educational disparities caused by income inequality. [Solution] A system including a processing device including a registration component, which has a means for inputting and saving learner information; a processing device including an analysis component, which has a means for analyzing learner information; a processing device including a generation component, which has a means for generating a learning plan based on the analysis results; a processing device including a learning plan transmission component, which has a means for sending the generated learning plan to the learner's terminal; and a processing device including a feedback input component, which has a means for inputting progress and feedback from the learner and a means for re-executing the generation component based on the feedback.

Description

[Technical Field]

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

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

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

[0004] In today's education system, there is a problem in which parents' incomes can significantly affect children's learning environments. Income disparities create inequalities in learning opportunities, especially when it comes to entering university or preparatory schools. This makes it more difficult for children from low-income families to receive a sufficient education than children from high-income families. Therefore, there is a need to provide appropriate learning plans for children from low-income families and to provide a system that eliminates educational disparities caused by income disparities. [Means for solving the problem]

[0005] The present invention is a system that includes a registration component, an analysis component, a generation component, a study plan transmission component, and a feedback input component. First, the registration component inputs and saves learner information. Next, the analysis component analyzes the learner information, and the generation component generates a study plan based on the results. After that, the study plan transmission component sends the generated study plan to the learner's device. Furthermore, the feedback input component inputs progress and feedback from the learner, and based on that feedback, the generation component is run again to adjust the study plan. This makes it possible to provide study plans customized for each learner at low cost, thereby eliminating educational disparities caused by income disparities.

[0006] A "registration component" is the part of the system that has the ability to enter and store learner information.

[0007] The "analysis component" is a part of the system that has the function of analyzing the stored learner information and extracting the learner's characteristics.

[0008] The "generative component" is the part of the system that has the functionality to generate an optimal learning plan based on the analysis results.

[0009] The "study plan transmission component" is a part of the system that has the function of transmitting the generated study plan to the learner's terminal.

[0010] A "feedback input component" is a part of the system that has the ability to input progress and feedback from learners.

[0011] A "study plan" is a plan that includes customized learning content based on a learner's strong and weak subjects and educational aspirations.

[0012] "Student information" is information entered by the user, such as grade, favorite subjects, weak subjects, and educational aspirations.

[0013] A "database" is a storage device for storing learner information saved in the system and generated learning plans. [Brief explanation of the drawings]

[0014] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] 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.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] This invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. Learner information is input, and an optimal study plan is generated based on that information and provided to the learner. It also has the function of adjusting the study plan as appropriate based on feedback from the learner.

[0036] User registration and data entry

[0037] Users access the system and register as new users. When registering, they enter basic information such as their grade, favorite subjects, weak subjects, and desired school. This information is then sent to the server by the terminal.

[0038] Analyzing data and generating learning plans

[0039] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates an optimal learning plan based on the results of this analysis. This learning plan is customized for each learner and also references data on other learners stored in the database.

[0040] Providing study plans

[0041] The server sends the generated study plan to the user's device using the study plan sending component. The user checks the study plan received on their device and proceeds with their studies based on it.

[0042] Collecting feedback

[0043] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[0044] Specific examples

[0045] For example, consider the case where User A, a third-year junior high school student, uses this system. User A's best subject is math, his weakest subject is English, and he hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. The generated study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A studies according to it. Then, after a few weeks, User A provides feedback on his progress and difficult points, and the server uses that information to readjust the study plan. In this way, support is provided to continuously maximize learning effectiveness.

[0046] The present invention makes it possible to provide optimal learning plans tailored to each learner at low cost, effectively eliminating educational disparities caused by income disparities.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The user accesses the system's registration page and registers as a new user. They enter their user information (name, grade, favorite subjects, favorite subjects, desired school) and click the "Register" button.

[0050] Step 2:

[0051] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[0052] Step 3:

[0053] The server stores the received user data in a database, which is used for analysis.

[0054] Step 4:

[0055] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[0056] Step 5:

[0057] The server uses a generation component to generate an optimal learning plan based on the analysis results, which includes specific subject reinforcement and mastery strategies.

[0058] Step 6:

[0059] The server transmits the generated study plan to the user's terminal using the study plan transmission component, so that the user can receive the study plan.

[0060] Step 7:

[0061] The user begins studying based on the received study plan, and as they proceed with their studies, they input their progress and feedback about their studies into the system.

[0062] Step 8:

[0063] The device sends the feedback information entered by the user to the server, including the learning progress and points that were difficult.

[0064] Step 9:

[0065] The server stores the received feedback in a database and analyzes it again. Based on the feedback information, the effectiveness of the learning plan is evaluated.

[0066] Step 10:

[0067] The server re-executes the generation component as needed to generate a new learning plan that reflects the feedback, and then transmits the new learning plan to the user's device.

[0068] Step 11:

[0069] Users receive new study plans and continue their studies, which allows for continuous provision of optimal learning support for each individual learner.

[0070] Example 1

[0071] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0072] In modern society, income disparities between parents create educational disparities for their children, which is a problem. Providing optimal learning plans for individual learners is particularly costly, preventing many families from benefiting from them. Furthermore, tracking learners' daily progress and adjusting learning plans accordingly requires a significant amount of work. A system that can solve this problem is needed.

[0073] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0074] In this invention, the server includes a processing device including a user registration component and means for inputting and saving learner information, a processing device including an analysis component and means for analyzing the learner information and extracting characteristics based on the learner's favorite subjects, weak subjects, and educational aspirations, a processing device including a generation component with a generative AI model and means for generating a study plan based on the characteristic data, a processing device including a study plan transmission component and means for transmitting the generated study plan to the learner's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the learner, and means for re-executing the generation component based on the feedback and adjusting the study plan as appropriate. This effectively solves the problem of educational disparities caused by income disparities and makes it possible to provide optimal study plans for individual learners at low cost.

[0075] A "user registration component" is a processing device that provides functionality for entering and saving learner information.

[0076] The "analysis component" is a processing device that provides a function for analyzing stored learner information and extracting characteristics based on strong subjects, weak subjects, and educational aspirations.

[0077] A "generative AI model" is a model that generates optimal learning plans based on machine learning technology.

[0078] A "generative component" is a processing device that includes a generative AI model and provides functionality for generating a learning plan based on feature data.

[0079] The "learning plan transmission component" is a processing device that provides a function for transmitting the generated learning plan to the learner's terminal.

[0080] A "feedback input component" is a processing device that provides functionality for inputting progress and feedback from a learner.

[0081] "Characteristic data" is information extracted by the analysis component regarding a learner's strong subjects, weak subjects, and educational aspirations.

[0082] A "study plan" is a customized study plan based on the learner's strengths and weaknesses, and their educational aspirations.

[0083] The present invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. The program processing of this system will be specifically described below.

[0084] Overall system configuration

[0085] The system starts when a user accesses the system using a terminal and inputs and sends the necessary information. The server receives the information, generates a learning plan through analysis and generation components, and sends it to the user's terminal. The server also has the function of adjusting the learning plan based on feedback information from the user.

[0086] User registration component: Provides the ability to enter and save user information.

[0087] Analysis component: Analyzes stored user information and extracts characteristics based on strong and weak subjects and educational aspirations.

[0088] Generative component equipped with a generative AI model: Generates an optimal learning plan based on feature data.

[0089] Study plan sending component: Sends the generated study plan to the user's device.

[0090] Feedback input component: Has a function for inputting progress and feedback from the user.

[0091] Operation details of each component

[0092] User Registration Component

[0093] After accessing the system, users register. When registering, they enter basic information such as email address and password to create an account on the system. They then enter additional information such as their grade, favorite subjects, favorite subjects, and desired school. The entered information is sent to the server via the terminal and stored in the database. This process ensures that subsequent analysis and plan generation are more effective when users enter accurate information.

[0094] Analytics Components

[0095] The server runs an analysis component based on user information stored in the database. The analysis component processes the received learner information and extracts characteristics related to the learner's strong and weak subjects and educational aspirations. This process uses SQL queries and data mining techniques. This clarifies the individual learner's learning style and needs.

[0096] Generative components equipped with generative AI models

[0097] The generative component operates based on the analysis results. Using a generative AI model that leverages machine learning techniques, the generative component generates a learning plan based on the obtained feature data. This model utilizes existing data to provide a customized learning plan suited to the learner. For example, it may suggest specific learning content to further develop strong subjects or specific methods to overcome weak subjects.

[0098] Learning Plan Submission Component

[0099] The generated study plan is sent to the user's device via the study plan sending component. There are two ways to send the plan: by sending a notification to the email address entered by the user when registering, or by making it available for viewing on the system's dashboard. This allows users to check their study plan at any time and proceed with their studies based on it.

[0100] Feedback Input Component

[0101] As they study, users can use their devices to input feedback about their progress and learning into the system. This feedback includes detailed information such as whether they are making good progress or whether a particular subject is difficult. This feedback information is also sent back to the server and stored in a database.

[0102] Adjusting your learning plan based on feedback

[0103] The server analyzes the feedback using the feedback input component based on the saved feedback, and if necessary, re-runs the generation component to adjust the learning plan. This process ensures that the user always receives a plan that is optimized for their learning progress.

[0104] Specific use cases

[0105] For example, if User A, a third-year junior high school student, were to use this system, he or she would enter information that their favorite subject is math and their weakest subject is English. They would also enter their desire to attend a public high school. The server would then analyze this information, and the generative AI model would generate an optimal learning plan accordingly. This plan would include specific details on how to improve math and how to overcome English.

[0106] The generated study plan is sent to User A's device, and User A studies according to the plan. After a few weeks, User A provides feedback on their progress and difficult points. The server receives this feedback, analyzes and adjusts it again, and generates and sends a new study plan.

[0107] Prompt Sentence Examples

[0108] "User A, a third-year junior high school student, has entered the following information: his best subject is math, his worst subject is English, and his desired school is a public high school. Based on this information, please generate an optimal study plan for User A and provide specific study content for at least one week according to that plan."

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1:

[0111] User Registration:

[0112] A user accesses the system and registers. During this process, the user enters an email address and password, which are then sent to the server. The server stores the received email address and password in a database and creates a new account. Input: Email address, password. Output: Creation of a new account.

[0113] Step 2:

[0114] Enter your user information:

[0115] The user then enters detailed information such as grade, favorite subjects, weak subjects, and desired school. This information is also sent to the server via the terminal. The server stores the received information in a database. Input: grade, favorite subjects, weak subjects, desired school. Output: User information saved.

[0116] Step 3:

[0117] User information analysis:

[0118] The server retrieves user information stored in the database and sends it to the analysis component. The analysis component analyzes this information and extracts features based on the learner's strong and weak subjects, and educational aspirations. For example, it uses SQL queries to extract specific information from the database and then uses data mining algorithms to extract features. Input: Stored user information. Output: Extracted feature data.

[0119] Step 4:

[0120] Learning plan generation:

[0121] The server's generation component uses a generative AI model to generate an optimal learning plan based on the extracted feature data. The generative AI model uses machine learning algorithms to provide a customized learning plan tailored to the user's individual learning needs. Input: Feature data. Output: Customized learning plan.

[0122] Step 5:

[0123] Submit your study plan:

[0124] The server sends the generated learning plan to the user's device via the learning plan sending component. The sending is done via a notification to the email address registered by the user or via the dashboard within the system. Input: Generated learning plan. Output: Delivery of the learning plan to the user's device.

[0125] Step 6:

[0126] Feedback Input:

[0127] As the user progresses with their studies, they input feedback about their progress and learning from their device. Feedback includes learning progress and difficulties they are experiencing in specific subjects. Input: Learning progress and feedback information. Output: Feedback sent to the server via the device.

[0128] Step 7:

[0129] Feedback analysis and learning plan adjustment:

[0130] The server stores the received feedback information in a database. The server's feedback input component analyzes this feedback information and runs the generation component again to make any necessary adjustments to the learning plan. This generates a new learning plan optimized for the latest progress. Input: Feedback information. Output: Adjusted learning plan.

[0131] (Application example 1)

[0132] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0133] The challenge is to provide an environment where learners can make effective use of their travel time and study efficiently. There is also a need to reduce educational disparities based on parental income and ensure that all learners have equal opportunities to receive high-quality education. To realize such an environment, it is necessary to provide a learning support system inside self-driving vehicles.

[0134] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0135] In this invention, the server includes a processing device including a registration component, which inputs and saves learner information; a processing device including an analysis component, which analyzes the learner information; a processing device including a generation component, which generates a study plan based on the analysis results; a processing device including a study plan transmission component, which transmits the generated study plan to the learner's device; a processing device including a feedback input component, which inputs progress and feedback from the learner; and a processing device including a user interface corresponding to multiple modes of transportation, which displays study content on a device in an autonomous vehicle and supports study progress in real time. This makes it possible to make effective use of time while traveling, reduce educational disparities, and promote efficient learning.

[0136] A "registration component" is a processing device capable of inputting and storing learner information.

[0137] An "analysis component" is a processing device that has the function of analyzing input learner information.

[0138] A "generative component" is a processing device that has the functionality to generate a lesson plan based on the analyzed results.

[0139] The "learning plan transmission component" is a processing device that has the function of transmitting the generated learning plan to the learner's terminal.

[0140] A "feedback input component" is a processing device that has the function of inputting progress and feedback from a learner.

[0141] A "user interface" is a processing device that displays learning content on a terminal inside an autonomous vehicle and has the function of supporting learning progress in real time.

[0142] An "autonomous vehicle" is a vehicle that operates autonomously and drives itself without occupant intervention.

[0143] A "study plan" is a customized plan of learning activities based on information such as the learner's strong and weak subjects, and their educational aspirations.

[0144] User registration and data entry

[0145] First, the user registers on a terminal inside the autonomous vehicle. When registering, the user enters basic information such as their grade, favorite subjects, weak subjects, and educational aspirations. This information is then sent to the server by the terminal.

[0146] Analyzing data and generating learning plans

[0147] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates a study plan based on the analysis results. This plan is customized for each user and also references data from other users stored in the database.

[0148] Learning plan delivery and user interface

[0149] The server sends the generated learning plan to the user's terminal using a learning plan sending component. The terminal in the autonomous vehicle receives the learning plan, displays the learning content through a user interface, and supports the learning progress in real time.

[0150] Gather feedback and adjust your plan

[0151] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[0152] Hardware and Software Usage

[0153] The server uses Python, with SQLite or PostgreSQL as the database. Data analysis tools such as Pandas are used for data analysis, and machine learning models such as Scikit-Learn are used for the generation component. The terminal inside the autonomous vehicle uses a tablet or smartphone to display the learning plan and support feedback input.

[0154] Specific examples

[0155] For example, if User A, a third-year junior high school student, uses this system, his or her best subject is math, his or her weakest subject is English, and he or she hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. This study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A proceeds with his or her studies according to the plan. After a few weeks, User A provides feedback on his or her progress and difficult points, and the server uses that information to readjust the study plan.

[0156] Prompt Sentence Examples

[0157] "User A has been newly registered. Next, please send him the 'Study Plan Generation' prompt."

[0158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0159] Step 1:

[0160] User registration and data entry

[0161] The user registers a new account on a terminal inside the autonomous vehicle.

[0162] Input: Basic information such as the user's grade, favorite subjects, favorite subjects, and educational aspirations

[0163] Operation: This information is sent from the device to the server.

[0164] Output: User information is saved on the server

[0165] Step 2:

[0166] Data storage and analysis

[0167] The server stores the received user data in a database.

[0168] Input: User basic information

[0169] How it works: Analyze the saved data using data analysis tools such as Pandas to extract characteristics based on strong and weak subjects and educational aspirations.

[0170] Output: Feature-extracted data

[0171] Step 3:

[0172] Generate a learning plan

[0173] The server's generation component generates a learning plan based on the analysis results.

[0174] Input: extracted feature data

[0175] How it works: Using machine learning models such as Scikit-Learn, it automatically generates a study plan that includes ways to improve your strengths and overcome your weaknesses.

[0176] Output: personalized learning plan

[0177] Step 4:

[0178] Providing study plans

[0179] The server transmits the generated learning plan to the user's terminal using a learning plan transmission component.

[0180] Input: Personalized Learning Plan

[0181] Operation: Sending a plan from the server to the device

[0182] Output: The lesson plan displayed on the device

[0183] Step 5:

[0184] Learning and gathering feedback

[0185] The user follows the learning plan provided via the device and inputs feedback on progress and problems encountered during the learning process.

[0186] Input: User learning progress information, feedback

[0187] Action: The device sends the entered information to the server.

[0188] Output: Feedback data stored on the server

[0189] Step 6:

[0190] Analyze feedback and adjust plans

[0191] The server analyzes the feedback information and re-runs the generation component to adjust the learning plan as needed.

[0192] Input: Feedback data

[0193] How it works: The feedback information is analyzed using tools like Pandas, and a new learning plan is generated using the machine learning model again.

[0194] Output: Adjusted study plan

[0195] Step 7:

[0196] New learning plans available

[0197] The server then sends the adjusted study plan back to the user's device.

[0198] Input: Adjusted study plan

[0199] Action: Retransmission from server to device

[0200] Output: The new study plan displayed on your device

[0201] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0202] This invention is a system that automatically generates and provides a learning plan that takes into account the learner's emotions by combining an emotion engine. By recognizing the learner's emotions and reflecting that information in the learning plan, more effective learning support is realized.

[0203] User registration and data entry

[0204] Users access the system and register as new users. They enter user information (such as name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and register in the system. The registration information is sent to the server via the terminal.

[0205] Analyzing data and generating learning plans

[0206] The server stores the received user data in a database. The analysis component analyzes the user data and extracts the learner's characteristics. The generation component then generates an optimal learning plan based on the analysis results. During this process, the emotion engine analyzes the learner's emotional information and influences the generation of the learning plan. Specifically, the difficulty and volume of the learning content are adjusted taking into account the learner's emotional state (e.g., stress level and motivation level).

[0207] Providing study plans

[0208] The server uses a learning plan transmission component to send the generated learning plan to the user's device. The user then checks the learning plan on their device and proceeds with their studies according to the plan.

[0209] Collecting feedback

[0210] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[0211] Analyze feedback and adjust your learning plan

[0212] The server stores the received feedback in a database and analyzes it using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the learning plan to take into account the learner's latest emotional state.

[0213] Specific examples

[0214] For example, consider the case where User B, a third-year junior high school student, uses this system. User B enters that his or her favorite subject is science, his or her weakest subject is Japanese, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the user's characteristics. Next, the generation component generates an optimal study plan, and the emotion engine adjusts the plan's difficulty taking the stress level into account. This study plan is sent to User B's device, and User B proceeds with his or her studies according to the plan. After studying, User B enters his or her progress and current emotional state into the system as feedback, and the server readjusts the study plan based on this.

[0215] In this way, by combining an emotion engine, the present invention can provide a customized learning plan that corresponds to the individual emotional state of the learner, thereby achieving more effective learning support.

[0216] The processing flow will be explained below.

[0217] Step 1:

[0218] The user accesses the system's registration page and registers as a new user. They enter user information (name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and click the "Register" button.

[0219] Step 2:

[0220] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[0221] Step 3:

[0222] The server stores the received user data in a database, which is used to generate a learning plan.

[0223] Step 4:

[0224] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[0225] Step 5:

[0226] The server retrieves the user's emotional state data and runs an emotion engine that analyzes the user's emotional state (e.g., stress level and motivation state).

[0227] Step 6:

[0228] The server uses a generation component to generate an optimal learning plan based on the analysis results and the analysis results of the emotion engine, the learning plan including content based on the user's strengths, weaknesses, and emotional state.

[0229] Step 7:

[0230] The server uses a learning plan sending component to send the generated learning plan to the user's terminal, so that the user can receive the learning plan.

[0231] Step 8:

[0232] The user begins studying based on the received study plan, and as they proceed with their studies, they can input feedback about their progress and learning into the system.

[0233] Step 9:

[0234] The terminal transmits the feedback information and emotional state input by the user to the server. The feedback information includes the learning progress, difficult points, and the current emotional state (e.g., fatigue or a sense of accomplishment).

[0235] Step 10:

[0236] The server stores the received feedback in a database, and the stored feedback information and emotional state are used to adjust the learning plan.

[0237] Step 11:

[0238] The server utilizes the feedback input component to analyze the feedback and emotional state. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback and emotional information.

[0239] Step 12:

[0240] The server then transmits the newly generated study plan to the user's device again, allowing the user to receive the updated study plan.

[0241] Step 13:

[0242] The user then resumes their studies based on the updated study plan, which allows the system to continuously provide optimal learning support for each individual learner, taking into account their emotional state.

[0243] Example 2

[0244] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0245] Conventional learning support systems provide learning plans without taking into account the learner's emotional state, making it difficult to provide appropriate learning support based on the learner's mental state. As a result, there are concerns that the learner's motivation may decrease and stress may increase. Therefore, there is a need to provide learning plans that appropriately reflect the learner's emotional state.

[0246] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting and saving user information, means for analyzing the user information and the emotional state, and means for adjusting the content and difficulty of the study plan using an emotion engine. This makes it possible to provide an appropriate study plan according to the learner's emotional state, thereby maintaining the learner's motivation and reducing stress.

[0247] A "registration component" is a means for entering and storing learner information.

[0248] "User information" is information including the learner's name, grade, favorite subjects, least favorite subjects, educational aspirations, and emotional state.

[0249] The "analysis component" is a means for acquiring and analyzing user information to analyze the learner's characteristics and emotional state.

[0250] "Emotional information" is information that indicates the learner's current emotional state, including stress level and motivation level.

[0251] The "generative component" is a means of generating a learning plan based on the analysis results and adjusting the content and difficulty level using an emotion engine.

[0252] The "emotion engine" is a function that analyzes the learner's emotional state and adjusts the content and difficulty of the learning plan based on the results.

[0253] The "study plan transmission component" is a means for transmitting the generated study plan to the user's terminal.

[0254] A "terminal" is an electronic device that a user uses to review a learning plan and enter feedback.

[0255] The "feedback input component" is a means for inputting progress and feedback from the learner, and is used to regenerate the learning plan.

[0256] A "study plan" is a customized study plan that takes into account the user's strong and weak subjects, academic aspirations, and emotional state.

[0257] "Server" is a central processing unit that stores and analyzes user information, and generates and transmits study plans.

[0258] This invention is a system that automatically generates a learning plan that takes into account the learner's emotions. This system is mainly composed of three elements: a server, a terminal, and a user. These elements work together to provide a customized learning plan that corresponds to the learner's individual emotional state.

[0259] User registration and data entry

[0260] Users access the system and first register. When registering, they enter information such as their name, grade, favorite subjects, favorite subjects, desired school, and emotional state (e.g., stress level and motivation). This information is sent to the server via a terminal. Terminals can be electronic devices such as PCs, tablets, and smartphones.

[0261] Data storage

[0262] The server stores the received user information in a database. This storage process uses a database management system (e.g., MySQL (registered trademark), PostgreSQL). The stored data is used for later analysis and for generating a learning plan.

[0263] Analyzing the data

[0264] The server's built-in analysis component retrieves user information from the database and analyzes it. The analysis covers learning progress by grade, trends in strong and weak subjects, the level of desired educational destination, emotional state, etc. Data analysis tools such as Python and R are used for this analysis.

[0265] Generate a learning plan

[0266] The generation component generates an optimal learning plan based on the analysis results of the analysis component. At this time, the emotion engine analyzes the learner's emotional state and adjusts the content and difficulty of the plan. For example, a user with a high stress level will be suggested learning content that is less stressful.

[0267] Submit your study plan

[0268] The server sends the generated learning plan to the user's device via the learning plan sending component, using a communication protocol such as HTTP or WebSocket.

[0269] Review and execute your study plan

[0270] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the learning content and proceed with their learning according to the plan.

[0271] Collecting feedback

[0272] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[0273] Feedback storage and analysis

[0274] The server stores the received feedback information in a database. The feedback input component analyzes the stored data and generates a new learning plan based on the analysis results. The emotion engine is also involved in this process, providing a plan that reflects the latest emotional state.

[0275] Specific examples

[0276] For example, if User B, a third-year junior high school student, uses this system, he or she accesses the system and registers his or her name, grade, favorite subject (science), least favorite subject (Japanese), desired school, and emotional state (current stress level). This information is sent to the server via the terminal.

[0277] The server receives the information and stores it in a database. After storage, the analysis component analyzes the data. Based on the analysis results, the generation component generates an optimal learning plan, and the emotion engine adjusts the difficulty of the plan taking into account the stress level. This learning plan is then sent to User B's device via the learning plan sending component.

[0278] User B checks the plan received on his / her device and begins studying according to the plan. After studying, he / she inputs his / her progress and emotional state as feedback and sends it to the server via his / her device. The server analyzes the feedback and generates a new study plan. In this way, the system constantly updates the study plan based on the latest user situation.

[0279] Prompt Sentence Examples

[0280] You can simulate specific scenarios by feeding prompts like the following into the generative AI model:

[0281] "Please tell us the steps for a third-year junior high school student to use the system to generate a lesson plan that takes emotional information into account. For example, please explain the case of a user who is good at science but not good at Japanese."

[0282] In this way, this system provides a learning plan that takes into account the learner's emotional state, providing effective learning support.

[0283] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0284] Step 1:

[0285] Users access the system and register. The information they enter includes their name, grade, favorite subjects, favorite subjects, desired school, emotional state (e.g., stress level), etc. This information is entered into the terminal through an input form, and the contents are sent to the server. Input: User information, Output: Data sent to the server.

[0286] Step 2:

[0287] The server stores the received user information in a database. A database management system (e.g., MySQL, PostgreSQL) is used for the storage process. This allows user information to be stored safely for a long period of time. Input: Transmitted user information, Output: Data stored in the database.

[0288] Step 3:

[0289] The analysis component installed on the server retrieves user information from the database and performs analysis. The analysis uses indicators such as learning progress by grade, trends in strong and weak subjects, the level of desired educational institution, and emotional state. Data analysis tools such as Python and R are used for this analysis. Input: User information in the database, Output: Analysis results.

[0290] Step 4:

[0291] The generation component receives the analysis results from the analysis component and generates an optimal study plan. The emotion engine is involved in this process, adjusting the content and difficulty of the plan taking into account the user's emotional state. Specifically, a user with a high stress level will be provided with a reduced study plan consisting of relatively easy content. Input: Analysis results, Output: Optimized study plan.

[0292] Step 5:

[0293] The server sends the generated learning plan to the user's device using the learning plan sending component. This sending uses a communication protocol such as HTTP or WebSocket. Input: Generated learning plan, Output: Data sent to the user's device.

[0294] Step 6:

[0295] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the study content and carry out their daily study plan. Input: Sent learning plan, Output: User starts studying.

[0296] Step 7:

[0297] The user inputs feedback about their learning progress and emotional state into the system. This includes their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). Feedback information is sent to the server via the terminal. Input: User feedback, Output: Data sent to the server.

[0298] Step 8:

[0299] The server stores the received feedback information in a database. The feedback input component analyzes the stored data, and the generation component is executed again based on the analysis results to generate a new learning plan. The emotion engine is also utilized this time, providing a plan that reflects the learner's latest emotional state. Input: Feedback information, Output: Newly generated learning plan.

[0300] (Application example 2)

[0301] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0302] Existing work plan generation systems are unable to take into account the user's emotional state, which can lead to reduced work efficiency. It is also difficult to dynamically adjust plans based on the user's strengths and weaknesses, as well as their progress. This leads to the accumulation of stress and fatigue in the user, resulting in reduced work productivity.

[0303] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a processing device including a registration component and means for inputting and saving user information, a processing device including an analysis component and means for analyzing the user information, a processing device including a generation component and means for generating a work plan based on the analysis results, a processing device including an emotion engine and means for analyzing the user's emotional state and influencing the work plan, a processing device including a work plan transmission component and means for transmitting the generated work plan to the user's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the user, and means for re-executing the generation component based on the feedback. This enables flexible generation and adjustment of work plans that take into account the user's emotional state and progress.

[0304] A "registration component" is a processing device that has a means for inputting and storing user information.

[0305] "User information" refers to basic information about the user (such as name, favorite tasks, least favorite tasks, emotional state, etc.).

[0306] An "analysis component" is a processing device that has means for analyzing user information and extracting its characteristics.

[0307] A "generation component" is a processing device that has means for generating an optimal work plan based on the analysis results.

[0308] The "emotion engine" is a processing device that has the means to analyze the user's emotional state and reflect that information in the work plan.

[0309] A "work plan" refers to specific work procedures and schedules that are created taking into account the user's characteristics and emotional state.

[0310] The "work plan transmission component" is a processing device that has means for transmitting the generated work plan to the user's terminal.

[0311] A "feedback input component" is a processing device that has means for inputting feedback from a user regarding progress and emotional state.

[0312] "Feedback" refers to input information about the progress of the task and the user's emotional state after the task.

[0313] This invention is a system that automatically generates and provides work plans by combining an emotion engine and taking into account the user's emotional state. Specifically, by recognizing the user's emotions and reflecting that information in the work plan, more effective work support is realized.

[0314] User registration and data entry

[0315] A user accesses the system and enters and saves basic information through the registration component. The user information includes name, favorite tasks, least favorite tasks, and emotional state. This information is sent from the user's terminal to the server and stored in the server's database.

[0316] Analyzing data and generating work plans

[0317] The server stores the received user data in a database. The analysis component then analyzes this data and extracts the user's characteristics. The generation component generates an optimal work plan based on the analysis results. The emotion engine is involved in this process, adjusting the difficulty and amount of the work content based on the user's emotional state (such as stress level and motivation level).

[0318] Providing a work plan

[0319] The server sends the generated work plan to the user's terminal via the work plan sending component. The user checks the work plan on their own terminal and proceeds with the work according to the plan.

[0320] Collecting feedback

[0321] After completing the task, the user inputs feedback about their progress and emotional state into the system. The feedback includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue, accomplishment). This information is sent from the user's device to the server.

[0322] Analyze feedback and adjust work plan

[0323] The server stores the received feedback in a database and analyzes it through the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the work plan to take into account the user's latest emotional state.

[0324] Specific examples

[0325] As a concrete example, consider a scenario in which Worker A at a factory uses this system. Worker A inputs that his or her strongest task is assembly, his or her weakest task is welding, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the worker's characteristics. Next, the generation component generates an optimal work plan, and the emotion engine adjusts the plan's difficulty by taking the worker's stress level into account. This work plan is sent to Worker A's device, and Worker A proceeds with the work according to the plan. After the work, Worker A inputs his or her progress and current emotional state into the system as feedback, and the server readjusts the work plan based on this.

[0326] Hardware and software used

[0327] This system requires a wearable device (e.g., a device that acquires vital signs) as an emotion sensor, a data transmission terminal, and a work support computer system. The software used includes Python for data analysis, MySQL for database management, and a machine learning model for feedback analysis.

[0328] Prompt Sentence Examples

[0329] "Generate the optimal work plan for the user's current stressful situation."

[0330] This enables flexible creation and adjustment of work plans that take into account the user's emotional state and progress.

[0331] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0332] Step 1:

[0333] A user accesses the system using a terminal. The user inputs basic information such as name, favorite tasks, least favorite tasks, and emotional state. This input information is sent from the terminal to the server and stored in the server's database. The input data is saved as properly formatted data by the registration component.

[0334] Step 2:

[0335] The server retrieves user information stored in the database. The analysis component uses this information to analyze the user's characteristics. Specifically, it extracts information such as the user's strengths and weaknesses, their current emotional state, and so on. This analysis data is used in the next phase of work plan generation.

[0336] Step 3:

[0337] The server's generation component generates an optimal work plan based on the analysis data. Here, the emotion engine analyzes the user's emotional state and adjusts the difficulty and amount of the work plan based on the results. For example, if the stress level is high, adjustments may be made such as reducing the amount of work. The generated work plan is temporarily stored in a database.

[0338] Step 4:

[0339] The server sends the work plan generated using the work plan sending component to the user's device. The user checks the provided work plan on their device and starts working according to the plan. This plan is optimized taking into account the user's emotional state, allowing the user to work efficiently.

[0340] Step 5:

[0341] After completing the task, the user again uses the device to input feedback about their progress and emotional state into the system. This feedback information includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). This information is sent from the device to the server and stored in a database.

[0342] Step 6:

[0343] The server analyzes the received feedback using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan. The emotion engine also participates in this process, generating a plan that reflects the latest emotional state. The newly generated work plan is then sent back to the user's device.

[0344] Step 7:

[0345] The user then checks the work plan again and proceeds with the work according to the adjusted plan. This cycle is repeated depending on the user's emotional state and work progress, making it possible to provide optimal work support.

[0346] 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.

[0347] 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> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0348] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0349] [Second embodiment]

[0350] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0351] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0352] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0353] 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.

[0354] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0355] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0356] 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. 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.

[0357] 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.

[0358] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0359] 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.

[0360] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0361] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0362] This invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. Learner information is input, and an optimal study plan is generated based on that information and provided to the learner. It also has the function of adjusting the study plan as appropriate based on feedback from the learner.

[0363] User registration and data entry

[0364] Users access the system and register as new users. When registering, they enter basic information such as their grade, favorite subjects, weak subjects, and desired school. This information is then sent to the server by the terminal.

[0365] Analyzing data and generating learning plans

[0366] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates an optimal learning plan based on the results of this analysis. This learning plan is customized for each learner and also references data on other learners stored in the database.

[0367] Providing study plans

[0368] The server sends the generated study plan to the user's device using the study plan sending component. The user checks the study plan received on their device and proceeds with their studies based on it.

[0369] Collecting feedback

[0370] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[0371] Specific examples

[0372] For example, consider the case where User A, a third-year junior high school student, uses this system. User A's best subject is math, his weakest subject is English, and he hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. The generated study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A studies according to it. Then, after a few weeks, User A provides feedback on his progress and difficult points, and the server uses that information to readjust the study plan. In this way, support is provided to continuously maximize learning effectiveness.

[0373] The present invention makes it possible to provide optimal learning plans tailored to each learner at low cost, effectively eliminating educational disparities caused by income disparities.

[0374] The processing flow will be explained below.

[0375] Step 1:

[0376] The user accesses the system's registration page and registers as a new user. They enter their user information (name, grade, favorite subjects, favorite subjects, desired school) and click the "Register" button.

[0377] Step 2:

[0378] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[0379] Step 3:

[0380] The server stores the received user data in a database, which is used for analysis.

[0381] Step 4:

[0382] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[0383] Step 5:

[0384] The server uses a generation component to generate an optimal learning plan based on the analysis results, which includes specific subject reinforcement and mastery strategies.

[0385] Step 6:

[0386] The server transmits the generated study plan to the user's terminal using the study plan transmission component, so that the user can receive the study plan.

[0387] Step 7:

[0388] The user begins studying based on the received study plan, and as they proceed with their studies, they input their progress and feedback about their studies into the system.

[0389] Step 8:

[0390] The device sends the feedback information entered by the user to the server, including the learning progress and points that were difficult.

[0391] Step 9:

[0392] The server stores the received feedback in a database and analyzes it again. Based on the feedback information, the effectiveness of the learning plan is evaluated.

[0393] Step 10:

[0394] The server re-executes the generation component as needed to generate a new learning plan that reflects the feedback, and then transmits the new learning plan to the user's device.

[0395] Step 11:

[0396] Users receive new study plans and continue their studies, which allows for continuous provision of optimal learning support for each individual learner.

[0397] Example 1

[0398] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0399] In modern society, income disparities between parents create educational disparities for their children, which is a problem. Providing optimal learning plans for individual learners is particularly costly, preventing many families from benefiting from them. Furthermore, tracking learners' daily progress and adjusting learning plans accordingly requires a significant amount of work. A system that can solve this problem is needed.

[0400] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0401] In this invention, the server includes a processing device including a user registration component and means for inputting and saving learner information, a processing device including an analysis component and means for analyzing the learner information and extracting characteristics based on the learner's favorite subjects, weak subjects, and educational aspirations, a processing device including a generation component with a generative AI model and means for generating a study plan based on the characteristic data, a processing device including a study plan transmission component and means for transmitting the generated study plan to the learner's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the learner, and means for re-executing the generation component based on the feedback and adjusting the study plan as appropriate. This effectively solves the problem of educational disparities caused by income disparities and makes it possible to provide optimal study plans for individual learners at low cost.

[0402] A "user registration component" is a processing device that provides functionality for entering and saving learner information.

[0403] The "analysis component" is a processing device that provides a function for analyzing stored learner information and extracting characteristics based on strong subjects, weak subjects, and educational aspirations.

[0404] A "generative AI model" is a model that generates optimal learning plans based on machine learning technology.

[0405] A "generative component" is a processing device that includes a generative AI model and provides functionality for generating a learning plan based on feature data.

[0406] The "learning plan transmission component" is a processing device that provides a function for transmitting the generated learning plan to the learner's terminal.

[0407] A "feedback input component" is a processing device that provides functionality for inputting progress and feedback from a learner.

[0408] "Characteristic data" is information extracted by the analysis component regarding a learner's strong subjects, weak subjects, and educational aspirations.

[0409] A "study plan" is a customized study plan based on the learner's strengths and weaknesses, and their educational aspirations.

[0410] The present invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. The program processing of this system will be specifically described below.

[0411] Overall system configuration

[0412] The system starts when a user accesses the system using a terminal and inputs and sends the necessary information. The server receives the information, generates a learning plan through analysis and generation components, and sends it to the user's terminal. The server also has the function of adjusting the learning plan based on feedback information from the user.

[0413] User registration component: Provides the ability to enter and save user information.

[0414] Analysis component: Analyzes stored user information and extracts characteristics based on strong and weak subjects and educational aspirations.

[0415] Generative component equipped with a generative AI model: Generates an optimal learning plan based on feature data.

[0416] Study plan sending component: Sends the generated study plan to the user's device.

[0417] Feedback input component: Has a function for inputting progress and feedback from the user.

[0418] Operation details of each component

[0419] User Registration Component

[0420] After accessing the system, users register. When registering, they enter basic information such as email address and password to create an account on the system. They then enter additional information such as their grade, favorite subjects, favorite subjects, and desired school. The entered information is sent to the server via the terminal and stored in the database. This process ensures that subsequent analysis and plan generation are more effective when users enter accurate information.

[0421] Analytics Components

[0422] The server runs an analysis component based on user information stored in the database. The analysis component processes the received learner information and extracts characteristics related to the learner's strong and weak subjects and educational aspirations. This process uses SQL queries and data mining techniques. This clarifies the individual learner's learning style and needs.

[0423] Generative components equipped with generative AI models

[0424] The generative component operates based on the analysis results. Using a generative AI model that leverages machine learning techniques, the generative component generates a learning plan based on the obtained feature data. This model utilizes existing data to provide a customized learning plan suited to the learner. For example, it may suggest specific learning content to further develop strong subjects or specific methods to overcome weak subjects.

[0425] Learning Plan Submission Component

[0426] The generated study plan is sent to the user's device via the study plan sending component. There are two ways to send the plan: by sending a notification to the email address entered by the user when registering, or by making it available for viewing on the system's dashboard. This allows users to check their study plan at any time and proceed with their studies based on it.

[0427] Feedback Input Component

[0428] As they study, users can use their devices to input feedback about their progress and learning into the system. This feedback includes detailed information such as whether they are making good progress or whether a particular subject is difficult. This feedback information is also sent back to the server and stored in a database.

[0429] Adjusting your learning plan based on feedback

[0430] The server analyzes the feedback using the feedback input component based on the saved feedback, and if necessary, re-runs the generation component to adjust the learning plan. This process ensures that the user always receives a plan that is optimized for their learning progress.

[0431] Specific use cases

[0432] For example, if User A, a third-year junior high school student, were to use this system, he or she would enter information that their favorite subject is math and their weakest subject is English. They would also enter their desire to attend a public high school. The server would then analyze this information, and the generative AI model would generate an optimal learning plan accordingly. This plan would include specific details on how to improve math and how to overcome English.

[0433] The generated study plan is sent to User A's device, and User A studies according to the plan. After a few weeks, User A provides feedback on their progress and difficult points. The server receives this feedback, analyzes and adjusts it again, and generates and sends a new study plan.

[0434] Prompt Sentence Examples

[0435] "User A, a third-year junior high school student, has entered the following information: his best subject is math, his worst subject is English, and his desired school is a public high school. Based on this information, please generate an optimal study plan for User A and provide specific study content for at least one week according to that plan."

[0436] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0437] Step 1:

[0438] User Registration:

[0439] A user accesses the system and registers. During this process, the user enters an email address and password, which are then sent to the server. The server stores the received email address and password in a database and creates a new account. Input: Email address, password. Output: Creation of a new account.

[0440] Step 2:

[0441] Enter your user information:

[0442] The user then enters detailed information such as grade, favorite subjects, weak subjects, and desired school. This information is also sent to the server via the terminal. The server stores the received information in a database. Input: grade, favorite subjects, weak subjects, desired school. Output: User information saved.

[0443] Step 3:

[0444] User information analysis:

[0445] The server retrieves user information stored in the database and sends it to the analysis component. The analysis component analyzes this information and extracts features based on the learner's strong and weak subjects, and educational aspirations. For example, it uses SQL queries to extract specific information from the database and then uses data mining algorithms to extract features. Input: Stored user information. Output: Extracted feature data.

[0446] Step 4:

[0447] Learning plan generation:

[0448] The server's generation component uses a generative AI model to generate an optimal learning plan based on the extracted feature data. The generative AI model uses machine learning algorithms to provide a customized learning plan tailored to the user's individual learning needs. Input: Feature data. Output: Customized learning plan.

[0449] Step 5:

[0450] Submit your study plan:

[0451] The server sends the generated learning plan to the user's device via the learning plan sending component. The sending is done via a notification to the email address registered by the user or via the dashboard within the system. Input: Generated learning plan. Output: Delivery of the learning plan to the user's device.

[0452] Step 6:

[0453] Feedback Input:

[0454] As the user progresses with their studies, they input feedback about their progress and learning from their device. Feedback includes learning progress and difficulties they are experiencing in specific subjects. Input: Learning progress and feedback information. Output: Feedback sent to the server via the device.

[0455] Step 7:

[0456] Feedback analysis and learning plan adjustment:

[0457] The server stores the received feedback information in a database. The server's feedback input component analyzes this feedback information and runs the generation component again to make any necessary adjustments to the learning plan. This generates a new learning plan optimized for the latest progress. Input: Feedback information. Output: Adjusted learning plan.

[0458] (Application example 1)

[0459] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0460] The challenge is to provide an environment where learners can make effective use of their travel time and study efficiently. There is also a need to reduce educational disparities based on parental income and ensure that all learners have equal opportunities to receive high-quality education. To realize such an environment, it is necessary to provide a learning support system inside self-driving vehicles.

[0461] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0462] In this invention, the server includes a processing device including a registration component, which inputs and saves learner information; a processing device including an analysis component, which analyzes the learner information; a processing device including a generation component, which generates a study plan based on the analysis results; a processing device including a study plan transmission component, which transmits the generated study plan to the learner's device; a processing device including a feedback input component, which inputs progress and feedback from the learner; and a processing device including a user interface corresponding to multiple modes of transportation, which displays study content on a device in an autonomous vehicle and supports study progress in real time. This makes it possible to make effective use of time while traveling, reduce educational disparities, and promote efficient learning.

[0463] A "registration component" is a processing device capable of inputting and storing learner information.

[0464] An "analysis component" is a processing device that has the function of analyzing input learner information.

[0465] A "generative component" is a processing device that has the functionality to generate a lesson plan based on the analyzed results.

[0466] The "learning plan transmission component" is a processing device that has the function of transmitting the generated learning plan to the learner's terminal.

[0467] A "feedback input component" is a processing device that has the function of inputting progress and feedback from a learner.

[0468] A "user interface" is a processing device that displays learning content on a terminal inside an autonomous vehicle and has the function of supporting learning progress in real time.

[0469] An "autonomous vehicle" is a vehicle that operates autonomously and drives itself without occupant intervention.

[0470] A "study plan" is a customized plan of learning activities based on information such as the learner's strong and weak subjects, and their educational aspirations.

[0471] User registration and data entry

[0472] First, the user registers on a terminal inside the autonomous vehicle. When registering, the user enters basic information such as their grade, favorite subjects, weak subjects, and educational aspirations. This information is then sent to the server by the terminal.

[0473] Analyzing data and generating learning plans

[0474] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates a study plan based on the analysis results. This plan is customized for each user and also references data from other users stored in the database.

[0475] Learning plan delivery and user interface

[0476] The server sends the generated learning plan to the user's terminal using a learning plan sending component. The terminal in the autonomous vehicle receives the learning plan, displays the learning content through a user interface, and supports the learning progress in real time.

[0477] Gather feedback and adjust your plan

[0478] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[0479] Hardware and Software Usage

[0480] The server uses Python, with SQLite or PostgreSQL as the database. Data analysis tools such as Pandas are used for data analysis, and machine learning models such as Scikit-Learn are used for the generation component. The terminal inside the autonomous vehicle uses a tablet or smartphone to display the learning plan and support feedback input.

[0481] Specific examples

[0482] For example, if User A, a third-year junior high school student, uses this system, his or her best subject is math, his or her weakest subject is English, and he or she hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. This study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A proceeds with his or her studies according to the plan. After a few weeks, User A provides feedback on his or her progress and difficult points, and the server uses that information to readjust the study plan.

[0483] Prompt Sentence Examples

[0484] "User A has been newly registered. Next, please send him the 'Study Plan Generation' prompt."

[0485] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0486] Step 1:

[0487] User registration and data entry

[0488] The user registers a new account on a terminal inside the autonomous vehicle.

[0489] Input: Basic information such as the user's grade, favorite subjects, favorite subjects, and educational aspirations

[0490] Operation: This information is sent from the device to the server.

[0491] Output: User information is saved on the server

[0492] Step 2:

[0493] Data storage and analysis

[0494] The server stores the received user data in a database.

[0495] Input: User basic information

[0496] How it works: Analyze the saved data using data analysis tools such as Pandas to extract characteristics based on strong and weak subjects and educational aspirations.

[0497] Output: Feature-extracted data

[0498] Step 3:

[0499] Generate a learning plan

[0500] The server's generation component generates a learning plan based on the analysis results.

[0501] Input: extracted feature data

[0502] How it works: Using machine learning models such as Scikit-Learn, it automatically generates a study plan that includes ways to improve your strengths and overcome your weaknesses.

[0503] Output: personalized learning plan

[0504] Step 4:

[0505] Providing study plans

[0506] The server transmits the generated learning plan to the user's terminal using a learning plan transmission component.

[0507] Input: Personalized Learning Plan

[0508] Operation: Sending a plan from the server to the device

[0509] Output: The lesson plan displayed on the device

[0510] Step 5:

[0511] Learning and gathering feedback

[0512] The user follows the learning plan provided via the device and inputs feedback on progress and problems encountered during the learning process.

[0513] Input: User learning progress information, feedback

[0514] Action: The device sends the entered information to the server.

[0515] Output: Feedback data stored on the server

[0516] Step 6:

[0517] Analyze feedback and adjust plans

[0518] The server analyzes the feedback information and re-runs the generation component to adjust the learning plan as needed.

[0519] Input: Feedback data

[0520] How it works: The feedback information is analyzed using tools like Pandas, and a new learning plan is generated using the machine learning model again.

[0521] Output: Adjusted study plan

[0522] Step 7:

[0523] New learning plans available

[0524] The server then sends the adjusted study plan back to the user's device.

[0525] Input: Adjusted study plan

[0526] Action: Retransmission from server to device

[0527] Output: The new study plan displayed on your device

[0528] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0529] This invention is a system that automatically generates and provides a learning plan that takes into account the learner's emotions by combining an emotion engine. By recognizing the learner's emotions and reflecting that information in the learning plan, more effective learning support is realized.

[0530] User registration and data entry

[0531] Users access the system and register as new users. They enter user information (such as name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and register in the system. The registration information is sent to the server via the terminal.

[0532] Analyzing data and generating learning plans

[0533] The server stores the received user data in a database. The analysis component analyzes the user data and extracts the learner's characteristics. The generation component then generates an optimal learning plan based on the analysis results. During this process, the emotion engine analyzes the learner's emotional information and influences the generation of the learning plan. Specifically, the difficulty and volume of the learning content are adjusted taking into account the learner's emotional state (e.g., stress level and motivation level).

[0534] Providing study plans

[0535] The server uses a learning plan transmission component to send the generated learning plan to the user's device. The user then checks the learning plan on their device and proceeds with their studies according to the plan.

[0536] Collecting feedback

[0537] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[0538] Analyze feedback and adjust your learning plan

[0539] The server stores the received feedback in a database and analyzes it using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the learning plan to take into account the learner's latest emotional state.

[0540] Specific examples

[0541] For example, consider the case where User B, a third-year junior high school student, uses this system. User B enters that his or her favorite subject is science, his or her weakest subject is Japanese, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the user's characteristics. Next, the generation component generates an optimal study plan, and the emotion engine adjusts the plan's difficulty taking the stress level into account. This study plan is sent to User B's device, and User B proceeds with his or her studies according to the plan. After studying, User B enters his or her progress and current emotional state into the system as feedback, and the server readjusts the study plan based on this.

[0542] In this way, by combining an emotion engine, the present invention can provide a customized learning plan that corresponds to the individual emotional state of the learner, thereby achieving more effective learning support.

[0543] The processing flow will be explained below.

[0544] Step 1:

[0545] The user accesses the system's registration page and registers as a new user. They enter user information (name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and click the "Register" button.

[0546] Step 2:

[0547] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[0548] Step 3:

[0549] The server stores the received user data in a database, which is used to generate a learning plan.

[0550] Step 4:

[0551] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[0552] Step 5:

[0553] The server retrieves the user's emotional state data and runs an emotion engine that analyzes the user's emotional state (e.g., stress level and motivation state).

[0554] Step 6:

[0555] The server uses a generation component to generate an optimal learning plan based on the analysis results and the analysis results of the emotion engine, the learning plan including content based on the user's strengths, weaknesses, and emotional state.

[0556] Step 7:

[0557] The server uses a learning plan sending component to send the generated learning plan to the user's terminal, so that the user can receive the learning plan.

[0558] Step 8:

[0559] The user begins studying based on the received study plan, and as they proceed with their studies, they can input feedback about their progress and learning into the system.

[0560] Step 9:

[0561] The terminal transmits the feedback information and emotional state input by the user to the server. The feedback information includes the learning progress, difficult points, and the current emotional state (e.g., fatigue or a sense of accomplishment).

[0562] Step 10:

[0563] The server stores the received feedback in a database, and the stored feedback information and emotional state are used to adjust the learning plan.

[0564] Step 11:

[0565] The server utilizes the feedback input component to analyze the feedback and emotional state. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback and emotional information.

[0566] Step 12:

[0567] The server then transmits the newly generated study plan to the user's device again, allowing the user to receive the updated study plan.

[0568] Step 13:

[0569] The user then resumes their studies based on the updated study plan, which allows the system to continuously provide optimal learning support for each individual learner, taking into account their emotional state.

[0570] Example 2

[0571] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0572] Conventional learning support systems provide learning plans without taking into account the learner's emotional state, making it difficult to provide appropriate learning support based on the learner's mental state. As a result, there are concerns that the learner's motivation may decrease and stress may increase. Therefore, there is a need to provide learning plans that appropriately reflect the learner's emotional state.

[0573] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting and saving user information, means for analyzing the user information and the emotional state, and means for adjusting the content and difficulty of the study plan using an emotion engine. This makes it possible to provide an appropriate study plan according to the learner's emotional state, thereby maintaining the learner's motivation and reducing stress.

[0574] A "registration component" is a means for entering and storing learner information.

[0575] "User information" is information including the learner's name, grade, favorite subjects, least favorite subjects, educational aspirations, and emotional state.

[0576] The "analysis component" is a means for acquiring and analyzing user information to analyze the learner's characteristics and emotional state.

[0577] "Emotional information" is information that indicates the learner's current emotional state, including stress level and motivation level.

[0578] The "generative component" is a means of generating a learning plan based on the analysis results and adjusting the content and difficulty level using an emotion engine.

[0579] The "emotion engine" is a function that analyzes the learner's emotional state and adjusts the content and difficulty of the learning plan based on the results.

[0580] The "study plan transmission component" is a means for transmitting the generated study plan to the user's terminal.

[0581] A "terminal" is an electronic device that a user uses to review a learning plan and enter feedback.

[0582] The "feedback input component" is a means for inputting progress and feedback from the learner, and is used to regenerate the learning plan.

[0583] A "study plan" is a customized study plan that takes into account the user's strong and weak subjects, academic aspirations, and emotional state.

[0584] "Server" is a central processing unit that stores and analyzes user information, and generates and transmits study plans.

[0585] This invention is a system that automatically generates a learning plan that takes into account the learner's emotions. This system is mainly composed of three elements: a server, a terminal, and a user. These elements work together to provide a customized learning plan that corresponds to the learner's individual emotional state.

[0586] User registration and data entry

[0587] Users access the system and first register. When registering, they enter information such as their name, grade, favorite subjects, favorite subjects, desired school, and emotional state (e.g., stress level and motivation). This information is sent to the server via a terminal. Terminals can be electronic devices such as PCs, tablets, and smartphones.

[0588] Data storage

[0589] The server stores the received user information in a database. This storage process uses a database management system (e.g., MySQL, PostgreSQL). The stored data is used for later analysis and learning plan generation.

[0590] Analyzing the data

[0591] The server's built-in analysis component retrieves user information from the database and analyzes it. The analysis covers learning progress by grade, trends in strong and weak subjects, the level of desired educational destination, emotional state, etc. Data analysis tools such as Python and R are used for this analysis.

[0592] Generate a learning plan

[0593] The generation component generates an optimal learning plan based on the analysis results of the analysis component. At this time, the emotion engine analyzes the learner's emotional state and adjusts the content and difficulty of the plan. For example, a user with a high stress level will be suggested learning content that is less stressful.

[0594] Submit your study plan

[0595] The server sends the generated learning plan to the user's device via the learning plan sending component, using a communication protocol such as HTTP or WebSocket.

[0596] Review and execute your study plan

[0597] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the learning content and proceed with their learning according to the plan.

[0598] Collecting feedback

[0599] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[0600] Feedback storage and analysis

[0601] The server stores the received feedback information in a database. The feedback input component analyzes the stored data and generates a new learning plan based on the analysis results. The emotion engine is also involved in this process, providing a plan that reflects the latest emotional state.

[0602] Specific examples

[0603] For example, if User B, a third-year junior high school student, uses this system, he or she accesses the system and registers his or her name, grade, favorite subject (science), least favorite subject (Japanese), desired school, and emotional state (current stress level). This information is sent to the server via the terminal.

[0604] The server receives the information and stores it in a database. After storage, the analysis component analyzes the data. Based on the analysis results, the generation component generates an optimal learning plan, and the emotion engine adjusts the difficulty of the plan taking into account the stress level. This learning plan is then sent to User B's device via the learning plan sending component.

[0605] User B checks the plan received on his / her device and begins studying according to the plan. After studying, he / she inputs his / her progress and emotional state as feedback and sends it to the server via his / her device. The server analyzes the feedback and generates a new study plan. In this way, the system constantly updates the study plan based on the latest user situation.

[0606] Prompt Sentence Examples

[0607] You can simulate specific scenarios by feeding prompts like the following into the generative AI model:

[0608] "Please tell us the steps for a third-year junior high school student to use the system to generate a lesson plan that takes emotional information into account. For example, please explain the case of a user who is good at science but not good at Japanese."

[0609] In this way, this system provides a learning plan that takes into account the learner's emotional state, providing effective learning support.

[0610] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0611] Step 1:

[0612] Users access the system and register. The information they enter includes their name, grade, favorite subjects, favorite subjects, desired school, emotional state (e.g., stress level), etc. This information is entered into the terminal through an input form, and the contents are sent to the server. Input: User information, Output: Data sent to the server.

[0613] Step 2:

[0614] The server stores the received user information in a database. A database management system (e.g., MySQL, PostgreSQL) is used for the storage process. This allows user information to be stored safely for a long period of time. Input: Transmitted user information, Output: Data stored in the database.

[0615] Step 3:

[0616] The analysis component installed on the server retrieves user information from the database and performs analysis. The analysis uses indicators such as learning progress by grade, trends in strong and weak subjects, the level of desired educational institution, and emotional state. Data analysis tools such as Python and R are used for this analysis. Input: User information in the database, Output: Analysis results.

[0617] Step 4:

[0618] The generation component receives the analysis results from the analysis component and generates an optimal study plan. The emotion engine is involved in this process, adjusting the content and difficulty of the plan taking into account the user's emotional state. Specifically, a user with a high stress level will be provided with a reduced study plan consisting of relatively easy content. Input: Analysis results, Output: Optimized study plan.

[0619] Step 5:

[0620] The server sends the generated learning plan to the user's device using the learning plan sending component. This sending uses a communication protocol such as HTTP or WebSocket. Input: Generated learning plan, Output: Data sent to the user's device.

[0621] Step 6:

[0622] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the study content and carry out their daily study plan. Input: Sent learning plan, Output: User starts studying.

[0623] Step 7:

[0624] The user inputs feedback about their learning progress and emotional state into the system. This includes their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). Feedback information is sent to the server via the terminal. Input: User feedback, Output: Data sent to the server.

[0625] Step 8:

[0626] The server stores the received feedback information in a database. The feedback input component analyzes the stored data, and the generation component is executed again based on the analysis results to generate a new learning plan. The emotion engine is also utilized this time, providing a plan that reflects the learner's latest emotional state. Input: Feedback information, Output: Newly generated learning plan.

[0627] (Application example 2)

[0628] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0629] Existing work plan generation systems are unable to take into account the user's emotional state, which can lead to reduced work efficiency. It is also difficult to dynamically adjust plans based on the user's strengths and weaknesses, as well as their progress. This leads to the accumulation of stress and fatigue in the user, resulting in reduced work productivity.

[0630] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a processing device including a registration component and means for inputting and saving user information, a processing device including an analysis component and means for analyzing the user information, a processing device including a generation component and means for generating a work plan based on the analysis results, a processing device including an emotion engine and means for analyzing the user's emotional state and influencing the work plan, a processing device including a work plan transmission component and means for transmitting the generated work plan to the user's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the user, and means for re-executing the generation component based on the feedback. This enables flexible generation and adjustment of work plans that take into account the user's emotional state and progress.

[0631] A "registration component" is a processing device that has a means for inputting and storing user information.

[0632] "User information" refers to basic information about the user (such as name, favorite tasks, least favorite tasks, emotional state, etc.).

[0633] An "analysis component" is a processing device that has means for analyzing user information and extracting its characteristics.

[0634] A "generation component" is a processing device that has means for generating an optimal work plan based on the analysis results.

[0635] The "emotion engine" is a processing device that has the means to analyze the user's emotional state and reflect that information in the work plan.

[0636] A "work plan" refers to specific work procedures and schedules that are created taking into account the user's characteristics and emotional state.

[0637] The "work plan transmission component" is a processing device that has means for transmitting the generated work plan to the user's terminal.

[0638] A "feedback input component" is a processing device that has means for inputting feedback from a user regarding progress and emotional state.

[0639] "Feedback" refers to input information about the progress of the task and the user's emotional state after the task.

[0640] This invention is a system that automatically generates and provides work plans by combining an emotion engine and taking into account the user's emotional state. Specifically, by recognizing the user's emotions and reflecting that information in the work plan, more effective work support is realized.

[0641] User registration and data entry

[0642] A user accesses the system and enters and saves basic information through the registration component. The user information includes name, favorite tasks, least favorite tasks, and emotional state. This information is sent from the user's terminal to the server and stored in the server's database.

[0643] Analyzing data and generating work plans

[0644] The server stores the received user data in a database. The analysis component then analyzes this data and extracts the user's characteristics. The generation component generates an optimal work plan based on the analysis results. The emotion engine is involved in this process, adjusting the difficulty and amount of the work content based on the user's emotional state (such as stress level and motivation level).

[0645] Providing a work plan

[0646] The server sends the generated work plan to the user's terminal via the work plan sending component. The user checks the work plan on their own terminal and proceeds with the work according to the plan.

[0647] Collecting feedback

[0648] After completing the task, the user inputs feedback about their progress and emotional state into the system. The feedback includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue, accomplishment). This information is sent from the user's device to the server.

[0649] Analyze feedback and adjust work plan

[0650] The server stores the received feedback in a database and analyzes it through the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the work plan to take into account the user's latest emotional state.

[0651] Specific examples

[0652] As a concrete example, consider a scenario in which Worker A at a factory uses this system. Worker A inputs that his or her strongest task is assembly, his or her weakest task is welding, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the worker's characteristics. Next, the generation component generates an optimal work plan, and the emotion engine adjusts the plan's difficulty by taking the worker's stress level into account. This work plan is sent to Worker A's device, and Worker A proceeds with the work according to the plan. After the work, Worker A inputs his or her progress and current emotional state into the system as feedback, and the server readjusts the work plan based on this.

[0653] Hardware and software used

[0654] This system requires a wearable device (e.g., a device that acquires vital signs) as an emotion sensor, a data transmission terminal, and a work support computer system. The software used includes Python for data analysis, MySQL for database management, and a machine learning model for feedback analysis.

[0655] Prompt Sentence Examples

[0656] "Generate the optimal work plan for the user's current stressful situation."

[0657] This enables flexible creation and adjustment of work plans that take into account the user's emotional state and progress.

[0658] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0659] Step 1:

[0660] A user accesses the system using a terminal. The user inputs basic information such as name, favorite tasks, least favorite tasks, and emotional state. This input information is sent from the terminal to the server and stored in the server's database. The input data is saved as properly formatted data by the registration component.

[0661] Step 2:

[0662] The server retrieves user information stored in the database. The analysis component uses this information to analyze the user's characteristics. Specifically, it extracts information such as the user's strengths and weaknesses, their current emotional state, and so on. This analysis data is used in the next phase of work plan generation.

[0663] Step 3:

[0664] The server's generation component generates an optimal work plan based on the analysis data. Here, the emotion engine analyzes the user's emotional state and adjusts the difficulty and amount of the work plan based on the results. For example, if the stress level is high, adjustments may be made such as reducing the amount of work. The generated work plan is temporarily stored in a database.

[0665] Step 4:

[0666] The server sends the work plan generated using the work plan sending component to the user's device. The user checks the provided work plan on their device and starts working according to the plan. This plan is optimized taking into account the user's emotional state, allowing the user to work efficiently.

[0667] Step 5:

[0668] After completing the task, the user again uses the device to input feedback about their progress and emotional state into the system. This feedback information includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). This information is sent from the device to the server and stored in a database.

[0669] Step 6:

[0670] The server analyzes the received feedback using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan. The emotion engine also participates in this process, generating a plan that reflects the latest emotional state. The newly generated work plan is then sent back to the user's device.

[0671] Step 7:

[0672] The user then checks the work plan again and proceeds with the work according to the adjusted plan. This cycle is repeated depending on the user's emotional state and work progress, making it possible to provide optimal work support.

[0673] 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.

[0674] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0675] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0676] [Third embodiment]

[0677] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0678] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0679] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0680] 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.

[0681] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0682] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0683] 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. 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.

[0684] 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.

[0685] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0686] 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.

[0687] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0688] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0689] This invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. Learner information is input, and an optimal study plan is generated based on that information and provided to the learner. It also has the function of adjusting the study plan as appropriate based on feedback from the learner.

[0690] User registration and data entry

[0691] Users access the system and register as new users. When registering, they enter basic information such as their grade, favorite subjects, weak subjects, and desired school. This information is then sent to the server by the terminal.

[0692] Analyzing data and generating learning plans

[0693] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates an optimal learning plan based on the results of this analysis. This learning plan is customized for each learner and also references data on other learners stored in the database.

[0694] Providing study plans

[0695] The server sends the generated study plan to the user's device using the study plan sending component. The user checks the study plan received on their device and proceeds with their studies based on it.

[0696] Collecting feedback

[0697] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[0698] Specific examples

[0699] For example, consider the case where User A, a third-year junior high school student, uses this system. User A's best subject is math, his weakest subject is English, and he hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. The generated study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A studies according to it. Then, after a few weeks, User A provides feedback on his progress and difficult points, and the server uses that information to readjust the study plan. In this way, support is provided to continuously maximize learning effectiveness.

[0700] The present invention makes it possible to provide optimal learning plans tailored to each learner at low cost, effectively eliminating educational disparities caused by income disparities.

[0701] The processing flow will be explained below.

[0702] Step 1:

[0703] The user accesses the system's registration page and registers as a new user. They enter their user information (name, grade, favorite subjects, favorite subjects, desired school) and click the "Register" button.

[0704] Step 2:

[0705] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[0706] Step 3:

[0707] The server stores the received user data in a database, which is used for analysis.

[0708] Step 4:

[0709] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[0710] Step 5:

[0711] The server uses a generation component to generate an optimal learning plan based on the analysis results, which includes specific subject reinforcement and mastery strategies.

[0712] Step 6:

[0713] The server transmits the generated study plan to the user's terminal using the study plan transmission component, so that the user can receive the study plan.

[0714] Step 7:

[0715] The user begins studying based on the received study plan, and as they proceed with their studies, they input their progress and feedback about their studies into the system.

[0716] Step 8:

[0717] The device sends the feedback information entered by the user to the server, including the learning progress and points that were difficult.

[0718] Step 9:

[0719] The server stores the received feedback in a database and analyzes it again. Based on the feedback information, the effectiveness of the learning plan is evaluated.

[0720] Step 10:

[0721] The server re-executes the generation component as needed to generate a new learning plan that reflects the feedback, and then transmits the new learning plan to the user's device.

[0722] Step 11:

[0723] Users receive new study plans and continue their studies, which allows for continuous provision of optimal learning support for each individual learner.

[0724] Example 1

[0725] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0726] In modern society, income disparities between parents create educational disparities for their children, which is a problem. Providing optimal learning plans for individual learners is particularly costly, preventing many families from benefiting from them. Furthermore, tracking learners' daily progress and adjusting learning plans accordingly requires a significant amount of work. A system that can solve this problem is needed.

[0727] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0728] In this invention, the server includes a processing device including a user registration component and means for inputting and saving learner information, a processing device including an analysis component and means for analyzing the learner information and extracting characteristics based on the learner's favorite subjects, weak subjects, and educational aspirations, a processing device including a generation component with a generative AI model and means for generating a study plan based on the characteristic data, a processing device including a study plan transmission component and means for transmitting the generated study plan to the learner's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the learner, and means for re-executing the generation component based on the feedback and adjusting the study plan as appropriate. This effectively solves the problem of educational disparities caused by income disparities and makes it possible to provide optimal study plans for individual learners at low cost.

[0729] A "user registration component" is a processing device that provides functionality for entering and saving learner information.

[0730] The "analysis component" is a processing device that provides a function for analyzing stored learner information and extracting characteristics based on strong subjects, weak subjects, and educational aspirations.

[0731] A "generative AI model" is a model that generates optimal learning plans based on machine learning technology.

[0732] A "generative component" is a processing device that includes a generative AI model and provides functionality for generating a learning plan based on feature data.

[0733] The "learning plan transmission component" is a processing device that provides a function for transmitting the generated learning plan to the learner's terminal.

[0734] A "feedback input component" is a processing device that provides functionality for inputting progress and feedback from a learner.

[0735] "Characteristic data" is information extracted by the analysis component regarding a learner's strong subjects, weak subjects, and educational aspirations.

[0736] A "study plan" is a customized study plan based on the learner's strengths and weaknesses, and their educational aspirations.

[0737] The present invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. The program processing of this system will be specifically described below.

[0738] Overall system configuration

[0739] The system starts when a user accesses the system using a terminal and inputs and sends the necessary information. The server receives the information, generates a learning plan through analysis and generation components, and sends it to the user's terminal. The server also has the function of adjusting the learning plan based on feedback information from the user.

[0740] User registration component: Provides the ability to enter and save user information.

[0741] Analysis component: Analyzes stored user information and extracts characteristics based on strong and weak subjects and educational aspirations.

[0742] Generative component equipped with a generative AI model: Generates an optimal learning plan based on feature data.

[0743] Study plan sending component: Sends the generated study plan to the user's device.

[0744] Feedback input component: Has a function for inputting progress and feedback from the user.

[0745] Operation details of each component

[0746] User Registration Component

[0747] After accessing the system, users register. When registering, they enter basic information such as email address and password to create an account on the system. They then enter additional information such as their grade, favorite subjects, favorite subjects, and desired school. The entered information is sent to the server via the terminal and stored in the database. This process ensures that subsequent analysis and plan generation are more effective when users enter accurate information.

[0748] Analytics Components

[0749] The server runs an analysis component based on user information stored in the database. The analysis component processes the received learner information and extracts characteristics related to the learner's strong and weak subjects and educational aspirations. This process uses SQL queries and data mining techniques. This clarifies the individual learner's learning style and needs.

[0750] Generative components equipped with generative AI models

[0751] The generative component operates based on the analysis results. Using a generative AI model that leverages machine learning techniques, the generative component generates a learning plan based on the obtained feature data. This model utilizes existing data to provide a customized learning plan suited to the learner. For example, it may suggest specific learning content to further develop strong subjects or specific methods to overcome weak subjects.

[0752] Learning Plan Submission Component

[0753] The generated study plan is sent to the user's device via the study plan sending component. There are two ways to send the plan: by sending a notification to the email address entered by the user when registering, or by making it available for viewing on the system's dashboard. This allows users to check their study plan at any time and proceed with their studies based on it.

[0754] Feedback Input Component

[0755] As they study, users can use their devices to input feedback about their progress and learning into the system. This feedback includes detailed information such as whether they are making good progress or whether a particular subject is difficult. This feedback information is also sent back to the server and stored in a database.

[0756] Adjusting your learning plan based on feedback

[0757] The server analyzes the feedback using the feedback input component based on the saved feedback, and if necessary, re-runs the generation component to adjust the learning plan. This process ensures that the user always receives a plan that is optimized for their learning progress.

[0758] Specific use cases

[0759] For example, if User A, a third-year junior high school student, were to use this system, he or she would enter information that their favorite subject is math and their weakest subject is English. They would also enter their desire to attend a public high school. The server would then analyze this information, and the generative AI model would generate an optimal learning plan accordingly. This plan would include specific details on how to improve math and how to overcome English.

[0760] The generated study plan is sent to User A's device, and User A studies according to the plan. After a few weeks, User A provides feedback on their progress and difficult points. The server receives this feedback, analyzes and adjusts it again, and generates and sends a new study plan.

[0761] Prompt Sentence Examples

[0762] "User A, a third-year junior high school student, has entered the following information: his best subject is math, his worst subject is English, and his desired school is a public high school. Based on this information, please generate an optimal study plan for User A and provide specific study content for at least one week according to that plan."

[0763] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0764] Step 1:

[0765] User Registration:

[0766] A user accesses the system and registers. During this process, the user enters an email address and password, which are then sent to the server. The server stores the received email address and password in a database and creates a new account. Input: Email address, password. Output: Creation of a new account.

[0767] Step 2:

[0768] Enter your user information:

[0769] The user then enters detailed information such as grade, favorite subjects, weak subjects, and desired school. This information is also sent to the server via the terminal. The server stores the received information in a database. Input: grade, favorite subjects, weak subjects, desired school. Output: User information saved.

[0770] Step 3:

[0771] User information analysis:

[0772] The server retrieves user information stored in the database and sends it to the analysis component. The analysis component analyzes this information and extracts features based on the learner's strong and weak subjects, and educational aspirations. For example, it uses SQL queries to extract specific information from the database and then uses data mining algorithms to extract features. Input: Stored user information. Output: Extracted feature data.

[0773] Step 4:

[0774] Learning plan generation:

[0775] The server's generation component uses a generative AI model to generate an optimal learning plan based on the extracted feature data. The generative AI model uses machine learning algorithms to provide a customized learning plan tailored to the user's individual learning needs. Input: Feature data. Output: Customized learning plan.

[0776] Step 5:

[0777] Submit your study plan:

[0778] The server sends the generated learning plan to the user's device via the learning plan sending component. The sending is done via a notification to the email address registered by the user or via the dashboard within the system. Input: Generated learning plan. Output: Delivery of the learning plan to the user's device.

[0779] Step 6:

[0780] Feedback Input:

[0781] As the user progresses with their studies, they input feedback about their progress and learning from their device. Feedback includes learning progress and difficulties they are experiencing in specific subjects. Input: Learning progress and feedback information. Output: Feedback sent to the server via the device.

[0782] Step 7:

[0783] Feedback analysis and learning plan adjustment:

[0784] The server stores the received feedback information in a database. The server's feedback input component analyzes this feedback information and runs the generation component again to make any necessary adjustments to the learning plan. This generates a new learning plan optimized for the latest progress. Input: Feedback information. Output: Adjusted learning plan.

[0785] (Application example 1)

[0786] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0787] The challenge is to provide an environment where learners can make effective use of their travel time and study efficiently. There is also a need to reduce educational disparities based on parental income and ensure that all learners have equal opportunities to receive high-quality education. To realize such an environment, it is necessary to provide a learning support system inside self-driving vehicles.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0789] In this invention, the server includes a processing device including a registration component, which inputs and saves learner information; a processing device including an analysis component, which analyzes the learner information; a processing device including a generation component, which generates a study plan based on the analysis results; a processing device including a study plan transmission component, which transmits the generated study plan to the learner's device; a processing device including a feedback input component, which inputs progress and feedback from the learner; and a processing device including a user interface corresponding to multiple modes of transportation, which displays study content on a device in an autonomous vehicle and supports study progress in real time. This makes it possible to make effective use of time while traveling, reduce educational disparities, and promote efficient learning.

[0790] A "registration component" is a processing device capable of inputting and storing learner information.

[0791] An "analysis component" is a processing device that has the function of analyzing input learner information.

[0792] A "generative component" is a processing device that has the functionality to generate a lesson plan based on the analyzed results.

[0793] The "learning plan transmission component" is a processing device that has the function of transmitting the generated learning plan to the learner's terminal.

[0794] A "feedback input component" is a processing device that has the function of inputting progress and feedback from a learner.

[0795] A "user interface" is a processing device that displays learning content on a terminal inside an autonomous vehicle and has the function of supporting learning progress in real time.

[0796] An "autonomous vehicle" is a vehicle that operates autonomously and drives itself without occupant intervention.

[0797] A "study plan" is a customized plan of learning activities based on information such as the learner's strong and weak subjects, and their educational aspirations.

[0798] User registration and data entry

[0799] First, the user registers on a terminal inside the autonomous vehicle. When registering, the user enters basic information such as their grade, favorite subjects, weak subjects, and educational aspirations. This information is then sent to the server by the terminal.

[0800] Analyzing data and generating learning plans

[0801] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates a study plan based on the analysis results. This plan is customized for each user and also references data from other users stored in the database.

[0802] Learning plan delivery and user interface

[0803] The server sends the generated learning plan to the user's terminal using a learning plan sending component. The terminal in the autonomous vehicle receives the learning plan, displays the learning content through a user interface, and supports the learning progress in real time.

[0804] Gather feedback and adjust your plan

[0805] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[0806] Hardware and Software Usage

[0807] The server uses Python, with SQLite or PostgreSQL as the database. Data analysis tools such as Pandas are used for data analysis, and machine learning models such as Scikit-Learn are used for the generation component. The terminal inside the autonomous vehicle uses a tablet or smartphone to display the learning plan and support feedback input.

[0808] Specific examples

[0809] For example, if User A, a third-year junior high school student, uses this system, his or her best subject is math, his or her weakest subject is English, and he or she hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. This study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A proceeds with his or her studies according to the plan. After a few weeks, User A provides feedback on his or her progress and difficult points, and the server uses that information to readjust the study plan.

[0810] Prompt Sentence Examples

[0811] "User A has been newly registered. Next, please send him the 'Study Plan Generation' prompt."

[0812] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0813] Step 1:

[0814] User registration and data entry

[0815] The user registers a new account on a terminal inside the autonomous vehicle.

[0816] Input: Basic information such as the user's grade, favorite subjects, favorite subjects, and educational aspirations

[0817] Operation: This information is sent from the device to the server.

[0818] Output: User information is saved on the server

[0819] Step 2:

[0820] Data storage and analysis

[0821] The server stores the received user data in a database.

[0822] Input: User basic information

[0823] How it works: Analyze the saved data using data analysis tools such as Pandas to extract characteristics based on strong and weak subjects and educational aspirations.

[0824] Output: Feature-extracted data

[0825] Step 3:

[0826] Generate a learning plan

[0827] The server's generation component generates a learning plan based on the analysis results.

[0828] Input: extracted feature data

[0829] How it works: Using machine learning models such as Scikit-Learn, it automatically generates a study plan that includes ways to improve your strengths and overcome your weaknesses.

[0830] Output: personalized learning plan

[0831] Step 4:

[0832] Providing study plans

[0833] The server transmits the generated learning plan to the user's terminal using a learning plan transmission component.

[0834] Input: Personalized Learning Plan

[0835] Operation: Sending a plan from the server to the device

[0836] Output: The lesson plan displayed on the device

[0837] Step 5:

[0838] Learning and gathering feedback

[0839] The user follows the learning plan provided via the device and inputs feedback on progress and problems encountered during the learning process.

[0840] Input: User learning progress information, feedback

[0841] Action: The device sends the entered information to the server.

[0842] Output: Feedback data stored on the server

[0843] Step 6:

[0844] Analyze feedback and adjust plans

[0845] The server analyzes the feedback information and re-runs the generation component to adjust the learning plan as needed.

[0846] Input: Feedback data

[0847] How it works: The feedback information is analyzed using tools like Pandas, and a new learning plan is generated using the machine learning model again.

[0848] Output: Adjusted study plan

[0849] Step 7:

[0850] New learning plans available

[0851] The server then sends the adjusted study plan back to the user's device.

[0852] Input: Adjusted study plan

[0853] Action: Retransmission from server to device

[0854] Output: The new study plan displayed on your device

[0855] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0856] This invention is a system that automatically generates and provides a learning plan that takes into account the learner's emotions by combining an emotion engine. By recognizing the learner's emotions and reflecting that information in the learning plan, more effective learning support is realized.

[0857] User registration and data entry

[0858] Users access the system and register as new users. They enter user information (such as name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and register in the system. The registration information is sent to the server via the terminal.

[0859] Analyzing data and generating learning plans

[0860] The server stores the received user data in a database. The analysis component analyzes the user data and extracts the learner's characteristics. The generation component then generates an optimal learning plan based on the analysis results. During this process, the emotion engine analyzes the learner's emotional information and influences the generation of the learning plan. Specifically, the difficulty and volume of the learning content are adjusted taking into account the learner's emotional state (e.g., stress level and motivation level).

[0861] Providing study plans

[0862] The server uses a learning plan transmission component to send the generated learning plan to the user's device. The user then checks the learning plan on their device and proceeds with their studies according to the plan.

[0863] Collecting feedback

[0864] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[0865] Analyze feedback and adjust your learning plan

[0866] The server stores the received feedback in a database and analyzes it using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the learning plan to take into account the learner's latest emotional state.

[0867] Specific examples

[0868] For example, consider the case where User B, a third-year junior high school student, uses this system. User B enters that his or her favorite subject is science, his or her weakest subject is Japanese, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the user's characteristics. Next, the generation component generates an optimal study plan, and the emotion engine adjusts the plan's difficulty taking the stress level into account. This study plan is sent to User B's device, and User B proceeds with his or her studies according to the plan. After studying, User B enters his or her progress and current emotional state into the system as feedback, and the server readjusts the study plan based on this.

[0869] In this way, by combining an emotion engine, the present invention can provide a customized learning plan that corresponds to the individual emotional state of the learner, thereby achieving more effective learning support.

[0870] The processing flow will be explained below.

[0871] Step 1:

[0872] The user accesses the system's registration page and registers as a new user. They enter user information (name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and click the "Register" button.

[0873] Step 2:

[0874] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[0875] Step 3:

[0876] The server stores the received user data in a database, which is used to generate a learning plan.

[0877] Step 4:

[0878] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[0879] Step 5:

[0880] The server retrieves the user's emotional state data and runs an emotion engine that analyzes the user's emotional state (e.g., stress level and motivation state).

[0881] Step 6:

[0882] The server uses a generation component to generate an optimal learning plan based on the analysis results and the analysis results of the emotion engine, the learning plan including content based on the user's strengths, weaknesses, and emotional state.

[0883] Step 7:

[0884] The server uses a learning plan sending component to send the generated learning plan to the user's terminal, so that the user can receive the learning plan.

[0885] Step 8:

[0886] The user begins studying based on the received study plan, and as they proceed with their studies, they can input feedback about their progress and learning into the system.

[0887] Step 9:

[0888] The terminal transmits the feedback information and emotional state input by the user to the server. The feedback information includes the learning progress, difficult points, and the current emotional state (e.g., fatigue or a sense of accomplishment).

[0889] Step 10:

[0890] The server stores the received feedback in a database, and the stored feedback information and emotional state are used to adjust the learning plan.

[0891] Step 11:

[0892] The server utilizes the feedback input component to analyze the feedback and emotional state. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback and emotional information.

[0893] Step 12:

[0894] The server then transmits the newly generated study plan to the user's device again, allowing the user to receive the updated study plan.

[0895] Step 13:

[0896] The user then resumes their studies based on the updated study plan, which allows the system to continuously provide optimal learning support for each individual learner, taking into account their emotional state.

[0897] Example 2

[0898] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0899] Conventional learning support systems provide learning plans without taking into account the learner's emotional state, making it difficult to provide appropriate learning support based on the learner's mental state. As a result, there are concerns that the learner's motivation may decrease and stress may increase. Therefore, there is a need to provide learning plans that appropriately reflect the learner's emotional state.

[0900] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting and saving user information, means for analyzing the user information and the emotional state, and means for adjusting the content and difficulty of the study plan using an emotion engine. This makes it possible to provide an appropriate study plan according to the learner's emotional state, thereby maintaining the learner's motivation and reducing stress.

[0901] A "registration component" is a means for entering and storing learner information.

[0902] "User information" is information including the learner's name, grade, favorite subjects, least favorite subjects, educational aspirations, and emotional state.

[0903] The "analysis component" is a means for acquiring and analyzing user information to analyze the learner's characteristics and emotional state.

[0904] "Emotional information" is information that indicates the learner's current emotional state, including stress level and motivation level.

[0905] The "generative component" is a means of generating a learning plan based on the analysis results and adjusting the content and difficulty level using an emotion engine.

[0906] The "emotion engine" is a function that analyzes the learner's emotional state and adjusts the content and difficulty of the learning plan based on the results.

[0907] The "study plan transmission component" is a means for transmitting the generated study plan to the user's terminal.

[0908] A "terminal" is an electronic device that a user uses to review a learning plan and enter feedback.

[0909] The "feedback input component" is a means for inputting progress and feedback from the learner, and is used to regenerate the learning plan.

[0910] A "study plan" is a customized study plan that takes into account the user's strong and weak subjects, academic aspirations, and emotional state.

[0911] "Server" is a central processing unit that stores and analyzes user information, and generates and transmits study plans.

[0912] This invention is a system that automatically generates a learning plan that takes into account the learner's emotions. This system is mainly composed of three elements: a server, a terminal, and a user. These elements work together to provide a customized learning plan that corresponds to the learner's individual emotional state.

[0913] User registration and data entry

[0914] Users access the system and first register. When registering, they enter information such as their name, grade, favorite subjects, favorite subjects, desired school, and emotional state (e.g., stress level and motivation). This information is sent to the server via a terminal. Terminals can be electronic devices such as PCs, tablets, and smartphones.

[0915] Data storage

[0916] The server stores the received user information in a database. This storage process uses a database management system (e.g., MySQL, PostgreSQL). The stored data is used for later analysis and learning plan generation.

[0917] Analyzing the data

[0918] The server's built-in analysis component retrieves user information from the database and analyzes it. The analysis covers learning progress by grade, trends in strong and weak subjects, the level of desired educational destination, emotional state, etc. Data analysis tools such as Python and R are used for this analysis.

[0919] Generate a learning plan

[0920] The generation component generates an optimal learning plan based on the analysis results of the analysis component. At this time, the emotion engine analyzes the learner's emotional state and adjusts the content and difficulty of the plan. For example, a user with a high stress level will be suggested learning content that is less stressful.

[0921] Submit your study plan

[0922] The server sends the generated learning plan to the user's device via the learning plan sending component, using a communication protocol such as HTTP or WebSocket.

[0923] Review and execute your study plan

[0924] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the learning content and proceed with their learning according to the plan.

[0925] Collecting feedback

[0926] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[0927] Feedback storage and analysis

[0928] The server stores the received feedback information in a database. The feedback input component analyzes the stored data and generates a new learning plan based on the analysis results. The emotion engine is also involved in this process, providing a plan that reflects the latest emotional state.

[0929] Specific examples

[0930] For example, if User B, a third-year junior high school student, uses this system, he or she accesses the system and registers his or her name, grade, favorite subject (science), least favorite subject (Japanese), desired school, and emotional state (current stress level). This information is sent to the server via the terminal.

[0931] The server receives the information and stores it in a database. After storage, the analysis component analyzes the data. Based on the analysis results, the generation component generates an optimal learning plan, and the emotion engine adjusts the difficulty of the plan taking into account the stress level. This learning plan is then sent to User B's device via the learning plan sending component.

[0932] User B checks the plan received on his / her device and begins studying according to the plan. After studying, he / she inputs his / her progress and emotional state as feedback and sends it to the server via his / her device. The server analyzes the feedback and generates a new study plan. In this way, the system constantly updates the study plan based on the latest user situation.

[0933] Prompt Sentence Examples

[0934] You can simulate specific scenarios by feeding prompts like the following into the generative AI model:

[0935] "Please tell us the steps for a third-year junior high school student to use the system to generate a lesson plan that takes emotional information into account. For example, please explain the case of a user who is good at science but not good at Japanese."

[0936] In this way, this system provides a learning plan that takes into account the learner's emotional state, providing effective learning support.

[0937] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] Users access the system and register. The information they enter includes their name, grade, favorite subjects, favorite subjects, desired school, emotional state (e.g., stress level), etc. This information is entered into the terminal through an input form, and the contents are sent to the server. Input: User information, Output: Data sent to the server.

[0940] Step 2:

[0941] The server stores the received user information in a database. A database management system (e.g., MySQL, PostgreSQL) is used for the storage process. This allows user information to be stored safely for a long period of time. Input: Transmitted user information, Output: Data stored in the database.

[0942] Step 3:

[0943] The analysis component installed on the server retrieves user information from the database and performs analysis. The analysis uses indicators such as learning progress by grade, trends in strong and weak subjects, the level of desired educational institution, and emotional state. Data analysis tools such as Python and R are used for this analysis. Input: User information in the database, Output: Analysis results.

[0944] Step 4:

[0945] The generation component receives the analysis results from the analysis component and generates an optimal study plan. The emotion engine is involved in this process, adjusting the content and difficulty of the plan taking into account the user's emotional state. Specifically, a user with a high stress level will be provided with a reduced study plan consisting of relatively easy content. Input: Analysis results, Output: Optimized study plan.

[0946] Step 5:

[0947] The server sends the generated learning plan to the user's device using the learning plan sending component. This sending uses a communication protocol such as HTTP or WebSocket. Input: Generated learning plan, Output: Data sent to the user's device.

[0948] Step 6:

[0949] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the study content and carry out their daily study plan. Input: Sent learning plan, Output: User starts studying.

[0950] Step 7:

[0951] The user inputs feedback about their learning progress and emotional state into the system. This includes their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). Feedback information is sent to the server via the terminal. Input: User feedback, Output: Data sent to the server.

[0952] Step 8:

[0953] The server stores the received feedback information in a database. The feedback input component analyzes the stored data, and the generation component is executed again based on the analysis results to generate a new learning plan. The emotion engine is also utilized this time, providing a plan that reflects the learner's latest emotional state. Input: Feedback information, Output: Newly generated learning plan.

[0954] (Application example 2)

[0955] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0956] Existing work plan generation systems are unable to take into account the user's emotional state, which can lead to reduced work efficiency. It is also difficult to dynamically adjust plans based on the user's strengths and weaknesses, as well as their progress. This leads to the accumulation of stress and fatigue in the user, resulting in reduced work productivity.

[0957] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a processing device including a registration component and means for inputting and saving user information, a processing device including an analysis component and means for analyzing the user information, a processing device including a generation component and means for generating a work plan based on the analysis results, a processing device including an emotion engine and means for analyzing the user's emotional state and influencing the work plan, a processing device including a work plan transmission component and means for transmitting the generated work plan to the user's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the user, and means for re-executing the generation component based on the feedback. This enables flexible generation and adjustment of work plans that take into account the user's emotional state and progress.

[0958] A "registration component" is a processing device that has a means for inputting and storing user information.

[0959] "User information" refers to basic information about the user (such as name, favorite tasks, least favorite tasks, emotional state, etc.).

[0960] An "analysis component" is a processing device that has means for analyzing user information and extracting its characteristics.

[0961] A "generation component" is a processing device that has means for generating an optimal work plan based on the analysis results.

[0962] The "emotion engine" is a processing device that has the means to analyze the user's emotional state and reflect that information in the work plan.

[0963] A "work plan" refers to specific work procedures and schedules that are created taking into account the user's characteristics and emotional state.

[0964] The "work plan transmission component" is a processing device that has means for transmitting the generated work plan to the user's terminal.

[0965] A "feedback input component" is a processing device that has means for inputting feedback from a user regarding progress and emotional state.

[0966] "Feedback" refers to input information about the progress of the task and the user's emotional state after the task.

[0967] This invention is a system that automatically generates and provides work plans by combining an emotion engine and taking into account the user's emotional state. Specifically, by recognizing the user's emotions and reflecting that information in the work plan, more effective work support is realized.

[0968] User registration and data entry

[0969] A user accesses the system and enters and saves basic information through the registration component. The user information includes name, favorite tasks, least favorite tasks, and emotional state. This information is sent from the user's terminal to the server and stored in the server's database.

[0970] Analyzing data and generating work plans

[0971] The server stores the received user data in a database. The analysis component then analyzes this data and extracts the user's characteristics. The generation component generates an optimal work plan based on the analysis results. The emotion engine is involved in this process, adjusting the difficulty and amount of the work content based on the user's emotional state (such as stress level and motivation level).

[0972] Providing a work plan

[0973] The server sends the generated work plan to the user's terminal via the work plan sending component. The user checks the work plan on their own terminal and proceeds with the work according to the plan.

[0974] Collecting feedback

[0975] After completing the task, the user inputs feedback about their progress and emotional state into the system. The feedback includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue, accomplishment). This information is sent from the user's device to the server.

[0976] Analyze feedback and adjust work plan

[0977] The server stores the received feedback in a database and analyzes it through the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the work plan to take into account the user's latest emotional state.

[0978] Specific examples

[0979] As a concrete example, consider a scenario in which Worker A at a factory uses this system. Worker A inputs that his or her strongest task is assembly, his or her weakest task is welding, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the worker's characteristics. Next, the generation component generates an optimal work plan, and the emotion engine adjusts the plan's difficulty by taking the worker's stress level into account. This work plan is sent to Worker A's device, and Worker A proceeds with the work according to the plan. After the work, Worker A inputs his or her progress and current emotional state into the system as feedback, and the server readjusts the work plan based on this.

[0980] Hardware and software used

[0981] This system requires a wearable device (e.g., a device that acquires vital signs) as an emotion sensor, a data transmission terminal, and a work support computer system. The software used includes Python for data analysis, MySQL for database management, and a machine learning model for feedback analysis.

[0982] Prompt Sentence Examples

[0983] "Generate the optimal work plan for the user's current stressful situation."

[0984] This enables flexible creation and adjustment of work plans that take into account the user's emotional state and progress.

[0985] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0986] Step 1:

[0987] A user accesses the system using a terminal. The user inputs basic information such as name, favorite tasks, least favorite tasks, and emotional state. This input information is sent from the terminal to the server and stored in the server's database. The input data is saved as properly formatted data by the registration component.

[0988] Step 2:

[0989] The server retrieves user information stored in the database. The analysis component uses this information to analyze the user's characteristics. Specifically, it extracts information such as the user's strengths and weaknesses, their current emotional state, and so on. This analysis data is used in the next phase of work plan generation.

[0990] Step 3:

[0991] The server's generation component generates an optimal work plan based on the analysis data. Here, the emotion engine analyzes the user's emotional state and adjusts the difficulty and amount of the work plan based on the results. For example, if the stress level is high, adjustments may be made such as reducing the amount of work. The generated work plan is temporarily stored in a database.

[0992] Step 4:

[0993] The server sends the work plan generated using the work plan sending component to the user's device. The user checks the provided work plan on their device and starts working according to the plan. This plan is optimized taking into account the user's emotional state, allowing the user to work efficiently.

[0994] Step 5:

[0995] After completing the task, the user again uses the device to input feedback about their progress and emotional state into the system. This feedback information includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). This information is sent from the device to the server and stored in a database.

[0996] Step 6:

[0997] The server analyzes the received feedback using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan. The emotion engine also participates in this process, generating a plan that reflects the latest emotional state. The newly generated work plan is then sent back to the user's device.

[0998] Step 7:

[0999] The user then checks the work plan again and proceeds with the work according to the adjusted plan. This cycle is repeated depending on the user's emotional state and work progress, making it possible to provide optimal work support.

[1000] 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.

[1001] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1002] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1003] [Fourth embodiment]

[1004] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1005] 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.

[1006] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1007] 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.

[1008] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1009] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1010] 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. 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.

[1011] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1012] 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.

[1013] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1014] 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.

[1015] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1016] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1017] This invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. Learner information is input, and an optimal study plan is generated based on that information and provided to the learner. It also has the function of adjusting the study plan as appropriate based on feedback from the learner.

[1018] User registration and data entry

[1019] Users access the system and register as new users. When registering, they enter basic information such as their grade, favorite subjects, weak subjects, and desired school. This information is then sent to the server by the terminal.

[1020] Analyzing data and generating learning plans

[1021] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates an optimal learning plan based on the results of this analysis. This learning plan is customized for each learner and also references data on other learners stored in the database.

[1022] Providing study plans

[1023] The server sends the generated study plan to the user's device using the study plan sending component. The user checks the study plan received on their device and proceeds with their studies based on it.

[1024] Collecting feedback

[1025] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[1026] Specific examples

[1027] For example, consider the case where User A, a third-year junior high school student, uses this system. User A's best subject is math, his weakest subject is English, and he hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. The generated study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A studies according to it. Then, after a few weeks, User A provides feedback on his progress and difficult points, and the server uses that information to readjust the study plan. In this way, support is provided to continuously maximize learning effectiveness.

[1028] The present invention makes it possible to provide optimal learning plans tailored to each learner at low cost, effectively eliminating educational disparities caused by income disparities.

[1029] The processing flow will be explained below.

[1030] Step 1:

[1031] The user accesses the system's registration page and registers as a new user. They enter their user information (name, grade, favorite subjects, favorite subjects, desired school) and click the "Register" button.

[1032] Step 2:

[1033] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[1034] Step 3:

[1035] The server stores the received user data in a database, which is used for analysis.

[1036] Step 4:

[1037] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[1038] Step 5:

[1039] The server uses a generation component to generate an optimal learning plan based on the analysis results, which includes specific subject reinforcement and mastery strategies.

[1040] Step 6:

[1041] The server transmits the generated study plan to the user's terminal using the study plan transmission component, so that the user can receive the study plan.

[1042] Step 7:

[1043] The user begins studying based on the received study plan, and as they proceed with their studies, they input their progress and feedback about their studies into the system.

[1044] Step 8:

[1045] The device sends the feedback information entered by the user to the server, including the learning progress and points that were difficult.

[1046] Step 9:

[1047] The server stores the received feedback in a database and analyzes it again. Based on the feedback information, the effectiveness of the learning plan is evaluated.

[1048] Step 10:

[1049] The server re-executes the generation component as needed to generate a new learning plan that reflects the feedback, and then transmits the new learning plan to the user's device.

[1050] Step 11:

[1051] Users receive new study plans and continue their studies, which allows for continuous provision of optimal learning support for each individual learner.

[1052] Example 1

[1053] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1054] In modern society, income disparities between parents create educational disparities for their children, which is a problem. Providing optimal learning plans for individual learners is particularly costly, preventing many families from benefiting from them. Furthermore, tracking learners' daily progress and adjusting learning plans accordingly requires a significant amount of work. A system that can solve this problem is needed.

[1055] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1056] In this invention, the server includes a processing device including a user registration component and means for inputting and saving learner information, a processing device including an analysis component and means for analyzing the learner information and extracting characteristics based on the learner's favorite subjects, weak subjects, and educational aspirations, a processing device including a generation component with a generative AI model and means for generating a study plan based on the characteristic data, a processing device including a study plan transmission component and means for transmitting the generated study plan to the learner's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the learner, and means for re-executing the generation component based on the feedback and adjusting the study plan as appropriate. This effectively solves the problem of educational disparities caused by income disparities and makes it possible to provide optimal study plans for individual learners at low cost.

[1057] A "user registration component" is a processing device that provides functionality for entering and saving learner information.

[1058] The "analysis component" is a processing device that provides a function for analyzing stored learner information and extracting characteristics based on strong subjects, weak subjects, and educational aspirations.

[1059] A "generative AI model" is a model that generates optimal learning plans based on machine learning technology.

[1060] A "generative component" is a processing device that includes a generative AI model and provides functionality for generating a learning plan based on feature data.

[1061] The "learning plan transmission component" is a processing device that provides a function for transmitting the generated learning plan to the learner's terminal.

[1062] A "feedback input component" is a processing device that provides functionality for inputting progress and feedback from a learner.

[1063] "Characteristic data" is information extracted by the analysis component regarding a learner's strong subjects, weak subjects, and educational aspirations.

[1064] A "study plan" is a customized study plan based on the learner's strengths and weaknesses, and their educational aspirations.

[1065] The present invention is a system that automatically generates and provides study plans to eliminate educational disparities due to parental income. The program processing of this system will be specifically described below.

[1066] Overall system configuration

[1067] The system starts when a user accesses the system using a terminal and inputs and sends the necessary information. The server receives the information, generates a learning plan through analysis and generation components, and sends it to the user's terminal. The server also has the function of adjusting the learning plan based on feedback information from the user.

[1068] User registration component: Provides the ability to enter and save user information.

[1069] Analysis component: Analyzes stored user information and extracts characteristics based on strong and weak subjects and educational aspirations.

[1070] Generative component equipped with a generative AI model: Generates an optimal learning plan based on feature data.

[1071] Study plan sending component: Sends the generated study plan to the user's device.

[1072] Feedback input component: Has a function for inputting progress and feedback from the user.

[1073] Operation details of each component

[1074] User Registration Component

[1075] After accessing the system, users register. When registering, they enter basic information such as email address and password to create an account on the system. They then enter additional information such as their grade, favorite subjects, favorite subjects, and desired school. The entered information is sent to the server via the terminal and stored in the database. This process ensures that subsequent analysis and plan generation are more effective when users enter accurate information.

[1076] Analytics Components

[1077] The server runs an analysis component based on user information stored in the database. The analysis component processes the received learner information and extracts characteristics related to the learner's strong and weak subjects and educational aspirations. This process uses SQL queries and data mining techniques. This clarifies the individual learner's learning style and needs.

[1078] Generative components equipped with generative AI models

[1079] The generative component operates based on the analysis results. Using a generative AI model that leverages machine learning techniques, the generative component generates a learning plan based on the obtained feature data. This model utilizes existing data to provide a customized learning plan suited to the learner. For example, it may suggest specific learning content to further develop strong subjects or specific methods to overcome weak subjects.

[1080] Learning Plan Submission Component

[1081] The generated study plan is sent to the user's device via the study plan sending component. There are two ways to send the plan: by sending a notification to the email address entered by the user when registering, or by making it available for viewing on the system's dashboard. This allows users to check their study plan at any time and proceed with their studies based on it.

[1082] Feedback Input Component

[1083] As they study, users can use their devices to input feedback about their progress and learning into the system. This feedback includes detailed information such as whether they are making good progress or whether a particular subject is difficult. This feedback information is also sent back to the server and stored in a database.

[1084] Adjusting your learning plan based on feedback

[1085] The server analyzes the feedback using the feedback input component based on the saved feedback, and if necessary, re-runs the generation component to adjust the learning plan. This process ensures that the user always receives a plan that is optimized for their learning progress.

[1086] Specific use cases

[1087] For example, if User A, a third-year junior high school student, were to use this system, he or she would enter information that their favorite subject is math and their weakest subject is English. They would also enter their desire to attend a public high school. The server would then analyze this information, and the generative AI model would generate an optimal learning plan accordingly. This plan would include specific details on how to improve math and how to overcome English.

[1088] The generated study plan is sent to User A's device, and User A studies according to the plan. After a few weeks, User A provides feedback on their progress and difficult points. The server receives this feedback, analyzes and adjusts it again, and generates and sends a new study plan.

[1089] Prompt Sentence Examples

[1090] "User A, a third-year junior high school student, has entered the following information: his best subject is math, his worst subject is English, and his desired school is a public high school. Based on this information, please generate an optimal study plan for User A and provide specific study content for at least one week according to that plan."

[1091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1092] Step 1:

[1093] User Registration:

[1094] A user accesses the system and registers. During this process, the user enters an email address and password, which are then sent to the server. The server stores the received email address and password in a database and creates a new account. Input: Email address, password. Output: Creation of a new account.

[1095] Step 2:

[1096] Enter your user information:

[1097] The user then enters detailed information such as grade, favorite subjects, weak subjects, and desired school. This information is also sent to the server via the terminal. The server stores the received information in a database. Input: grade, favorite subjects, weak subjects, desired school. Output: User information saved.

[1098] Step 3:

[1099] User information analysis:

[1100] The server retrieves user information stored in the database and sends it to the analysis component. The analysis component analyzes this information and extracts features based on the learner's strong and weak subjects, and educational aspirations. For example, it uses SQL queries to extract specific information from the database and then uses data mining algorithms to extract features. Input: Stored user information. Output: Extracted feature data.

[1101] Step 4:

[1102] Learning plan generation:

[1103] The server's generation component uses a generative AI model to generate an optimal learning plan based on the extracted feature data. The generative AI model uses machine learning algorithms to provide a customized learning plan tailored to the user's individual learning needs. Input: Feature data. Output: Customized learning plan.

[1104] Step 5:

[1105] Submit your study plan:

[1106] The server sends the generated learning plan to the user's device via the learning plan sending component. The sending is done via a notification to the email address registered by the user or via the dashboard within the system. Input: Generated learning plan. Output: Delivery of the learning plan to the user's device.

[1107] Step 6:

[1108] Feedback Input:

[1109] As the user progresses with their studies, they input feedback about their progress and learning from their device. Feedback includes learning progress and difficulties they are experiencing in specific subjects. Input: Learning progress and feedback information. Output: Feedback sent to the server via the device.

[1110] Step 7:

[1111] Feedback analysis and learning plan adjustment:

[1112] The server stores the received feedback information in a database. The server's feedback input component analyzes this feedback information and runs the generation component again to make any necessary adjustments to the learning plan. This generates a new learning plan optimized for the latest progress. Input: Feedback information. Output: Adjusted learning plan.

[1113] (Application example 1)

[1114] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1115] The challenge is to provide an environment where learners can make effective use of their travel time and study efficiently. There is also a need to reduce educational disparities based on parental income and ensure that all learners have equal opportunities to receive high-quality education. To realize such an environment, it is necessary to provide a learning support system inside self-driving vehicles.

[1116] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1117] In this invention, the server includes a processing device including a registration component, which inputs and saves learner information; a processing device including an analysis component, which analyzes the learner information; a processing device including a generation component, which generates a study plan based on the analysis results; a processing device including a study plan transmission component, which transmits the generated study plan to the learner's device; a processing device including a feedback input component, which inputs progress and feedback from the learner; and a processing device including a user interface corresponding to multiple modes of transportation, which displays study content on a device in an autonomous vehicle and supports study progress in real time. This makes it possible to make effective use of time while traveling, reduce educational disparities, and promote efficient learning.

[1118] A "registration component" is a processing device capable of inputting and storing learner information.

[1119] An "analysis component" is a processing device that has the function of analyzing input learner information.

[1120] A "generative component" is a processing device that has the functionality to generate a lesson plan based on the analyzed results.

[1121] The "learning plan transmission component" is a processing device that has the function of transmitting the generated learning plan to the learner's terminal.

[1122] A "feedback input component" is a processing device that has the function of inputting progress and feedback from a learner.

[1123] A "user interface" is a processing device that displays learning content on a terminal inside an autonomous vehicle and has the function of supporting learning progress in real time.

[1124] An "autonomous vehicle" is a vehicle that operates autonomously and drives itself without occupant intervention.

[1125] A "study plan" is a customized plan of learning activities based on information such as the learner's strong and weak subjects, and their educational aspirations.

[1126] User registration and data entry

[1127] First, the user registers on a terminal inside the autonomous vehicle. When registering, the user enters basic information such as their grade, favorite subjects, weak subjects, and educational aspirations. This information is then sent to the server by the terminal.

[1128] Analyzing data and generating learning plans

[1129] The server stores the received user data in a database. The stored data is analyzed by an analysis component to extract characteristics based on the user's strong and weak subjects and educational aspirations. Next, a generation component generates a study plan based on the analysis results. This plan is customized for each user and also references data from other users stored in the database.

[1130] Learning plan delivery and user interface

[1131] The server sends the generated learning plan to the user's terminal using a learning plan sending component. The terminal in the autonomous vehicle receives the learning plan, displays the learning content through a user interface, and supports the learning progress in real time.

[1132] Gather feedback and adjust your plan

[1133] As the user progresses with their learning, they input feedback about their progress and learning into the system via their device. This feedback information is then sent back to the server and stored in a database. The server then analyzes this information using the feedback input component and, if necessary, re-executes the generation component to adjust the learning plan.

[1134] Hardware and Software Usage

[1135] The server uses Python, with SQLite or PostgreSQL as the database. Data analysis tools such as Pandas are used for data analysis, and machine learning models such as Scikit-Learn are used for the generation component. The terminal inside the autonomous vehicle uses a tablet or smartphone to display the learning plan and support feedback input.

[1136] Specific examples

[1137] For example, if User A, a third-year junior high school student, uses this system, his or her best subject is math, his or her weakest subject is English, and he or she hopes to go on to a public high school. When this information is entered, the server's analysis component operates based on this data, and the generation component generates a specific study plan. This study plan includes content to strengthen math and methods for overcoming English. This plan is sent to User A's device, and User A proceeds with his or her studies according to the plan. After a few weeks, User A provides feedback on his or her progress and difficult points, and the server uses that information to readjust the study plan.

[1138] Prompt Sentence Examples

[1139] "User A has been newly registered. Next, please send him the 'Study Plan Generation' prompt."

[1140] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1141] Step 1:

[1142] User registration and data entry

[1143] The user registers a new account on a terminal inside the autonomous vehicle.

[1144] Input: Basic information such as the user's grade, favorite subjects, favorite subjects, and educational aspirations

[1145] Operation: This information is sent from the device to the server.

[1146] Output: User information is saved on the server

[1147] Step 2:

[1148] Data storage and analysis

[1149] The server stores the received user data in a database.

[1150] Input: User basic information

[1151] How it works: Analyze the saved data using data analysis tools such as Pandas to extract characteristics based on strong and weak subjects and educational aspirations.

[1152] Output: Feature-extracted data

[1153] Step 3:

[1154] Generate a learning plan

[1155] The server's generation component generates a learning plan based on the analysis results.

[1156] Input: extracted feature data

[1157] How it works: Using machine learning models such as Scikit-Learn, it automatically generates a study plan that includes ways to improve your strengths and overcome your weaknesses.

[1158] Output: personalized learning plan

[1159] Step 4:

[1160] Providing study plans

[1161] The server transmits the generated learning plan to the user's terminal using a learning plan transmission component.

[1162] Input: Personalized Learning Plan

[1163] Operation: Sending a plan from the server to the device

[1164] Output: The lesson plan displayed on the device

[1165] Step 5:

[1166] Learning and gathering feedback

[1167] The user follows the learning plan provided via the device and inputs feedback on progress and problems encountered during the learning process.

[1168] Input: User learning progress information, feedback

[1169] Action: The device sends the entered information to the server.

[1170] Output: Feedback data stored on the server

[1171] Step 6:

[1172] Analyze feedback and adjust plans

[1173] The server analyzes the feedback information and re-runs the generation component to adjust the learning plan as needed.

[1174] Input: Feedback data

[1175] How it works: The feedback information is analyzed using tools like Pandas, and a new learning plan is generated using the machine learning model again.

[1176] Output: Adjusted study plan

[1177] Step 7:

[1178] New learning plans available

[1179] The server then sends the adjusted study plan back to the user's device.

[1180] Input: Adjusted study plan

[1181] Action: Retransmission from server to device

[1182] Output: The new study plan displayed on your device

[1183] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1184] This invention is a system that automatically generates and provides a learning plan that takes into account the learner's emotions by combining an emotion engine. By recognizing the learner's emotions and reflecting that information in the learning plan, more effective learning support is realized.

[1185] User registration and data entry

[1186] Users access the system and register as new users. They enter user information (such as name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and register in the system. The registration information is sent to the server via the terminal.

[1187] Analyzing data and generating learning plans

[1188] The server stores the received user data in a database. The analysis component analyzes the user data and extracts the learner's characteristics. The generation component then generates an optimal learning plan based on the analysis results. During this process, the emotion engine analyzes the learner's emotional information and influences the generation of the learning plan. Specifically, the difficulty and volume of the learning content are adjusted taking into account the learner's emotional state (e.g., stress level and motivation level).

[1189] Providing study plans

[1190] The server uses a learning plan transmission component to send the generated learning plan to the user's device. The user then checks the learning plan on their device and proceeds with their studies according to the plan.

[1191] Collecting feedback

[1192] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[1193] Analyze feedback and adjust your learning plan

[1194] The server stores the received feedback in a database and analyzes it using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the learning plan to take into account the learner's latest emotional state.

[1195] Specific examples

[1196] For example, consider the case where User B, a third-year junior high school student, uses this system. User B enters that his or her favorite subject is science, his or her weakest subject is Japanese, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the user's characteristics. Next, the generation component generates an optimal study plan, and the emotion engine adjusts the plan's difficulty taking the stress level into account. This study plan is sent to User B's device, and User B proceeds with his or her studies according to the plan. After studying, User B enters his or her progress and current emotional state into the system as feedback, and the server readjusts the study plan based on this.

[1197] In this way, by combining an emotion engine, the present invention can provide a customized learning plan that corresponds to the individual emotional state of the learner, thereby achieving more effective learning support.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The user accesses the system's registration page and registers as a new user. They enter user information (name, grade, favorite subjects, favorite subjects, desired school, emotional state, etc.) and click the "Register" button.

[1201] Step 2:

[1202] The terminal sends the information entered by the user to the server, where it is treated as learner information.

[1203] Step 3:

[1204] The server stores the received user data in a database, which is used to generate a learning plan.

[1205] Step 4:

[1206] The server runs an analysis component to analyze the stored user data, extracting characteristics such as the user's favorite subjects, weak subjects, and educational aspirations.

[1207] Step 5:

[1208] The server retrieves the user's emotional state data and runs an emotion engine that analyzes the user's emotional state (e.g., stress level and motivation state).

[1209] Step 6:

[1210] The server uses a generation component to generate an optimal learning plan based on the analysis results and the analysis results of the emotion engine, the learning plan including content based on the user's strengths, weaknesses, and emotional state.

[1211] Step 7:

[1212] The server uses a learning plan sending component to send the generated learning plan to the user's terminal, so that the user can receive the learning plan.

[1213] Step 8:

[1214] The user begins studying based on the received study plan, and as they proceed with their studies, they can input feedback about their progress and learning into the system.

[1215] Step 9:

[1216] The terminal transmits the feedback information and emotional state input by the user to the server. The feedback information includes the learning progress, difficult points, and the current emotional state (e.g., fatigue or a sense of accomplishment).

[1217] Step 10:

[1218] The server stores the received feedback in a database, and the stored feedback information and emotional state are used to adjust the learning plan.

[1219] Step 11:

[1220] The server utilizes the feedback input component to analyze the feedback and emotional state. Based on the analysis results, the generation component is executed again to generate a new learning plan that reflects the feedback and emotional information.

[1221] Step 12:

[1222] The server then transmits the newly generated study plan to the user's device again, allowing the user to receive the updated study plan.

[1223] Step 13:

[1224] The user then resumes their studies based on the updated study plan, which allows the system to continuously provide optimal learning support for each individual learner, taking into account their emotional state.

[1225] Example 2

[1226] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1227] Conventional learning support systems provide learning plans without taking into account the learner's emotional state, making it difficult to provide appropriate learning support based on the learner's mental state. As a result, there are concerns that the learner's motivation may decrease and stress may increase. Therefore, there is a need to provide learning plans that appropriately reflect the learner's emotional state.

[1228] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for inputting and saving user information, means for analyzing the user information and the emotional state, and means for adjusting the content and difficulty of the study plan using an emotion engine. This makes it possible to provide an appropriate study plan according to the learner's emotional state, thereby maintaining the learner's motivation and reducing stress.

[1229] A "registration component" is a means for entering and storing learner information.

[1230] "User information" is information including the learner's name, grade, favorite subjects, least favorite subjects, educational aspirations, and emotional state.

[1231] The "analysis component" is a means for acquiring and analyzing user information to analyze the learner's characteristics and emotional state.

[1232] "Emotional information" is information that indicates the learner's current emotional state, including stress level and motivation level.

[1233] The "generative component" is a means of generating a learning plan based on the analysis results and adjusting the content and difficulty level using an emotion engine.

[1234] The "emotion engine" is a function that analyzes the learner's emotional state and adjusts the content and difficulty of the learning plan based on the results.

[1235] The "study plan transmission component" is a means for transmitting the generated study plan to the user's terminal.

[1236] A "terminal" is an electronic device that a user uses to review a learning plan and enter feedback.

[1237] The "feedback input component" is a means for inputting progress and feedback from the learner, and is used to regenerate the learning plan.

[1238] A "study plan" is a customized study plan that takes into account the user's strong and weak subjects, academic aspirations, and emotional state.

[1239] "Server" is a central processing unit that stores and analyzes user information, and generates and transmits study plans.

[1240] This invention is a system that automatically generates a learning plan that takes into account the learner's emotions. This system is mainly composed of three elements: a server, a terminal, and a user. These elements work together to provide a customized learning plan that corresponds to the learner's individual emotional state.

[1241] User registration and data entry

[1242] Users access the system and first register. When registering, they enter information such as their name, grade, favorite subjects, favorite subjects, desired school, and emotional state (e.g., stress level and motivation). This information is sent to the server via a terminal. Terminals can be electronic devices such as PCs, tablets, and smartphones.

[1243] Data storage

[1244] The server stores the received user information in a database. This storage process uses a database management system (e.g., MySQL, PostgreSQL). The stored data is used for later analysis and learning plan generation.

[1245] Analyzing the data

[1246] The server's built-in analysis component retrieves user information from the database and analyzes it. The analysis covers learning progress by grade, trends in strong and weak subjects, the level of desired educational destination, emotional state, etc. Data analysis tools such as Python and R are used for this analysis.

[1247] Generate a learning plan

[1248] The generation component generates an optimal learning plan based on the analysis results of the analysis component. At this time, the emotion engine analyzes the learner's emotional state and adjusts the content and difficulty of the plan. For example, a user with a high stress level will be suggested learning content that is less stressful.

[1249] Submit your study plan

[1250] The server sends the generated learning plan to the user's device via the learning plan sending component, using a communication protocol such as HTTP or WebSocket.

[1251] Review and execute your study plan

[1252] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the learning content and proceed with their learning according to the plan.

[1253] Collecting feedback

[1254] The user inputs feedback about their learning progress and emotional state into the system, including their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). The feedback information is sent to the server via the terminal.

[1255] Feedback storage and analysis

[1256] The server stores the received feedback information in a database. The feedback input component analyzes the stored data and generates a new learning plan based on the analysis results. The emotion engine is also involved in this process, providing a plan that reflects the latest emotional state.

[1257] Specific examples

[1258] For example, if User B, a third-year junior high school student, uses this system, he or she accesses the system and registers his or her name, grade, favorite subject (science), least favorite subject (Japanese), desired school, and emotional state (current stress level). This information is sent to the server via the terminal.

[1259] The server receives the information and stores it in a database. After storage, the analysis component analyzes the data. Based on the analysis results, the generation component generates an optimal learning plan, and the emotion engine adjusts the difficulty of the plan taking into account the stress level. This learning plan is then sent to User B's device via the learning plan sending component.

[1260] User B checks the plan received on his / her device and begins studying according to the plan. After studying, he / she inputs his / her progress and emotional state as feedback and sends it to the server via his / her device. The server analyzes the feedback and generates a new study plan. In this way, the system constantly updates the study plan based on the latest user situation.

[1261] Prompt Sentence Examples

[1262] You can simulate specific scenarios by feeding prompts like the following into the generative AI model:

[1263] "Please tell us the steps for a third-year junior high school student to use the system to generate a lesson plan that takes emotional information into account. For example, please explain the case of a user who is good at science but not good at Japanese."

[1264] In this way, this system provides a learning plan that takes into account the learner's emotional state, providing effective learning support.

[1265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1266] Step 1:

[1267] Users access the system and register. The information they enter includes their name, grade, favorite subjects, favorite subjects, desired school, emotional state (e.g., stress level), etc. This information is entered into the terminal through an input form, and the contents are sent to the server. Input: User information, Output: Data sent to the server.

[1268] Step 2:

[1269] The server stores the received user information in a database. A database management system (e.g., MySQL, PostgreSQL) is used for the storage process. This allows user information to be stored safely for a long period of time. Input: Transmitted user information, Output: Data stored in the database.

[1270] Step 3:

[1271] The analysis component installed on the server retrieves user information from the database and performs analysis. The analysis uses indicators such as learning progress by grade, trends in strong and weak subjects, the level of desired educational institution, and emotional state. Data analysis tools such as Python and R are used for this analysis. Input: User information in the database, Output: Analysis results.

[1272] Step 4:

[1273] The generation component receives the analysis results from the analysis component and generates an optimal study plan. The emotion engine is involved in this process, adjusting the content and difficulty of the plan taking into account the user's emotional state. Specifically, a user with a high stress level will be provided with a reduced study plan consisting of relatively easy content. Input: Analysis results, Output: Optimized study plan.

[1274] Step 5:

[1275] The server sends the generated learning plan to the user's device using the learning plan sending component. This sending uses a communication protocol such as HTTP or WebSocket. Input: Generated learning plan, Output: Data sent to the user's device.

[1276] Step 6:

[1277] The user checks the received learning plan on their device. After checking, they start studying according to the plan. Specifically, they view the details of the study content and carry out their daily study plan. Input: Sent learning plan, Output: User starts studying.

[1278] Step 7:

[1279] The user inputs feedback about their learning progress and emotional state into the system. This includes their learning progress, items they found difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). Feedback information is sent to the server via the terminal. Input: User feedback, Output: Data sent to the server.

[1280] Step 8:

[1281] The server stores the received feedback information in a database. The feedback input component analyzes the stored data, and the generation component is executed again based on the analysis results to generate a new learning plan. The emotion engine is also utilized this time, providing a plan that reflects the learner's latest emotional state. Input: Feedback information, Output: Newly generated learning plan.

[1282] (Application example 2)

[1283] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1284] Existing work plan generation systems are unable to take into account the user's emotional state, which can lead to reduced work efficiency. It is also difficult to dynamically adjust plans based on the user's strengths and weaknesses, as well as their progress. This leads to the accumulation of stress and fatigue in the user, resulting in reduced work productivity.

[1285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a processing device including a registration component and means for inputting and saving user information, a processing device including an analysis component and means for analyzing the user information, a processing device including a generation component and means for generating a work plan based on the analysis results, a processing device including an emotion engine and means for analyzing the user's emotional state and influencing the work plan, a processing device including a work plan transmission component and means for transmitting the generated work plan to the user's terminal, and a processing device including a feedback input component and means for inputting progress and feedback from the user, and means for re-executing the generation component based on the feedback. This enables flexible generation and adjustment of work plans that take into account the user's emotional state and progress.

[1286] A "registration component" is a processing device that has a means for inputting and storing user information.

[1287] "User information" refers to basic information about the user (such as name, favorite tasks, least favorite tasks, emotional state, etc.).

[1288] An "analysis component" is a processing device that has means for analyzing user information and extracting its characteristics.

[1289] A "generation component" is a processing device that has means for generating an optimal work plan based on the analysis results.

[1290] The "emotion engine" is a processing device that has the means to analyze the user's emotional state and reflect that information in the work plan.

[1291] A "work plan" refers to specific work procedures and schedules that are created taking into account the user's characteristics and emotional state.

[1292] The "work plan transmission component" is a processing device that has means for transmitting the generated work plan to the user's terminal.

[1293] A "feedback input component" is a processing device that has means for inputting feedback from a user regarding progress and emotional state.

[1294] "Feedback" refers to input information about the progress of the task and the user's emotional state after the task.

[1295] This invention is a system that automatically generates and provides work plans by combining an emotion engine and taking into account the user's emotional state. Specifically, by recognizing the user's emotions and reflecting that information in the work plan, more effective work support is realized.

[1296] User registration and data entry

[1297] A user accesses the system and enters and saves basic information through the registration component. The user information includes name, favorite tasks, least favorite tasks, and emotional state. This information is sent from the user's terminal to the server and stored in the server's database.

[1298] Analyzing data and generating work plans

[1299] The server stores the received user data in a database. The analysis component then analyzes this data and extracts the user's characteristics. The generation component generates an optimal work plan based on the analysis results. The emotion engine is involved in this process, adjusting the difficulty and amount of the work content based on the user's emotional state (such as stress level and motivation level).

[1300] Providing a work plan

[1301] The server sends the generated work plan to the user's terminal via the work plan sending component. The user checks the work plan on their own terminal and proceeds with the work according to the plan.

[1302] Collecting feedback

[1303] After completing the task, the user inputs feedback about their progress and emotional state into the system. The feedback includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue, accomplishment). This information is sent from the user's device to the server.

[1304] Analyze feedback and adjust work plan

[1305] The server stores the received feedback in a database and analyzes it through the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan that reflects the feedback. The emotion engine is also involved in this process, adjusting the work plan to take into account the user's latest emotional state.

[1306] Specific examples

[1307] As a concrete example, consider a scenario in which Worker A at a factory uses this system. Worker A inputs that his or her strongest task is assembly, his or her weakest task is welding, and that he or she is currently feeling stressed as an emotional state. The server receives this data, and the analysis component analyzes the worker's characteristics. Next, the generation component generates an optimal work plan, and the emotion engine adjusts the plan's difficulty by taking the worker's stress level into account. This work plan is sent to Worker A's device, and Worker A proceeds with the work according to the plan. After the work, Worker A inputs his or her progress and current emotional state into the system as feedback, and the server readjusts the work plan based on this.

[1308] Hardware and software used

[1309] This system requires a wearable device (e.g., a device that acquires vital signs) as an emotion sensor, a data transmission terminal, and a work support computer system. The software used includes Python for data analysis, MySQL for database management, and a machine learning model for feedback analysis.

[1310] Prompt Sentence Examples

[1311] "Generate the optimal work plan for the user's current stressful situation."

[1312] This enables flexible creation and adjustment of work plans that take into account the user's emotional state and progress.

[1313] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1314] Step 1:

[1315] A user accesses the system using a terminal. The user inputs basic information such as name, favorite tasks, least favorite tasks, and emotional state. This input information is sent from the terminal to the server and stored in the server's database. The input data is saved as properly formatted data by the registration component.

[1316] Step 2:

[1317] The server retrieves user information stored in the database. The analysis component uses this information to analyze the user's characteristics. Specifically, it extracts information such as the user's strengths and weaknesses, their current emotional state, and so on. This analysis data is used in the next phase of work plan generation.

[1318] Step 3:

[1319] The server's generation component generates an optimal work plan based on the analysis data. Here, the emotion engine analyzes the user's emotional state and adjusts the difficulty and amount of the work plan based on the results. For example, if the stress level is high, adjustments may be made such as reducing the amount of work. The generated work plan is temporarily stored in a database.

[1320] Step 4:

[1321] The server sends the work plan generated using the work plan sending component to the user's device. The user checks the provided work plan on their device and starts working according to the plan. This plan is optimized taking into account the user's emotional state, allowing the user to work efficiently.

[1322] Step 5:

[1323] After completing the task, the user again uses the device to input feedback about their progress and emotional state into the system. This feedback information includes the progress of the task, any items that were difficult, and their current emotional state (e.g., fatigue or a sense of accomplishment). This information is sent from the device to the server and stored in a database.

[1324] Step 6:

[1325] The server analyzes the received feedback using the feedback input component. Based on the analysis results, the generation component is executed again to generate a new work plan. The emotion engine also participates in this process, generating a plan that reflects the latest emotional state. The newly generated work plan is then sent back to the user's device.

[1326] Step 7:

[1327] The user then checks the work plan again and proceeds with the work according to the adjusted plan. This cycle is repeated depending on the user's emotional state and work progress, making it possible to provide optimal work support.

[1328] 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.

[1329] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1330] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1331] 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.

[1332] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1333] 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.

[1334] 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).

[1335] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1336] 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."

[1337] 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.

[1338] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1339] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1340] 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.

[1341] 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.

[1342] 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.

[1343] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1344] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1345] 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.

[1346] 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.

[1347] 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.

[1348] 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.

[1349] The following is further disclosed regarding the above embodiment.

[1350] (Claim 1)

[1351] 1. A processing device including a registration component,

[1352] a registration component for entering and storing learner information;

[1353] 1. A processing device including an analytical component,

[1354] means for the analysis component to analyze the learner information;

[1355] A processing device including a generation component,

[1356] means for generating a lesson plan based on the analysis results, wherein the generation component

[1357] 1. A processing device including a lesson plan transmission component,

[1358] a means for transmitting the generated learning plan to a learner's terminal by the learning plan transmission component;

[1359] 1. A processing device including a feedback input component,

[1360] a feedback input component for inputting progress and feedback from a learner;

[1361] means for re-executing the generation component based on said feedback.

[1362] (Claim 2)

[1363] 2. The system according to claim 1, wherein the study plan is customized based on the learner's strong subjects, weak subjects, and educational aspirations.

[1364] (Claim 3)

[1365] 10. The system of claim 1, wherein the lesson plan is generated by a generation component using data of other learners stored in a database.

[1366] "Example 1"

[1367] (Claim 1)

[1368] 1. A processing device including a user registration component, comprising:

[1369] a means for said user registration component to input and store learner information;

[1370] 1. A processing device including an analytical component,

[1371] The analysis component analyzes the learner information and extracts features based on the learner's favorite subjects, weak subjects, and educational aspirations;

[1372] 1. A processing device including a generative component that includes a generative AI model,

[1373] A generation component of the generative AI model generates a learning plan based on the feature data;

[1374] 1. A processing device including a lesson plan transmission component,

[1375] a means for transmitting the generated learning plan to a learner's terminal by the learning plan transmission component;

[1376] 1. A processing device including a feedback input component,

[1377] a feedback input component for inputting progress and feedback from a learner;

[1378] The system includes means for re-running the generation component based on said feedback and adjusting the learning plan accordingly.

[1379] (Claim 2)

[1380] 2. The system according to claim 1, wherein the study plan is customized based on the learner's strong subjects, weak subjects, and educational aspirations.

[1381] (Claim 3)

[1382] 10. The system of claim 1, wherein the lesson plan is generated by a generation component using data of other learners stored in a database.

[1383] "Application Example 1"

[1384] (Claim 1)

[1385] 1. A processing device including a registration component,

[1386] a registration component for entering and storing learner information;

[1387] 1. A processing device including an analytical component,

[1388] means for the analysis component to analyze the learner information;

[1389] A processing device including a generation component,

[1390] means for generating a lesson plan based on the analysis results, wherein the generation component

[1391] 1. A processing device including a lesson plan transmission component,

[1392] a means for transmitting the generated learning plan to a learner's terminal by the learning plan transmission component;

[1393] 1. A processing device including a feedback input component,

[1394] a feedback input component for inputting progress and feedback from a learner;

[1395] means for re-executing the generation component based on said feedback;

[1396] 1. A processing device including a user interface corresponding to a plurality of means of transportation,

[1397] The system includes a means for displaying learning content on a terminal within an autonomous vehicle and supporting learning progress in real time.

[1398] (Claim 2)

[1399] 2. The system according to claim 1, wherein the study plan is customized based on the learner's strong subjects, weak subjects, and educational aspirations.

[1400] (Claim 3)

[1401] 10. The system of claim 1, wherein the lesson plan is generated by a generation component using data of other learners stored in a database.

[1402] "Example 2: Combining Emotion Engines"

[1403] (Claim 1)

[1404] 1. A processing system including a registration component for entering and storing user information,

[1405] a means for the registration component to input and store the learner's emotional information;

[1406] 1. A processing system including an analysis component that analyzes user information,

[1407] The analysis component analyzes the user information and analyzes the emotional state;

[1408] a processing system including a generation component that generates a lesson plan based on the analysis results,

[1409] a means for the generation component to adjust the content and difficulty of the lesson plan using an emotion engine;

[1410] a processing system including a lesson plan sending component that sends the generated lesson plan to a terminal;

[1411] The learning plan sending component has a means for sending the learning plan to a user's terminal;

[1412] 1. A processing system including a feedback input component for inputting progress and feedback,

[1413] The system wherein the feedback input component includes means for re-executing the generation component based on feedback from the learner.

[1414] (Claim 2)

[1415] 2. The system of claim 1, wherein the learning plan is customized based on the learner's emotional state, strong subjects, weak subjects, and educational aspirations.

[1416] (Claim 3)

[1417] 10. The system of claim 1, wherein the lesson plan is generated by a generation component using data of other learners stored in a database.

[1418] "Application example 2 when combining emotion engines"

[1419] (Claim 1)

[1420] 1. A processing device including a registration component,

[1421] a registration component for inputting and storing user information;

[1422] 1. A processing device including an analytical component,

[1423] means for the analysis component to analyze the user information;

[1424] A processing device including a generation component,

[1425] means for generating an operation plan based on the analysis results;

[1426] A processing device including an emotion engine,

[1427] means for the emotion engine to analyze the user's emotional state and influence the work plan;

[1428] 1. A processing device including a work plan transmission component,

[1429] a means for transmitting the generated work plan to a user's terminal by the work plan transmission component;

[1430] 1. A processing device including a feedback input component,

[1431] a means for said feedback input component to input progress and feedback from a user;

[1432] means for re-executing the generation component based on said feedback.

[1433] (Claim 2)

[1434] 2. The system according to claim 1, wherein the work plan is customized based on the user's strengths, weaknesses, and desired tasks.

[1435] (Claim 3)

[1436] 2. The system of claim 1, wherein the work plan is generated by a generation component using data of other users stored in a database. [Explanation of symbols]

[1437] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. 1. A processing device including a registration component, a registration component for entering and storing learner information; 1. A processing device including an analytical component, means for the analysis component to analyze the learner information; A processing device including a generation component, means for generating a lesson plan based on the analysis results, wherein the generation component 1. A processing device including a lesson plan transmission component, a means for transmitting the generated learning plan to a learner's terminal by the learning plan transmission component; 1. A processing device including a feedback input component, a feedback input component for inputting progress and feedback from a learner; means for re-executing the generation component based on said feedback.

2. 2. The system according to claim 1, wherein the study plan is customized based on the learner's strong subjects, weak subjects, and educational aspirations.

3. 10. The system of claim 1, wherein the lesson plan is generated by a generation component using data of other learners stored in a database.

Images