System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting and analyzing learning progress data of a student in real time using a generation model; means for generating a customized learning program based on an analysis result using the generation model; means for providing the generated learning program to a terminal of the student; means for creating a food ingredient procurement plan using the generation model for optimizing food ingredient demand prediction and stock management; and means for procuring food ingredients and providing meals in cooperation with local restaurants and retail stores based on the generated procurement plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's society, where declining birth rates are a serious problem, parents raising children are struggling with the high cost of education and food. These burdens increase parents' financial anxiety and may ultimately lead to a decline in the birth rate. Furthermore, there is a lack of efficient and personalized educational methods, and insufficient support is provided based on students' learning progress. Meanwhile, in terms of meals, the school lunch supply system results in food waste and food loss. There is a need for a system that solves these issues and provides high-quality education and healthy meals while reducing the burden of child-rearing. [Means for solving the problem]

[0005] The system of the present invention uses AI, including generative models, to provide a means for collecting and analyzing students' learning progress data in real time. This allows the system to generate individually optimized learning programs using the generative models and provide them to students' devices. Furthermore, the system also includes a means for creating ingredient procurement plans using generative models for optimizing ingredient demand forecasts and inventory management. This allows the system to procure ingredients in cooperation with local restaurants and retailers and provide school lunches at schools or designated pickup locations. This system reduces the burden of education and meal costs, alleviates parents' financial concerns, and contributes to resolving the issue of a declining birthrate.

[0006] "Generative models" refer to machine learning algorithms and artificial intelligence technologies used to analyze student learning progress data and food ingredient demand forecast data to generate optimal learning programs and procurement plans.

[0007] "Learning progress data" refers to a set of data that shows a student's individual learning situation, such as how much material they have consumed, what they have understood, and their performance on tests and assignments.

[0008] "Customized learning program" refers to a program that uses generative models to provide individually optimized learning materials and study plans based on each student's learning progress data.

[0009] "Educational expenses" refers to all expenses paid by parents or guardians for their children's education.

[0010] "Food expenses" refers to all expenses incurred for the food a child consumes in their daily lives.

[0011] "Demand forecasting" refers to predicting future demand for food ingredients and supplies based on past consumption data and seasonal trends.

[0012] "Inventory management" refers to the management of necessary supplies and ingredients so that they can be stored appropriately and supplied in the required quantities at the required times.

[0013] "Procurement planning" refers to planning the supply method and schedule for necessary supplies and ingredients based on demand forecast data.

[0014] "Local restaurants and retail stores" refers to restaurants and food retail stores operating within a specific area.

[0015] "School lunch" refers to meals provided to students at schools or other facilities. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system of this invention uses a generative model to collect and analyze students' learning progress data in real time and provide customized learning programs free of charge or at a low cost. It also uses the generative model to optimize food demand forecasting and inventory management, and works with local restaurants and retailers to provide healthy school lunches to students free of charge, thereby reducing the burden on parents and reducing food waste.

[0038] Educational support implementation form

[0039] Data collection

[0040] The server collects students' test results, assignment submission status, and learning history in real time and stores them in a database. Students use learning applications through their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data.

[0041] Create a customized learning program

[0042] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends the program to the device.

[0043] Specific examples

[0044] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. The student can then use their device to access the customized learning program and study more efficiently.

[0045] Meal support implementation form

[0046] Demand forecasting and inventory management

[0047] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[0048] Procurement and Delivery

[0049] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[0050] Specific examples

[0051] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[0052] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[0053] The processing flow will be explained below.

[0054] Educational Support Program Processing Steps

[0055] Step 1: Collect data

[0056] Device: When students complete online tests or assignments, their results and progress data are recorded and sent to the server.

[0057] Server: Stores the received data in a database.

[0058] Specific actions

[0059] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[0060] The server stores this data in a database for later analysis.

[0061] Step 2: Analyze your learning progress

[0062] Server: Provides student learning progress data stored in a database to the generative model and performs analysis.

[0063] Device: Display progress on a dashboard so users can see student progress in real time.

[0064] Specific actions

[0065] The server inputs students' test scores and assignment submission status into the generative model, and analyzes the current situation and evaluates their level of understanding.

[0066] The device displays feedback on progress and level of understanding, which users (students and parents) can check.

[0067] Step 3: Create a customized learning program

[0068] Server: Uses the generative model to create a learning program optimized for each student and sends that program to the device.

[0069] Device: Displays received learning programs and allows students to access them.

[0070] Specific actions

[0071] Based on the generative model, the server selects teaching materials and exercises to strengthen the student's weak points and generates a customized learning program.

[0072] The generated learning program is sent to the terminal, and the student can access the program and start learning.

[0073] Step 4: Tracking and feedback

[0074] Terminal: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress has been made.

[0075] Server: Analyzes progress data and updates learning programs as needed.

[0076] Specific actions

[0077] When students complete online exercises on their devices, the results are automatically sent to the server.

[0078] The server analyzes this data and adjusts the learning program accordingly based on progress and level of understanding.

[0079] Meal Assistance Program Processing Steps

[0080] Step 1: Demand forecast

[0081] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[0082] Specific actions

[0083] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[0084] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[0085] Step 2: Plan your food procurement

[0086] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[0087] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[0088] Specific actions

[0089] The server calculates how much of each ingredient is needed based on the predicted demand.

[0090] The server automatically sends ordering information to local retailers and restaurants.

[0091] Step 3: Ingredient delivery and inventory management

[0092] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[0093] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[0094] Specific actions

[0095] The server receives order confirmation from the store and plans when to deliver the ingredients.

[0096] The store terminal sends an order confirmation and delivery completion notification to the server.

[0097] Step 4: Meal delivery and feedback

[0098] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[0099] Server: Analyzes the received data and reflects it in the next demand forecast.

[0100] Specific actions

[0101] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[0102] The server analyzes this data and further optimizes the food supply plan.

[0103] Through these steps, the system provides efficient and effective support in both education and feeding.

[0104] Example 1

[0105] 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."

[0106] With conventional learning programs and school lunch delivery systems, it was difficult to customize them to suit each student's learning progress, and food demand forecasting and inventory management were insufficient, which meant that educational effectiveness and meal quality were not fully improved. For this reason, there is a need for a system that provides individually optimized learning programs and efficiently manages ingredients and provides school lunches.

[0107] 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.

[0108] In this invention, the server includes means for collecting and analyzing a learner's learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the learner's information processing device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients and providing meals in cooperation with local restaurants and retailers based on the generated procurement plan, means for providing the learner with access to the customized learning program via the learner's information processing device, and means for providing the learner with meal pickup instructions via the learner's information processing device. This enables the provision of an individually optimized learning program and the efficient and prompt procurement of ingredients and provision of meals.

[0109] A "generative model" is a system that uses machine learning algorithms to learn patterns in data and make predictions or generate new data.

[0110] "Learning progress data" refers to data that indicates the results and progress a learner has achieved through their learning activities, and specifically includes test results, assignment submission status, learning history, etc.

[0111] "Real-time" means that a process or operation occurs immediately or with very little delay.

[0112] A "customized learning program" is a program that provides learning content and materials tailored to the needs and progress of individual learners.

[0113] An "information processing device" is an electronic device that has functions such as collecting, processing, storing, and transmitting data, and specifically includes tablets and personal computers.

[0114] "Demand forecasting" is the process of predicting future demand based on past data and various factors.

[0115] "Inventory management" means understanding the stock status of necessary goods and materials and maintaining and managing them appropriately.

[0116] "Food procurement planning" refers to the process of planning the types and quantities of ingredients needed based on predicted demand and securing them.

[0117] "Food and beverage establishment" means a facility that has a place or equipment for serving food and beverages, and specifically includes restaurants and cafeterias.

[0118] "Retailer" refers to a trader or company that sells goods to the general public.

[0119] "Learner" means a person who participates in an educational program or learning activity.

[0120] "Access" means making a system or data available.

[0121] "Pickup Instructions" means notices or instructions providing information regarding the pickup of goods or services.

[0122] The system of this invention uses a generative model to collect and analyze learner progress data in real time and provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, aiming to provide learners with healthy meals in collaboration with local restaurants and retailers.

[0123] Educational support implementation form

[0124] Data collection

[0125] The server collects learners' test results, assignment submission status, and learning history in real time and stores them in a database. Learners use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. The software used is a learning management system (LMS). This allows the server to always have the latest learning progress data.

[0126] Create a customized learning program

[0127] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates a learning program optimized for each learner and sends that program to the information processing device. The generative AI model used includes, for example, a large-scale GPT-based language model.

[0128] Specific examples

[0129] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to that student. The student can then use their device to access the customized learning program and study efficiently.

[0130] Example prompts to input to a generative AI model:

[0131] "Please create additional learning materials for today based on Learner A's latest learning progress data."

[0132] Meal support implementation form

[0133] Demand forecasting and inventory management

[0134] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, an ingredient procurement plan is created. The generative AI model used includes, for example, machine learning algorithms and statistical models.

[0135] Procurement and Delivery

[0136] Based on the generated procurement plan, the server places orders for the necessary ingredients with local restaurants and retailers. Each restaurant prepares the ingredients according to the order information sent from the server and delivers them according to the specified delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the specified pickup location.

[0137] Specific examples

[0138] For example, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[0139] Example prompts to input to a generative AI model:

[0140] "Please forecast the demand for ingredients needed for school lunches next Monday and create a procurement plan."

[0141] In this way, we will create a system that provides efficient and effective services to learners in both educational and dietary support, reducing the burden on parents while supporting high-quality education and healthy eating habits.

[0142] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0143] Educational support implementation form

[0144] Data collection and storage

[0145] Step 1: Collect training data

[0146] A user (learner) logs in to a learning application using a device (e.g., a tablet or PC).

[0147] The device collects learning data such as the results of tests taken by learners, assignment submission status, and learning history.

[0148] The server issues a log data request and receives the data in real time from the terminal.

[0149] Input: Learner test results, assignment submission status, learning history, etc.

[0150] Output: Training data received in real time

[0151] Step 2: Save your data

[0152] The server stores the received learning data in a database.

[0153] Perform validation to check for data consistency and duplication.

[0154] The server performs backups to ensure data integrity.

[0155] Input: Training data received in real time

[0156] Output: Training data stored in a database

[0157] Creating and delivering customized learning programs

[0158] Step 3: Analyze the data

[0159] The server uses the generative model to analyze the learning progress data stored in the database.

[0160] Apply statistical analysis and machine learning algorithms to identify learner strengths and weaknesses.

[0161] Input: Learning progress data stored in a database

[0162] Output: Analysis results for each learner

[0163] Step 4: Generate a customized learning program

[0164] The server inputs prompts into the generative model to generate a customized learning program.

[0165] The server optimizes and organizes the generated programs for each learner.

[0166] Input: Analysis results for each learner

[0167] Output: A customized learning program

[0168] Step 5: Deliver and execute the learning program

[0169] The server transmits the generated study program to the learner's terminal.

[0170] Learners use their devices to access their customized learning programs and begin their studies.

[0171] The device again transmits the learner's progress to the server.

[0172] Input: Customized Learning Program

[0173] Output: Learning program delivered to the device and new learning progress data

[0174] Specific actions

[0175] The device receives a "fraction calculation problem set" and displays explanatory videos on the learning screen, and the user (learner) works on them.

[0176] The server generates additional learning materials using a prompt such as "Student A's weak point: Please generate additional learning materials for fraction calculations" and sends them to the terminal.

[0177] Meal support implementation form

[0178] Demand forecasting and inventory management

[0179] Step 1: Collect historical data

[0180] The server collects past school lunch data and local consumption data.

[0181] The server stores the collected data in a database.

[0182] Input: Past school lunch data and local consumption data

[0183] Output: Meal data stored in a database

[0184] Step 2: Forecast demand

[0185] The server uses a generative AI model to analyze collected past data and predict future food demand.

[0186] The server determines the amount of ingredients to be procured based on the predicted data.

[0187] Input: Meal data stored in the database

[0188] Output: Demand forecast data for ingredients

[0189] Procurement planning and execution

[0190] Step 3: Create a procurement plan

[0191] The server creates a procurement plan based on the forecast data and generates a list of required ingredients.

[0192] Store procurement plans in a database.

[0193] Input: Demand forecast data for ingredients

[0194] Output: Procurement plan and ingredients list

[0195] Step 4: Order and deliver ingredients

[0196] The server transmits food ordering information to local restaurants and retailers based on the procurement plan.

[0197] Each store prepares ingredients according to the order information from the server and delivers them according to the specified schedule.

[0198] Input: Procurement plan and ingredients list

[0199] Output: Ordering information for local restaurants and retailers

[0200] Meal provision

[0201] Step 5: Providing and managing school meals

[0202] Students receive instructions on how to collect their school lunches via their terminal.

[0203] Learners will collect their meals at designated collection points.

[0204] The server monitors the receipt status in real time and issues additional instructions as needed.

[0205] Input: Lunch information notification from the server

[0206] Output: New data generated when a learner receives a lunch.

[0207] Specific actions

[0208] The server "predicts that a large number of students will eat school lunches next Monday, plans to procure additional fresh vegetables and bread based on past data, and orders the necessary ingredients from local retailers."

[0209] The device sends a notification to the learner that "you can pick up your lunch at the school cafeteria at 8:30," and the learner picks up their lunch at the specified time.

[0210] (Application example 1)

[0211] 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."

[0212] Conventional learning support systems have difficulty monitoring students' learning progress in real time and providing individually optimized learning programs. Furthermore, there was a lack of effective methods for predicting demand for school lunches and managing inventory, making it impossible to provide healthy, waste-free school lunches. Furthermore, there was no system that could centrally manage and notify learning programs and school lunch receipt information using devices such as smartphones.

[0213] 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.

[0214] In this invention, the server includes means for collecting and analyzing student learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the student's device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches, and means for centrally managing and notifying the learning program and school lunch receipt information via the student's smartphone. This enables improved learning efficiency and the provision of healthy school lunches, while simultaneously reducing the burden on parents and reducing food waste.

[0215] A "generative model" is a model that uses machine learning algorithms to learn patterns from large datasets and generate new data.

[0216] "Learning progress data" refers to data such as the results and history of students' educational activities, test results, and assignment submission status.

[0217] "Study Program" means customized learning materials, assignments, and lesson plans to support and facilitate student learning.

[0218] "Means of collecting and analyzing in real time" refers to technologies and systems for instantly obtaining student learning progress data via a network and analyzing that data.

[0219] A "means for generating a customized learning program" is an algorithm or system for generating an optimal learning plan based on the learning progress data and characteristics of each individual student.

[0220] A "terminal" is a device that allows a user to access the system via the Internet, such as a smartphone, tablet, or PC.

[0221] "Demand forecast for ingredients" refers to predicting the amount of ingredients needed for a specific period in the future.

[0222] "Inventory management" is the act or system of understanding and appropriately managing the stock status of ingredients and other items.

[0223] A "procurement plan" is a plan that determines what items to procure, when, and in what quantities in order to meet future demand.

[0224] "Local Restaurants and Retailers" means food and beverage businesses and retailers located within the Service Area.

[0225] "Means of notification" refers to technologies and systems for informing users of information via smartphones or other devices.

[0226] This invention is a system that collects and analyzes students' learning progress data in real time, provides customized learning programs, and also provides free healthy school lunches in cooperation with local restaurants and retailers. This system aims to make students' learning more efficient and reduce the burden on parents.

[0227] First, the server uses the generative model to collect and analyze students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database and analyzed by the generative model.

[0228] The server then uses the generative model to generate a customized learning program based on the analysis results. The generated learning program is optimized for each student's learning progress and areas of weakness, and includes specific problem sets and learning materials. This program is then sent to the student's device and displayed there.

[0229] In addition to supporting learning, the server uses generative models to forecast food demand and optimize inventory management, creating food procurement plans. It predicts future food demand based on past school lunch data and local consumption data, and places orders with local restaurants and retailers based on that data.

[0230] Local restaurants and retailers prepare ingredients according to the procurement plan sent from the server and deliver them to the school or students' homes at the designated date and time. Students receive instructions on how to collect their school lunches via their smartphones and pick them up at the designated pickup location.

[0231] This series of processes is carried out using the following hardware and software.

[0232] Hardware: Smartphones (iOS / Android), tablets, PCs, servers

[0233] Software: Python, Flask (backend), React Native (frontend), generative AI model (OpenAI GPT), database (e.g., PostgreSQL)

[0234] As a specific example of use, if a student has many weak points on a math test, this data is sent to the server and analyzed. For example, a prompt such as, "This student's learning progress data is as follows. Since his math test scores are poor, please generate the most appropriate additional learning materials and review questions" is input into the generative model. The server then provides the generated learning program to the student. The student can access the program through their device and study efficiently.

[0235] Regarding school lunches, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their smartphones that they can pick up their school lunch at the school cafeteria at 8:30, allowing them to pick up their lunch free of charge at the specified location and time.

[0236] This system will improve students' learning efficiency, enable the provision of healthy school lunches, reduce the burden on parents, and reduce food waste.

[0237] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0238] Step 1:

[0239] The server collects and analyzes students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database. The input is learning progress data, and the output is the student's learning data stored in the database.

[0240] Step 2:

[0241] The server uses the generative model to analyze the learning progress data stored in the database. The server inputs the prompts and learning progress data into the generative model and obtains the analysis results. Specifically, the generative model identifies the student's weaknesses and suggests optimal additional learning materials and review questions. The inputs are the learning progress data and prompts, and the output is the analysis results.

[0242] Step 3:

[0243] The server uses the generative model to generate a customized learning program based on the analysis results. Specifically, the generative model generates an optimal learning program based on the analysis results, and the program is configured to match the student's learning goals. The input is the analysis results, and the output is a customized learning program.

[0244] Step 4:

[0245] The server provides the generated learning program to the student's terminal. Specifically, the server transmits the generated learning program to the student's terminal, and the learning program is displayed on the terminal. The input is the customized learning program, and the output is the learning program displayed on the student's terminal.

[0246] Step 5:

[0247] The server uses a generative model to optimize food ingredient demand forecasting and inventory management. The server inputs past school lunch data and local consumption data, and the generative model predicts future food ingredient demand. The inputs are past school lunch data and local consumption data, and the output is the predicted food ingredient demand.

[0248] Step 6:

[0249] The server creates a procurement plan based on the predicted food demand. Specifically, the server uses a generative model to generate an optimal procurement plan and orders ingredients from local restaurants and retailers. The input is the predicted food demand, and the output is the procurement plan and ordering information.

[0250] Step 7:

[0251] Based on the procurement plan, the server works with local restaurants and retailers to procure ingredients and provide meals. The stores prepare ingredients according to the procurement plan sent from the server and deliver them on the specified date and time. The input is the procurement plan, and the output is the delivered ingredients.

[0252] Step 8:

[0253] The user receives the school lunch pickup instructions via their smartphone and picks up the lunch at the designated pickup location. The student's smartphone receives the pickup information sent from the server and is notified to the device. The input is the pickup instructions from the server, and the output is the pickup instructions displayed on the student's smartphone.

[0254] Through the above processing steps, the system not only efficiently manages students' learning progress and provides individually optimized learning programs, but also provides healthy school lunches, reducing the burden on parents and food waste.

[0255] 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.

[0256] The system of this invention uses a generative model and an emotion engine to collect and analyze students' learning progress data and emotion data in real time to provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, and aims to reduce the burden on parents and food waste by providing healthy school lunches to students in collaboration with local restaurants and retailers.

[0257] Educational support implementation form

[0258] Data collection

[0259] The server collects students' test results, assignment submission status, learning history, and emotional data collected through the emotion engine in real time and stores them in a database. Students use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data and emotional data.

[0260] Create a customized learning program

[0261] Using the generative model and emotion engine, the server analyzes the learning progress data and emotion data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends it to the device. Emotional data is also taken into account, so for example, if a student feels stressed while studying, relaxing content will be provided.

[0262] Specific examples

[0263] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. At the same time, if the emotion engine detects that the student is feeling stressed, it will also provide relaxation content and advice. The student can then use their device to access the customized learning program and study more efficiently.

[0264] Meal support implementation form

[0265] Demand forecasting and inventory management

[0266] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[0267] Procurement and Delivery

[0268] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[0269] Specific examples

[0270] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[0271] Embodiment of Emotion Engine

[0272] Collecting and analyzing emotional data

[0273] The emotion engine recognizes emotions from students' facial expressions and voice in real time and sends this emotional data to the server, which stores it in a database and analyzes it in conjunction with learning progress data.

[0274] Specific examples

[0275] For example, if a student's facial expressions are analyzed through the camera while they are studying, and the emotion engine detects signs of fatigue or stress, this information is sent to the server, which can use this data to adjust the study program and add content or exercises that help the student relax.

[0276] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[0277] The processing flow will be explained below.

[0278] Educational Support Program Processing Steps

[0279] Step 1: Collect data

[0280] Device: When students complete online tests or assignments, the results and progress data are recorded and sent to the server. The device also collects emotional data from students' facial expressions and voices via the device's camera and microphone.

[0281] Server: Stores the received learning progress data and emotion data in a database.

[0282] Specific actions

[0283] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[0284] The device captures the student's facial expressions, collects emotional data such as stress and concentration, and sends it to a server.

[0285] The server stores this data in a database for analysis.

[0286] Step 2: Analyzing learning progress and sentiment data

[0287] Server: Provides the learning progress data and emotion data stored in the database to the generative model and emotion engine for analysis.

[0288] Device: Display information on a dashboard so users can see students' learning progress and emotional state in real time.

[0289] Specific actions

[0290] The server inputs students' test scores, assignment submission status, and emotional data into the generative model and emotion engine, and analyzes the current situation and evaluates their level of understanding and emotional state.

[0291] The device displays feedback on learning progress and emotional state, which can be checked by the user (students or parents).

[0292] Step 3: Create a customized learning program

[0293] Server: Uses generative models and emotion engines to create learning programs optimized for each student and send them to the device.

[0294] Device: Displays received learning programs and allows students to access them.

[0295] Specific actions

[0296] Based on the generative model and emotional data, the server selects teaching materials and exercises with individually tailored content, and generates a customized learning program.

[0297] The device will display this learning program so students can access it and begin learning.

[0298] Step 4: Tracking and feedback

[0299] Device: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress is reached. It also simultaneously records the student's emotional state through an emotion engine.

[0300] Server: Analyzes progress and emotion data and updates the learning program as needed.

[0301] Specific actions

[0302] When students complete online exercises on their devices, the results are automatically sent to the server.

[0303] The device also records the student's emotional state and transmits it to the server.

[0304] The server analyzes this data and adjusts the learning program accordingly based on progress, level of understanding, and emotional state.

[0305] Meal Assistance Program Processing Steps

[0306] Step 1: Demand forecast

[0307] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[0308] Specific actions

[0309] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[0310] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[0311] Step 2: Plan your food procurement

[0312] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[0313] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[0314] Specific actions

[0315] The server calculates how much of each ingredient is needed based on the predicted demand.

[0316] The server automatically sends ordering information to local retailers and restaurants.

[0317] Step 3: Ingredient delivery and inventory management

[0318] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[0319] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[0320] Specific actions

[0321] The server receives order confirmation from the store and plans when to deliver the ingredients.

[0322] The store terminal sends an order confirmation and delivery completion notification to the server.

[0323] Step 4: Meal delivery and feedback

[0324] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[0325] Server: Analyzes the received data and reflects it in the next demand forecast.

[0326] Specific actions

[0327] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[0328] The server analyzes this data and further optimizes the food supply plan.

[0329] Through these steps, the system provides efficient and effective support in both education and feeding.

[0330] Example 2

[0331] 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."

[0332] Conventional educational support systems and school lunch management systems lack the functionality to monitor students' learning progress and emotional state in real time and provide customized learning programs and meals based on that information. This has resulted in issues such as ineffective learning support and meal provision tailored to the needs of each student, reduced learning efficiency, and increased childcare burdens. Furthermore, systems lack the ability to adjust learning programs using emotional data or optimize food procurement based on local consumption patterns.

[0333] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0334] In this invention, the server includes: means for collecting and analyzing students' learning progress data and emotional data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model and an emotion engine; means for providing the generated learning program to the student's device; means for creating a procurement plan for optimizing ingredient demand forecasting and inventory management using the generative model; means for procuring ingredients in cooperation with local stores based on the generated procurement plan and providing school lunches; means for collecting and analyzing emotional data from students' facial expressions and voices using the emotion engine; and means for appropriately adjusting the learning program based on the collected emotional data. This makes it possible to provide an optimal learning program and healthy school lunches based on each student's learning progress and emotional state.

[0335] A "generative model" is a model designed based on artificial intelligence, and is a technology that learns patterns from large amounts of data and generates new data and content.

[0336] The "emotion engine" is a system that recognizes emotions in real time from students' facial expressions, voices, etc., and generates or analyzes data based on that.

[0337] "Study progress data" is a general term for data that indicates a student's learning progress, such as test results, assignment submission status, and learning history.

[0338] A "customized learning program" refers to learning plans and materials that are individually designed based on each student's learning progress and emotional data.

[0339] "Device" refers to an electronic device (e.g., tablet or PC) used by a student, on which a learning application runs.

[0340] "Food demand forecasting" is the process of predicting the amount of food ingredients that will be needed in the future based on past consumption data and regional consumption patterns.

[0341] "Inventory management" is the process of monitoring and adjusting inventory to ensure needed materials and goods are available at the right time.

[0342] "Procurement plan" refers to a schedule or action plan for appropriately procuring necessary supplies and ingredients based on predicted demand.

[0343] "Local stores" refers to organizations or individual businesses that provide or sell food ingredients, such as restaurants and retail stores located within the local area.

[0344] "Learning program adjustment" is the process of appropriately modifying and optimizing an existing learning program based on a student's latest learning progress and emotional state.

[0345] The system of this invention utilizes generative models and emotion engines to collect and analyze students' learning progress and emotion data in real time, providing individually optimized learning programs. It also has the function of optimizing food demand forecasting and inventory management, and collaborating with local stores to provide healthy school lunches to students.

[0346] Specifically, the server system is configured using the following hardware and software:

[0347] Hardware: Database server, application server, camera, microphone

[0348] Software: generative AI models, emotion engines, learning applications

[0349] Educational support implementation form

[0350] In educational support, the program is executed in the following steps.

[0351] 1. Data Collection

[0352] Devices send learning data: Students' devices (e.g., tablets or PCs) collect learning data such as test results, assignment submission status, and learning history, and send this data to the server.

[0353] The server receives emotion data: The server receives emotion data from students' facial expressions and voices collected via the emotion engine in real time and stores it in a database.

[0354] The server stores the data: The server stores the received learning data and emotion data in a database, and keeps the information up to date.

[0355] 2. Creating a customized learning program

[0356] The server analyzes the data: Using a generative AI model and emotion engine, the learning progress data and emotion data stored in the database are analyzed to understand the individual needs of students.

[0357] The server generates a learning program: Based on the analysis results, a generative AI model is used to generate a learning program optimized for each student.

[0358] The terminal receives the learning program: The generated learning program is distributed to the student's terminal, and the student can use it to advance their studies.

[0359] Specific examples

[0360] If a student has difficulty with many questions on a math test, the server analyzes the data and generates a customized learning program that includes additional practice problems and explanatory videos. At the same time, if the emotion engine detects that the student is feeling stressed, it also provides relaxing content (e.g., simple meditation videos). The student can access the new learning program through their device and study more efficiently.

[0361] "Based on students' math test results, generate additional learning materials to strengthen their weak areas. Also, suggest relaxing content based on emotional data."

[0362] Meal support implementation form

[0363] In meal assistance, the program is executed in the following steps.

[0364] 1. Demand forecasting and inventory management

[0365] Server collects historical data: The server collects historical school lunch data and local consumption data from a database.

[0366] Server predicts demand: Using a generative AI model, the server predicts future demand for ingredients. Based on the prediction results, the server determines the amount of ingredients needed.

[0367] 2. Procurement and Delivery

[0368] The server creates an ordering plan: The server creates a procurement plan for ingredients based on the predicted demand data.

[0369] The server places an order with the local store: Based on the created procurement plan, the server places an order with the local store for the necessary ingredients.

[0370] The device will notify you of the pickup instructions: The student's device will receive a pickup instruction for the school lunch.

[0371] Specific examples

[0372] If the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan additional orders for fresh vegetables and bread, and order the necessary ingredients from local stores. Students will receive a notification via their device that they can pick up their school lunch at 8:30 a.m. at the school cafeteria, allowing them to receive it free of charge.

[0373] "Predict student lunch demand for the coming week and generate a food procurement plan based on that. Consider past consumption data and current inventory to create a plan for optimal sourcing of fresh ingredients."

[0374] Embodiment of Emotion Engine

[0375] The emotion engine functions as follows:

[0376] 1. Collecting and analyzing emotional data

[0377] The device records facial expressions and voice: The student's device uses a camera and microphone to capture emotional data from facial expressions and voice.

[0378] The server receives and stores the emotion data: The acquired emotion data is sent to the server and stored in a database.

[0379] The server analyzes the emotional data: The stored emotional data is analyzed in conjunction with learning progress data and reflected in the learning program.

[0380] Specific examples

[0381] If a student feels fatigued or stressed while studying, facial expression data is captured through the device's camera and sent to the server. The server uses this data to adjust the learning program and add relaxing content (e.g., relaxation music or short exercises), thereby improving the student's learning efficiency.

[0382] As described above, this system uses a generative AI model and an emotion engine to provide optimal learning programs based on each student's learning progress and emotional state, as well as healthy school lunches based on local consumption patterns. The system aims to provide efficient and effective services in both educational and meal support, reducing the burden on parents.

[0383] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0384] Educational support processing steps

[0385] Step 1: Data collection

[0386] The device sends the learning data

[0387] Input: Student test results, assignment submission status, learning history.

[0388] Data processing: The device collects this learning data and standardizes the format.

[0389] Output: Send the organized training data to the server.

[0390] Specific operation: Every time a student submits a test or assignment, the device automatically collects data and periodically sends it to the server.

[0391] Step 2: Collect and store emotion data

[0392] The device records facial expressions and voice

[0393] Input: Real-time facial expressions and voice of students.

[0394] Data processing: The emotion engine analyzes these data and extracts the emotional state.

[0395] Output: Send the extracted emotion data to the server.

[0396] How it works: While learning, the device's camera and microphone record the student's facial expressions and voice, and an emotion engine detects signs of stress or fatigue.

[0397] Step 3: Save your data

[0398] The server receives and stores the data

[0399] Input: Training data and emotion data sent from the device.

[0400] Data processing: The server organizes the data and stores it in a database.

[0401] Output: The latest learning progress data and emotion data are stored in the database.

[0402] Specific operation: The server periodically updates the database and maintains the data in real time.

[0403] Step 4: Data analysis

[0404] The server analyzes the data

[0405] Input: Saved learning progress data and emotion data.

[0406] Data processing: Analyze data using generative AI models and emotion engines to understand individual student needs.

[0407] Output: The analytical results that form the basis of the learning program.

[0408] Specific operation: The server periodically scans and analyzes the database.

[0409] Step 5: Generate a learning program

[0410] The server generates the learning program.

[0411] Input: Results of data analysis.

[0412] Data processing: The generative AI model generates a customized learning program based on the analysis results.

[0413] Output: An individually optimized learning program.

[0414] Specific operation: Using the analysis results, additional learning materials are generated for students who need extra help with math, for example.

[0415] Step 6: Delivering the learning program

[0416] The device receives the learning program

[0417] Input: The customized learning program sent from the server.

[0418] Data processing: The learning program received by the terminal is converted into a displayable format.

[0419] Output: The learning program provided to the student.

[0420] Specific operation: When a student logs in, the latest learning program is displayed on the device.

[0421] Meal assistance processing steps

[0422] Step 1: Collect demand forecast data

[0423] The server collects historical data

[0424] Input: Past school lunch data, local consumption data.

[0425] Data processing: Read the necessary data from the database and prepare it for analysis.

[0426] Output: A historical dataset that can be analyzed.

[0427] Specific operation: The server periodically extracts the necessary data from the database and prepares it for analysis.

[0428] Step 2: Demand forecast

[0429] Server predicts demand

[0430] Input: Collected historical data.

[0431] Data processing: Using generative AI models to predict future food demand.

[0432] Output: The amount of ingredients needed.

[0433] Specific operation: Based on the generated forecast data, a list of ingredients needed for the next week is created.

[0434] Step 3: Create a procurement plan

[0435] The server creates an ordering plan

[0436] Input: Forecasted demand data.

[0437] Data processing: A procurement plan is created based on this data.

[0438] Output: A procurement plan including the order quantity and source of each ingredient.

[0439] Specific operation: Create detailed ordering instructions for local stores based on the generative model.

[0440] Step 4: Place an order

[0441] The server places an order with the local store.

[0442] Input: Procurement Plan.

[0443] Data processing: Converting procurement plans into actual order data.

[0444] Output: Purchase order email or system message.

[0445] Specific operation: The server orders ingredients from local stores based on the procurement plan.

[0446] Step 5: Notification of school lunch information

[0447] The device will notify you of the pickup instructions.

[0448] Input: Lunch guide data from the server.

[0449] Data processing: Converting data into a format that is easy for students to understand.

[0450] Output: Pickup instructions displayed on the terminal.

[0451] Specific operation: Notify students' devices of the time and location to pick up their lunch.

[0452] Emotion Engine Processing Steps

[0453] Step 1: Collecting emotion data

[0454] The device records facial expressions and voice

[0455] Input: Real-time facial expressions and voices of students as they learn.

[0456] Data processing: The emotion engine analyzes the emotional state from facial expressions and voice.

[0457] Output: Parsed emotion data.

[0458] Specific operation: The device's camera and microphone continuously monitor the student's condition, and the emotion engine analyzes the data.

[0459] Step 2: Storing emotion data

[0460] The server receives and stores emotion data.

[0461] Input: Emotion data sent from the device.

[0462] Data processing: Organize the data and store it in a database.

[0463] Output: The latest emotion data stored in the database.

[0464] Specific operation: Emotional data is recorded in a database in real time and used for analysis.

[0465] Step 3: Analyze the emotion data

[0466] The server analyzes the emotion data

[0467] Input: Stored emotion data and learning progress data.

[0468] Data processing: Using the emotion engine, emotional data is analyzed in conjunction with training data.

[0469] Output: Analysis results that are reflected in the learning program.

[0470] Specific Actions: Assess how students' emotional states affect their learning and provide feedback to their learning programs.

[0471] Step 4: Adjust your learning program

[0472] The server coordinates the learning program

[0473] Input: Analysis results of emotion data.

[0474] Data processing: Adjust the learning program as needed.

[0475] Output: A tailored learning program.

[0476] Action: If relaxation is needed, add relaxing content to your study program.

[0477] Through the above processing steps, the system can provide optimal learning programs and meal services according to the student's learning progress and emotional state.

[0478] (Application example 2)

[0479] 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."

[0480] Conventional learning support systems have difficulty grasping the emotional state of each student in real time and providing customized content according to that state. Furthermore, effective demand forecasting and inventory management are difficult when it comes to procuring and providing ingredients for school lunches, resulting in food waste. It is necessary to simultaneously provide students with an effective learning environment and healthy eating habits while reducing the burden on parents.

[0481] 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: means for collecting and analyzing students' learning progress data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model; means for providing the generated learning program to the student's device; means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management; means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches; and means for analyzing students' emotional states in real time via smart devices and displaying customized content. This enables an optimized learning environment for each student and efficient school lunch provision based on demand forecasts.

[0482] A "generative model" is an algorithm or statistical model used to generate new information or content from data.

[0483] "Learning progress data" refers to data that indicates a student's learning progress, such as their learning activities and test results.

[0484] "Analysis" is the process of examining specific data or information in detail to understand its meaning and patterns.

[0485] A "customized learning program" is learning materials or plans that are optimized for each individual student based on the student's learning progress data and emotional state.

[0486] "Terminal" refers to an electronic device for processing and displaying digital data, such as a tablet, PC, or smart device.

[0487] "Food demand forecasting" is the process of predicting the amount of food ingredients that will be needed based on future consumption trends.

[0488] "Inventory management" is the process of controlling and optimizing the quantity of goods held for sale or consumption.

[0489] "Procurement Plan" means a plan established for the purchase or acquisition of needed goods or services.

[0490] "Local restaurants and retailers" are establishments that sell food and goods within a specific geographic area.

[0491] "School lunch" refers to meals provided at schools and other facilities.

[0492] A "smart device" is an electronic device that has internet connectivity and advanced computing capabilities.

[0493] "Emotional state" refers to an individual's psychological or emotional state at a particular moment.

[0494] "Customized Content" means content that is tailored to a user's specific needs or preferences.

[0495] The system of this invention uses a generative model and emotion engine to collect and analyze students' learning progress and emotion data in real time to provide customized learning programs. Furthermore, it aims to reduce the burden on parents and food waste by optimizing food demand forecasting and inventory management and providing healthy school lunches to students in collaboration with local restaurants and retailers.

[0496] System Configuration

[0497] Hardware configuration:

[0498] Server: Executes and manages data collection, analysis, and generative models for the entire system.

[0499] Devices: Tablets, PCs, smart devices (smart glasses), etc. used by students to interactively access learning programs.

[0500] Smart devices: Collect students' emotional states in real time and use them for analysis.

[0501] Software configuration:

[0502] Generative model: An algorithm that generates new information or content from data.

[0503] Emotion engine: Software that analyzes students' facial expressions and voices via camera to recognize their emotional state in real time.

[0504] OpenCV (cv2): A library for image processing.

[0505] DeepFace: A library for emotion recognition.

[0506] TensorFlow / Keras: Deep learning frameworks for training models.

[0507] Requests: An HTTP request library for retrieving data from the server.

[0508] Processing Details

[0509] Data collection and analysis:

[0510] The server collects students' learning progress data (test results, assignment submission status, learning history) and emotional data (facial expressions, voice, etc.) in real time and stores them in a database. Using the emotion engine, emotional data collected from smart devices is also sent to the server, ensuring that the latest data is always kept.

[0511] Generate a customized learning program:

[0512] Using the generative model and emotion engine, the server analyzes the learning progress data and emotion data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends it to the device. Emotional data is also taken into account, so for example, if a student feels stressed while studying, relaxing content will be provided.

[0513] Demand forecasting and inventory management:

[0514] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan. It sends ordering information to each store and manages the preparation and delivery of appropriate ingredients.

[0515] Examples:

[0516] For example, when a student wears smart glasses and enters a physical store, the camera captures the student's facial expressions and the emotion engine analyzes the data. The server generates optimized content based on the student's emotional state and learning progress data in real time and displays it on the smart glasses. This allows students to receive content that promotes relaxation and learning on the spot.

[0517] Example prompt sentence:

[0518] "Design a system that performs sentiment analysis and displays customized content based on a student's learning progress. When a student wearing smart glasses enters a store, the camera will capture their facial expressions in real time and analyze their emotions. The system will display the most appropriate content on the screen along with the progress data obtained from the server."

[0519] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0520] Step 1:

[0521] The server collects students' learning progress data (test results, assignment submission status, learning history) and emotional data (facial expressions, voice, etc.) in real time. This involves the student's device capturing data using a camera or microphone and sending the data to the server. The input is the student's learning progress data and emotional data, and the output is processed data that is stored in a database on the server.

[0522] Step 2:

[0523] The server stores the collected data in a database. This database stores learning progress data and emotional data for each student. The input is the data collected in step 1, and the output is updated information for the database.

[0524] Step 3:

[0525] The server analyzes the learning progress data and emotion data stored in the database using the generative model and emotion engine. Based on the analysis, a customized learning program for each student is generated. The input is the data stored in the database, and the output is the generated learning program.

[0526] Step 4:

[0527] The server sends the generated learning program to the student's terminal, which displays the received learning program and allows the student to access it. The input is the generated learning program, and the output is the customized learning content displayed on the terminal.

[0528] Step 5:

[0529] The server collects past school lunch data and local consumption data and uses this to predict food demand. It uses a generative model to predict future food demand and creates a food procurement plan based on this prediction. The input is past school lunch data and local consumption data, and the output is a procurement plan.

[0530] Step 6:

[0531] The server orders the necessary ingredients from local restaurants and retail stores based on the procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the specified delivery schedule. The input is the procurement plan, and the output is the order information and delivery instructions.

[0532] Step 7:

[0533] When a student wearing a smart device enters a physical store, the camera captures the student's facial expression, and the emotion engine analyzes the data in real time. The input is the student's facial expression data, and the output is the analyzed emotion data.

[0534] Step 8:

[0535] The server generates optimized content based on the emotional data and learning progress data analyzed in real time and displays it on the smart device. The input is the emotional data and learning progress data, and the output is customized content displayed on the smart device.

[0536] Step 9:

[0537] Students can view the customized content displayed on their smart devices, and experience learning and relaxation benefits. Here, the input is the content displayed on the smart device, and the output is the student's learning and relaxation benefits.

[0538] The above are the processing steps of this system.

[0539] 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.

[0540] 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.

[0541] 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.

[0542] [Second embodiment]

[0543] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0544] 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.

[0545] 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).

[0546] 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.

[0547] 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.

[0548] 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).

[0549] 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.

[0550] 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.

[0551] 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.

[0552] 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.

[0553] In the smart glasses 214, 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.

[0554] 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."

[0555] The system of this invention uses a generative model to collect and analyze students' learning progress data in real time and provide customized learning programs free of charge or at a low cost. It also uses the generative model to optimize food demand forecasting and inventory management, and works with local restaurants and retailers to provide healthy school lunches to students free of charge, thereby reducing the burden on parents and reducing food waste.

[0556] Educational support implementation form

[0557] Data collection

[0558] The server collects students' test results, assignment submission status, and learning history in real time and stores them in a database. Students use learning applications through their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data.

[0559] Create a customized learning program

[0560] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends the program to the device.

[0561] Specific examples

[0562] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. The student can then use their device to access the customized learning program and study more efficiently.

[0563] Meal support implementation form

[0564] Demand forecasting and inventory management

[0565] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[0566] Procurement and Delivery

[0567] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[0568] Specific examples

[0569] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[0570] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[0571] The processing flow will be explained below.

[0572] Educational Support Program Processing Steps

[0573] Step 1: Collect data

[0574] Device: When students complete online tests or assignments, their results and progress data are recorded and sent to the server.

[0575] Server: Stores the received data in a database.

[0576] Specific actions

[0577] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[0578] The server stores this data in a database for later analysis.

[0579] Step 2: Analyze your learning progress

[0580] Server: Provides student learning progress data stored in a database to the generative model and performs analysis.

[0581] Device: Display progress on a dashboard so users can see student progress in real time.

[0582] Specific actions

[0583] The server inputs students' test scores and assignment submission status into the generative model, and analyzes the current situation and evaluates their level of understanding.

[0584] The device displays feedback on progress and level of understanding, which users (students and parents) can check.

[0585] Step 3: Create a customized learning program

[0586] Server: Uses the generative model to create a learning program optimized for each student and sends that program to the device.

[0587] Device: Displays received learning programs and allows students to access them.

[0588] Specific actions

[0589] Based on the generative model, the server selects teaching materials and exercises to strengthen the student's weak points and generates a customized learning program.

[0590] The generated learning program is sent to the terminal, and the student can access the program and start learning.

[0591] Step 4: Tracking and feedback

[0592] Terminal: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress has been made.

[0593] Server: Analyzes progress data and updates learning programs as needed.

[0594] Specific actions

[0595] When students complete online exercises on their devices, the results are automatically sent to the server.

[0596] The server analyzes this data and adjusts the learning program accordingly based on progress and level of understanding.

[0597] Meal Assistance Program Processing Steps

[0598] Step 1: Demand forecast

[0599] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[0600] Specific actions

[0601] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[0602] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[0603] Step 2: Plan your food procurement

[0604] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[0605] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[0606] Specific actions

[0607] The server calculates how much of each ingredient is needed based on the predicted demand.

[0608] The server automatically sends ordering information to local retailers and restaurants.

[0609] Step 3: Ingredient delivery and inventory management

[0610] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[0611] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[0612] Specific actions

[0613] The server receives order confirmation from the store and plans when to deliver the ingredients.

[0614] The store terminal sends an order confirmation and delivery completion notification to the server.

[0615] Step 4: Meal delivery and feedback

[0616] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[0617] Server: Analyzes the received data and reflects it in the next demand forecast.

[0618] Specific actions

[0619] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[0620] The server analyzes this data and further optimizes the food supply plan.

[0621] Through these steps, the system provides efficient and effective support in both education and feeding.

[0622] Example 1

[0623] 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."

[0624] With conventional learning programs and school lunch delivery systems, it was difficult to customize them to suit each student's learning progress, and food demand forecasting and inventory management were insufficient, which meant that educational effectiveness and meal quality were not fully improved. For this reason, there is a need for a system that provides individually optimized learning programs and efficiently manages ingredients and provides school lunches.

[0625] 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.

[0626] In this invention, the server includes means for collecting and analyzing a learner's learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the learner's information processing device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients and providing meals in cooperation with local restaurants and retailers based on the generated procurement plan, means for providing the learner with access to the customized learning program via the learner's information processing device, and means for providing the learner with meal pickup instructions via the learner's information processing device. This enables the provision of an individually optimized learning program and the efficient and prompt procurement of ingredients and provision of meals.

[0627] A "generative model" is a system that uses machine learning algorithms to learn patterns in data and make predictions or generate new data.

[0628] "Learning progress data" refers to data that indicates the results and progress a learner has achieved through their learning activities, and specifically includes test results, assignment submission status, learning history, etc.

[0629] "Real-time" means that a process or operation occurs immediately or with very little delay.

[0630] A "customized learning program" is a program that provides learning content and materials tailored to the needs and progress of individual learners.

[0631] An "information processing device" is an electronic device that has functions such as collecting, processing, storing, and transmitting data, and specifically includes tablets and personal computers.

[0632] "Demand forecasting" is the process of predicting future demand based on past data and various factors.

[0633] "Inventory management" means understanding the stock status of necessary goods and materials and maintaining and managing them appropriately.

[0634] "Food procurement planning" refers to the process of planning the types and quantities of ingredients needed based on predicted demand and securing them.

[0635] "Food and beverage establishment" means a facility that has a place or equipment for serving food and beverages, and specifically includes restaurants and cafeterias.

[0636] "Retailer" refers to a trader or company that sells goods to the general public.

[0637] "Learner" means a person who participates in an educational program or learning activity.

[0638] "Access" means making a system or data available.

[0639] "Pickup Instructions" means notices or instructions providing information regarding the pickup of goods or services.

[0640] The system of this invention uses a generative model to collect and analyze learner progress data in real time and provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, aiming to provide learners with healthy meals in collaboration with local restaurants and retailers.

[0641] Educational support implementation form

[0642] Data collection

[0643] The server collects learners' test results, assignment submission status, and learning history in real time and stores them in a database. Learners use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. The software used is a learning management system (LMS). This allows the server to always have the latest learning progress data.

[0644] Create a customized learning program

[0645] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates a learning program optimized for each learner and sends that program to the information processing device. The generative AI model used includes, for example, a large-scale GPT-based language model.

[0646] Specific examples

[0647] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to that student. The student can then use their device to access the customized learning program and study efficiently.

[0648] Example prompts to input to a generative AI model:

[0649] "Please create additional learning materials for today based on Learner A's latest learning progress data."

[0650] Meal support implementation form

[0651] Demand forecasting and inventory management

[0652] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, an ingredient procurement plan is created. The generative AI model used includes, for example, machine learning algorithms and statistical models.

[0653] Procurement and Delivery

[0654] Based on the generated procurement plan, the server places orders for the necessary ingredients with local restaurants and retailers. Each restaurant prepares the ingredients according to the order information sent from the server and delivers them according to the specified delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the specified pickup location.

[0655] Specific examples

[0656] For example, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[0657] Example prompts to input to a generative AI model:

[0658] "Please forecast the demand for ingredients needed for school lunches next Monday and create a procurement plan."

[0659] In this way, we will create a system that provides efficient and effective services to learners in both educational and dietary support, reducing the burden on parents while supporting high-quality education and healthy eating habits.

[0660] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0661] Educational support implementation form

[0662] Data collection and storage

[0663] Step 1: Collect training data

[0664] A user (learner) logs in to a learning application using a device (e.g., a tablet or PC).

[0665] The device collects learning data such as the results of tests taken by learners, assignment submission status, and learning history.

[0666] The server issues a log data request and receives the data in real time from the terminal.

[0667] Input: Learner test results, assignment submission status, learning history, etc.

[0668] Output: Training data received in real time

[0669] Step 2: Save your data

[0670] The server stores the received learning data in a database.

[0671] Perform validation to check for data consistency and duplication.

[0672] The server performs backups to ensure data integrity.

[0673] Input: Training data received in real time

[0674] Output: Training data stored in a database

[0675] Creating and delivering customized learning programs

[0676] Step 3: Analyze the data

[0677] The server uses the generative model to analyze the learning progress data stored in the database.

[0678] Apply statistical analysis and machine learning algorithms to identify learner strengths and weaknesses.

[0679] Input: Learning progress data stored in a database

[0680] Output: Analysis results for each learner

[0681] Step 4: Generate a customized learning program

[0682] The server inputs prompts into the generative model to generate a customized learning program.

[0683] The server optimizes and organizes the generated programs for each learner.

[0684] Input: Analysis results for each learner

[0685] Output: A customized learning program

[0686] Step 5: Deliver and execute the learning program

[0687] The server transmits the generated study program to the learner's terminal.

[0688] Learners use their devices to access their customized learning programs and begin their studies.

[0689] The device again transmits the learner's progress to the server.

[0690] Input: Customized Learning Program

[0691] Output: Learning program delivered to the device and new learning progress data

[0692] Specific actions

[0693] The device receives a "fraction calculation problem set" and displays explanatory videos on the learning screen, and the user (learner) works on them.

[0694] The server generates additional learning materials using a prompt such as "Student A's weak point: Please generate additional learning materials for fraction calculations" and sends them to the terminal.

[0695] Meal support implementation form

[0696] Demand forecasting and inventory management

[0697] Step 1: Collect historical data

[0698] The server collects past school lunch data and local consumption data.

[0699] The server stores the collected data in a database.

[0700] Input: Past school lunch data and local consumption data

[0701] Output: Meal data stored in a database

[0702] Step 2: Forecast demand

[0703] The server uses a generative AI model to analyze collected past data and predict future food demand.

[0704] The server determines the amount of ingredients to be procured based on the predicted data.

[0705] Input: Meal data stored in the database

[0706] Output: Demand forecast data for ingredients

[0707] Procurement planning and execution

[0708] Step 3: Create a procurement plan

[0709] The server creates a procurement plan based on the forecast data and generates a list of required ingredients.

[0710] Store procurement plans in a database.

[0711] Input: Demand forecast data for ingredients

[0712] Output: Procurement plan and ingredients list

[0713] Step 4: Order and deliver ingredients

[0714] The server transmits food ordering information to local restaurants and retailers based on the procurement plan.

[0715] Each store prepares ingredients according to the order information from the server and delivers them according to the specified schedule.

[0716] Input: Procurement plan and ingredients list

[0717] Output: Ordering information for local restaurants and retailers

[0718] Meal provision

[0719] Step 5: Providing and managing school meals

[0720] Students receive instructions on how to collect their school lunches via their terminal.

[0721] Learners will collect their meals at designated collection points.

[0722] The server monitors the receipt status in real time and issues additional instructions as needed.

[0723] Input: Lunch information notification from the server

[0724] Output: New data generated when a learner receives a lunch.

[0725] Specific actions

[0726] The server "predicts that a large number of students will eat school lunches next Monday, plans to procure additional fresh vegetables and bread based on past data, and orders the necessary ingredients from local retailers."

[0727] The device sends a notification to the learner that "you can pick up your lunch at the school cafeteria at 8:30," and the learner picks up their lunch at the specified time.

[0728] (Application example 1)

[0729] 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."

[0730] Conventional learning support systems have difficulty monitoring students' learning progress in real time and providing individually optimized learning programs. Furthermore, there was a lack of effective methods for predicting demand for school lunches and managing inventory, making it impossible to provide healthy, waste-free school lunches. Furthermore, there was no system that could centrally manage and notify learning programs and school lunch receipt information using devices such as smartphones.

[0731] 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.

[0732] In this invention, the server includes means for collecting and analyzing student learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the student's device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches, and means for centrally managing and notifying the learning program and school lunch receipt information via the student's smartphone. This enables improved learning efficiency and the provision of healthy school lunches, while simultaneously reducing the burden on parents and reducing food waste.

[0733] A "generative model" is a model that uses machine learning algorithms to learn patterns from large datasets and generate new data.

[0734] "Learning progress data" refers to data such as the results and history of students' educational activities, test results, and assignment submission status.

[0735] "Study Program" means customized learning materials, assignments, and lesson plans to support and facilitate student learning.

[0736] "Means of collecting and analyzing in real time" refers to technologies and systems for instantly obtaining student learning progress data via a network and analyzing that data.

[0737] A "means for generating a customized learning program" is an algorithm or system for generating an optimal learning plan based on the learning progress data and characteristics of each individual student.

[0738] A "terminal" is a device that allows a user to access the system via the Internet, such as a smartphone, tablet, or PC.

[0739] "Demand forecast for ingredients" refers to predicting the amount of ingredients needed for a specific period in the future.

[0740] "Inventory management" is the act or system of understanding and appropriately managing the stock status of ingredients and other items.

[0741] A "procurement plan" is a plan that determines what items to procure, when, and in what quantities in order to meet future demand.

[0742] "Local Restaurants and Retailers" means food and beverage businesses and retailers located within the Service Area.

[0743] "Means of notification" refers to technologies and systems for informing users of information via smartphones or other devices.

[0744] This invention is a system that collects and analyzes students' learning progress data in real time, provides customized learning programs, and also provides free healthy school lunches in cooperation with local restaurants and retailers. This system aims to make students' learning more efficient and reduce the burden on parents.

[0745] First, the server uses the generative model to collect and analyze students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database and analyzed by the generative model.

[0746] The server then uses the generative model to generate a customized learning program based on the analysis results. The generated learning program is optimized for each student's learning progress and areas of weakness, and includes specific problem sets and learning materials. This program is then sent to the student's device and displayed there.

[0747] In addition to supporting learning, the server uses generative models to forecast food demand and optimize inventory management, creating food procurement plans. It predicts future food demand based on past school lunch data and local consumption data, and places orders with local restaurants and retailers based on that data.

[0748] Local restaurants and retailers prepare ingredients according to the procurement plan sent from the server and deliver them to the school or students' homes at the designated date and time. Students receive instructions on how to collect their school lunches via their smartphones and pick them up at the designated pickup location.

[0749] This series of processes is carried out using the following hardware and software.

[0750] Hardware: Smartphones (iOS / Android), tablets, PCs, servers

[0751] Software: Python, Flask (backend), React Native (frontend), generative AI model (OpenAI GPT), database (e.g., PostgreSQL)

[0752] As a specific example of use, if a student has many weak points on a math test, this data is sent to the server and analyzed. For example, a prompt such as, "This student's learning progress data is as follows. Since his math test scores are poor, please generate the most appropriate additional learning materials and review questions" is input into the generative model. The server then provides the generated learning program to the student. The student can access the program through their device and study efficiently.

[0753] Regarding school lunches, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their smartphones that they can pick up their school lunch at the school cafeteria at 8:30, allowing them to pick up their lunch free of charge at the specified location and time.

[0754] This system will improve students' learning efficiency, enable the provision of healthy school lunches, reduce the burden on parents, and reduce food waste.

[0755] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0756] Step 1:

[0757] The server collects and analyzes students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database. The input is learning progress data, and the output is the student's learning data stored in the database.

[0758] Step 2:

[0759] The server uses the generative model to analyze the learning progress data stored in the database. The server inputs the prompts and learning progress data into the generative model and obtains the analysis results. Specifically, the generative model identifies the student's weaknesses and suggests optimal additional learning materials and review questions. The inputs are the learning progress data and prompts, and the output is the analysis results.

[0760] Step 3:

[0761] The server uses the generative model to generate a customized learning program based on the analysis results. Specifically, the generative model generates an optimal learning program based on the analysis results, and the program is configured to match the student's learning goals. The input is the analysis results, and the output is a customized learning program.

[0762] Step 4:

[0763] The server provides the generated learning program to the student's terminal. Specifically, the server transmits the generated learning program to the student's terminal, and the learning program is displayed on the terminal. The input is the customized learning program, and the output is the learning program displayed on the student's terminal.

[0764] Step 5:

[0765] The server uses a generative model to optimize food ingredient demand forecasting and inventory management. The server inputs past school lunch data and local consumption data, and the generative model predicts future food ingredient demand. The inputs are past school lunch data and local consumption data, and the output is the predicted food ingredient demand.

[0766] Step 6:

[0767] The server creates a procurement plan based on the predicted food demand. Specifically, the server uses a generative model to generate an optimal procurement plan and orders ingredients from local restaurants and retailers. The input is the predicted food demand, and the output is the procurement plan and ordering information.

[0768] Step 7:

[0769] Based on the procurement plan, the server works with local restaurants and retailers to procure ingredients and provide meals. The stores prepare ingredients according to the procurement plan sent from the server and deliver them on the specified date and time. The input is the procurement plan, and the output is the delivered ingredients.

[0770] Step 8:

[0771] The user receives the school lunch pickup instructions via their smartphone and picks up the lunch at the designated pickup location. The student's smartphone receives the pickup information sent from the server and is notified to the device. The input is the pickup instructions from the server, and the output is the pickup instructions displayed on the student's smartphone.

[0772] Through the above processing steps, the system not only efficiently manages students' learning progress and provides individually optimized learning programs, but also provides healthy school lunches, reducing the burden on parents and food waste.

[0773] 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.

[0774] The system of this invention uses a generative model and an emotion engine to collect and analyze students' learning progress data and emotion data in real time to provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, and aims to reduce the burden on parents and food waste by providing healthy school lunches to students in collaboration with local restaurants and retailers.

[0775] Educational support implementation form

[0776] Data collection

[0777] The server collects students' test results, assignment submission status, learning history, and emotional data collected through the emotion engine in real time and stores them in a database. Students use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data and emotional data.

[0778] Create a customized learning program

[0779] Using the generative model and emotion engine, the server analyzes the learning progress data and emotion data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends it to the device. Emotional data is also taken into account, so for example, if a student feels stressed while studying, relaxing content will be provided.

[0780] Specific examples

[0781] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. At the same time, if the emotion engine detects that the student is feeling stressed, it will also provide relaxation content and advice. The student can then use their device to access the customized learning program and study more efficiently.

[0782] Meal support implementation form

[0783] Demand forecasting and inventory management

[0784] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[0785] Procurement and Delivery

[0786] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[0787] Specific examples

[0788] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[0789] Embodiment of Emotion Engine

[0790] Collecting and analyzing emotional data

[0791] The emotion engine recognizes emotions from students' facial expressions and voice in real time and sends this emotional data to the server, which stores it in a database and analyzes it in conjunction with learning progress data.

[0792] Specific examples

[0793] For example, if a student's facial expressions are analyzed through the camera while they are studying, and the emotion engine detects signs of fatigue or stress, this information is sent to the server, which can use this data to adjust the study program and add content or exercises that help the student relax.

[0794] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[0795] The processing flow will be explained below.

[0796] Educational Support Program Processing Steps

[0797] Step 1: Collect data

[0798] Device: When students complete online tests or assignments, the results and progress data are recorded and sent to the server. The device also collects emotional data from students' facial expressions and voices via the device's camera and microphone.

[0799] Server: Stores the received learning progress data and emotion data in a database.

[0800] Specific actions

[0801] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[0802] The device captures the student's facial expressions, collects emotional data such as stress and concentration, and sends it to a server.

[0803] The server stores this data in a database for analysis.

[0804] Step 2: Analyzing learning progress and sentiment data

[0805] Server: Provides the learning progress data and emotion data stored in the database to the generative model and emotion engine for analysis.

[0806] Device: Display information on a dashboard so users can see students' learning progress and emotional state in real time.

[0807] Specific actions

[0808] The server inputs students' test scores, assignment submission status, and emotional data into the generative model and emotion engine, and analyzes the current situation and evaluates their level of understanding and emotional state.

[0809] The device displays feedback on learning progress and emotional state, which can be checked by the user (students or parents).

[0810] Step 3: Create a customized learning program

[0811] Server: Uses generative models and emotion engines to create learning programs optimized for each student and send them to the device.

[0812] Device: Displays received learning programs and allows students to access them.

[0813] Specific actions

[0814] Based on the generative model and emotional data, the server selects teaching materials and exercises with individually tailored content, and generates a customized learning program.

[0815] The device will display this learning program so students can access it and begin learning.

[0816] Step 4: Tracking and feedback

[0817] Device: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress is reached. It also simultaneously records the student's emotional state through an emotion engine.

[0818] Server: Analyzes progress and emotion data and updates the learning program as needed.

[0819] Specific actions

[0820] When students complete online exercises on their devices, the results are automatically sent to the server.

[0821] The device also records the student's emotional state and transmits it to the server.

[0822] The server analyzes this data and adjusts the learning program accordingly based on progress, level of understanding, and emotional state.

[0823] Meal Assistance Program Processing Steps

[0824] Step 1: Demand forecast

[0825] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[0826] Specific actions

[0827] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[0828] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[0829] Step 2: Plan your food procurement

[0830] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[0831] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[0832] Specific actions

[0833] The server calculates how much of each ingredient is needed based on the predicted demand.

[0834] The server automatically sends ordering information to local retailers and restaurants.

[0835] Step 3: Ingredient delivery and inventory management

[0836] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[0837] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[0838] Specific actions

[0839] The server receives order confirmation from the store and plans when to deliver the ingredients.

[0840] The store terminal sends an order confirmation and delivery completion notification to the server.

[0841] Step 4: Meal delivery and feedback

[0842] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[0843] Server: Analyzes the received data and reflects it in the next demand forecast.

[0844] Specific actions

[0845] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[0846] The server analyzes this data and further optimizes the food supply plan.

[0847] Through these steps, the system provides efficient and effective support in both education and feeding.

[0848] Example 2

[0849] 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."

[0850] Conventional educational support systems and school lunch management systems lack the functionality to monitor students' learning progress and emotional state in real time and provide customized learning programs and meals based on that information. This has resulted in issues such as ineffective learning support and meal provision tailored to the needs of each student, reduced learning efficiency, and increased childcare burdens. Furthermore, systems lack the ability to adjust learning programs using emotional data or optimize food procurement based on local consumption patterns.

[0851] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0852] In this invention, the server includes: means for collecting and analyzing students' learning progress data and emotional data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model and an emotion engine; means for providing the generated learning program to the student's device; means for creating a procurement plan for optimizing ingredient demand forecasting and inventory management using the generative model; means for procuring ingredients in cooperation with local stores based on the generated procurement plan and providing school lunches; means for collecting and analyzing emotional data from students' facial expressions and voices using the emotion engine; and means for appropriately adjusting the learning program based on the collected emotional data. This makes it possible to provide an optimal learning program and healthy school lunches based on each student's learning progress and emotional state.

[0853] A "generative model" is a model designed based on artificial intelligence, and is a technology that learns patterns from large amounts of data and generates new data and content.

[0854] The "emotion engine" is a system that recognizes emotions in real time from students' facial expressions, voices, etc., and generates or analyzes data based on that.

[0855] "Study progress data" is a general term for data that indicates a student's learning progress, such as test results, assignment submission status, and learning history.

[0856] A "customized learning program" refers to learning plans and materials that are individually designed based on each student's learning progress and emotional data.

[0857] "Device" refers to an electronic device (e.g., tablet or PC) used by a student, on which a learning application runs.

[0858] "Food demand forecasting" is the process of predicting the amount of food ingredients that will be needed in the future based on past consumption data and regional consumption patterns.

[0859] "Inventory management" is the process of monitoring and adjusting inventory to ensure needed materials and goods are available at the right time.

[0860] "Procurement plan" refers to a schedule or action plan for appropriately procuring necessary supplies and ingredients based on predicted demand.

[0861] "Local stores" refers to organizations or individual businesses that provide or sell food ingredients, such as restaurants and retail stores located within the local area.

[0862] "Learning program adjustment" is the process of appropriately modifying and optimizing an existing learning program based on a student's latest learning progress and emotional state.

[0863] The system of this invention utilizes generative models and emotion engines to collect and analyze students' learning progress and emotion data in real time, providing individually optimized learning programs. It also has the function of optimizing food demand forecasting and inventory management, and collaborating with local stores to provide healthy school lunches to students.

[0864] Specifically, the server system is configured using the following hardware and software:

[0865] Hardware: Database server, application server, camera, microphone

[0866] Software: generative AI models, emotion engines, learning applications

[0867] Educational support implementation form

[0868] In educational support, the program is executed in the following steps.

[0869] 1. Data Collection

[0870] Devices send learning data: Students' devices (e.g., tablets or PCs) collect learning data such as test results, assignment submission status, and learning history, and send this data to the server.

[0871] The server receives emotion data: The server receives emotion data from students' facial expressions and voices collected via the emotion engine in real time and stores it in a database.

[0872] The server stores the data: The server stores the received learning data and emotion data in a database, and keeps the information up to date.

[0873] 2. Creating a customized learning program

[0874] The server analyzes the data: Using a generative AI model and emotion engine, the learning progress data and emotion data stored in the database are analyzed to understand the individual needs of students.

[0875] The server generates a learning program: Based on the analysis results, a generative AI model is used to generate a learning program optimized for each student.

[0876] The terminal receives the learning program: The generated learning program is distributed to the student's terminal, and the student can use it to advance their studies.

[0877] Specific examples

[0878] If a student has difficulty with many questions on a math test, the server analyzes the data and generates a customized learning program that includes additional practice problems and explanatory videos. At the same time, if the emotion engine detects that the student is feeling stressed, it also provides relaxing content (e.g., simple meditation videos). The student can access the new learning program through their device and study more efficiently.

[0879] "Based on students' math test results, generate additional learning materials to strengthen their weak areas. Also, suggest relaxing content based on emotional data."

[0880] Meal support implementation form

[0881] In meal assistance, the program is executed in the following steps.

[0882] 1. Demand forecasting and inventory management

[0883] Server collects historical data: The server collects historical school lunch data and local consumption data from a database.

[0884] Server predicts demand: Using a generative AI model, the server predicts future demand for ingredients. Based on the prediction results, the server determines the amount of ingredients needed.

[0885] 2. Procurement and Delivery

[0886] The server creates an ordering plan: The server creates a procurement plan for ingredients based on the predicted demand data.

[0887] The server places an order with the local store: Based on the created procurement plan, the server places an order with the local store for the necessary ingredients.

[0888] The device will notify you of the pickup instructions: The student's device will receive a pickup instruction for the school lunch.

[0889] Specific examples

[0890] If the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan additional orders for fresh vegetables and bread, and order the necessary ingredients from local stores. Students will receive a notification via their device that they can pick up their school lunch at 8:30 a.m. at the school cafeteria, allowing them to receive it free of charge.

[0891] "Predict student lunch demand for the coming week and generate a food procurement plan based on that. Consider past consumption data and current inventory to create a plan for optimal sourcing of fresh ingredients."

[0892] Embodiment of Emotion Engine

[0893] The emotion engine functions as follows:

[0894] 1. Collecting and analyzing emotional data

[0895] The device records facial expressions and voice: The student's device uses a camera and microphone to capture emotional data from facial expressions and voice.

[0896] The server receives and stores the emotion data: The acquired emotion data is sent to the server and stored in a database.

[0897] The server analyzes the emotional data: The stored emotional data is analyzed in conjunction with learning progress data and reflected in the learning program.

[0898] Specific examples

[0899] If a student feels fatigued or stressed while studying, facial expression data is captured through the device's camera and sent to the server. The server uses this data to adjust the learning program and add relaxing content (e.g., relaxation music or short exercises), thereby improving the student's learning efficiency.

[0900] As described above, this system uses a generative AI model and an emotion engine to provide optimal learning programs based on each student's learning progress and emotional state, as well as healthy school lunches based on local consumption patterns. The system aims to provide efficient and effective services in both educational and meal support, reducing the burden on parents.

[0901] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0902] Educational support processing steps

[0903] Step 1: Data collection

[0904] The device sends the learning data

[0905] Input: Student test results, assignment submission status, learning history.

[0906] Data processing: The device collects this learning data and standardizes the format.

[0907] Output: Send the organized training data to the server.

[0908] Specific operation: Every time a student submits a test or assignment, the device automatically collects data and periodically sends it to the server.

[0909] Step 2: Collect and store emotion data

[0910] The device records facial expressions and voice

[0911] Input: Real-time facial expressions and voice of students.

[0912] Data processing: The emotion engine analyzes these data and extracts the emotional state.

[0913] Output: Send the extracted emotion data to the server.

[0914] How it works: While learning, the device's camera and microphone record the student's facial expressions and voice, and an emotion engine detects signs of stress or fatigue.

[0915] Step 3: Save your data

[0916] The server receives and stores the data

[0917] Input: Training data and emotion data sent from the device.

[0918] Data processing: The server organizes the data and stores it in a database.

[0919] Output: The latest learning progress data and emotion data are stored in the database.

[0920] Specific operation: The server periodically updates the database and maintains the data in real time.

[0921] Step 4: Data analysis

[0922] The server analyzes the data

[0923] Input: Saved learning progress data and emotion data.

[0924] Data processing: Analyze data using generative AI models and emotion engines to understand individual student needs.

[0925] Output: The analytical results that form the basis of the learning program.

[0926] Specific operation: The server periodically scans and analyzes the database.

[0927] Step 5: Generate a learning program

[0928] The server generates the learning program.

[0929] Input: Results of data analysis.

[0930] Data processing: The generative AI model generates a customized learning program based on the analysis results.

[0931] Output: An individually optimized learning program.

[0932] Specific operation: Using the analysis results, additional learning materials are generated for students who need extra help with math, for example.

[0933] Step 6: Delivering the learning program

[0934] The device receives the learning program

[0935] Input: The customized learning program sent from the server.

[0936] Data processing: The learning program received by the terminal is converted into a displayable format.

[0937] Output: The learning program provided to the student.

[0938] Specific operation: When a student logs in, the latest learning program is displayed on the device.

[0939] Meal assistance processing steps

[0940] Step 1: Collect demand forecast data

[0941] The server collects historical data

[0942] Input: Past school lunch data, local consumption data.

[0943] Data processing: Read the necessary data from the database and prepare it for analysis.

[0944] Output: A historical dataset that can be analyzed.

[0945] Specific operation: The server periodically extracts the necessary data from the database and prepares it for analysis.

[0946] Step 2: Demand forecast

[0947] Server predicts demand

[0948] Input: Collected historical data.

[0949] Data processing: Using generative AI models to predict future food demand.

[0950] Output: The amount of ingredients needed.

[0951] Specific operation: Based on the generated forecast data, a list of ingredients needed for the next week is created.

[0952] Step 3: Create a procurement plan

[0953] The server creates an ordering plan

[0954] Input: Forecasted demand data.

[0955] Data processing: A procurement plan is created based on this data.

[0956] Output: A procurement plan including the order quantity and source of each ingredient.

[0957] Specific operation: Create detailed ordering instructions for local stores based on the generative model.

[0958] Step 4: Place an order

[0959] The server places an order with the local store.

[0960] Input: Procurement Plan.

[0961] Data processing: Converting procurement plans into actual order data.

[0962] Output: Purchase order email or system message.

[0963] Specific operation: The server orders ingredients from local stores based on the procurement plan.

[0964] Step 5: Notification of school lunch information

[0965] The device will notify you of the pickup instructions.

[0966] Input: Lunch guide data from the server.

[0967] Data processing: Converting data into a format that is easy for students to understand.

[0968] Output: Pickup instructions displayed on the terminal.

[0969] Specific operation: Notify students' devices of the time and location to pick up their lunch.

[0970] Emotion Engine Processing Steps

[0971] Step 1: Collecting emotion data

[0972] The device records facial expressions and voice

[0973] Input: Real-time facial expressions and voices of students as they learn.

[0974] Data processing: The emotion engine analyzes the emotional state from facial expressions and voice.

[0975] Output: Parsed emotion data.

[0976] Specific operation: The device's camera and microphone continuously monitor the student's condition, and the emotion engine analyzes the data.

[0977] Step 2: Storing emotion data

[0978] The server receives and stores emotion data.

[0979] Input: Emotion data sent from the device.

[0980] Data processing: Organize the data and store it in a database.

[0981] Output: The latest emotion data stored in the database.

[0982] Specific operation: Emotional data is recorded in a database in real time and used for analysis.

[0983] Step 3: Analyze the emotion data

[0984] The server analyzes the emotion data

[0985] Input: Stored emotion data and learning progress data.

[0986] Data processing: Using the emotion engine, emotional data is analyzed in conjunction with training data.

[0987] Output: Analysis results that are reflected in the learning program.

[0988] Specific Actions: Assess how students' emotional states affect their learning and provide feedback to their learning programs.

[0989] Step 4: Adjust your learning program

[0990] The server coordinates the learning program

[0991] Input: Analysis results of emotion data.

[0992] Data processing: Adjust the learning program as needed.

[0993] Output: A tailored learning program.

[0994] Action: If relaxation is needed, add relaxing content to your study program.

[0995] Through the above processing steps, the system can provide optimal learning programs and meal services according to the student's learning progress and emotional state.

[0996] (Application example 2)

[0997] 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."

[0998] Conventional learning support systems have difficulty grasping the emotional state of each student in real time and providing customized content according to that state. Furthermore, effective demand forecasting and inventory management are difficult when it comes to procuring and providing ingredients for school lunches, resulting in food waste. It is necessary to simultaneously provide students with an effective learning environment and healthy eating habits while reducing the burden on parents.

[0999] 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: means for collecting and analyzing students' learning progress data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model; means for providing the generated learning program to the student's device; means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management; means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches; and means for analyzing students' emotional states in real time via smart devices and displaying customized content. This enables an optimized learning environment for each student and efficient school lunch provision based on demand forecasts.

[1000] A "generative model" is an algorithm or statistical model used to generate new information or content from data.

[1001] "Learning progress data" refers to data that indicates a student's learning progress, such as their learning activities and test results.

[1002] "Analysis" is the process of examining specific data or information in detail to understand its meaning and patterns.

[1003] A "customized learning program" is learning materials or plans that are optimized for each individual student based on the student's learning progress data and emotional state.

[1004] "Terminal" refers to an electronic device for processing and displaying digital data, such as a tablet, PC, or smart device.

[1005] "Food demand forecasting" is the process of predicting the amount of food ingredients that will be needed based on future consumption trends.

[1006] "Inventory management" is the process of controlling and optimizing the quantity of goods held for sale or consumption.

[1007] "Procurement Plan" means a plan established for the purchase or acquisition of needed goods or services.

[1008] "Local restaurants and retailers" are establishments that sell food and goods within a specific geographic area.

[1009] "School lunch" refers to meals provided at schools and other facilities.

[1010] A "smart device" is an electronic device that has internet connectivity and advanced computing capabilities.

[1011] "Emotional state" refers to an individual's psychological or emotional state at a particular moment.

[1012] "Customized Content" means content that is tailored to a user's specific needs or preferences.

[1013] The system of this invention uses a generative model and emotion engine to collect and analyze students' learning progress and emotion data in real time to provide customized learning programs. Furthermore, it aims to reduce the burden on parents and food waste by optimizing food demand forecasting and inventory management and providing healthy school lunches to students in collaboration with local restaurants and retailers.

[1014] System Configuration

[1015] Hardware configuration:

[1016] Server: Executes and manages data collection, analysis, and generative models for the entire system.

[1017] Devices: Tablets, PCs, smart devices (smart glasses), etc. used by students to interactively access learning programs.

[1018] Smart devices: Collect students' emotional states in real time and use them for analysis.

[1019] Software configuration:

[1020] Generative model: An algorithm that generates new information or content from data.

[1021] Emotion engine: Software that analyzes students' facial expressions and voices via camera to recognize their emotional state in real time.

[1022] OpenCV (cv2): A library for image processing.

[1023] DeepFace: A library for emotion recognition.

[1024] TensorFlow / Keras: Deep learning frameworks for training models.

[1025] Requests: An HTTP request library for retrieving data from the server.

[1026] Processing Details

[1027] Data collection and analysis:

[1028] The server collects students' learning progress data (test results, assignment submission status, learning history) and emotional data (facial expressions, voice, etc.) in real time and stores them in a database. Using the emotion engine, emotional data collected from smart devices is also sent to the server, ensuring that the latest data is always kept.

[1029] Generate a customized learning program:

[1030] Using the generative model and emotion engine, the server analyzes the learning progress data and emotion data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends it to the device. Emotional data is also taken into account, so for example, if a student feels stressed while studying, relaxing content will be provided.

[1031] Demand forecasting and inventory management:

[1032] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan. It sends ordering information to each store and manages the preparation and delivery of appropriate ingredients.

[1033] Examples:

[1034] For example, when a student wears smart glasses and enters a physical store, the camera captures the student's facial expressions and the emotion engine analyzes the data. The server generates optimized content based on the student's emotional state and learning progress data in real time and displays it on the smart glasses. This allows students to receive content that promotes relaxation and learning on the spot.

[1035] Example prompt sentence:

[1036] "Design a system that performs sentiment analysis and displays customized content based on a student's learning progress. When a student wearing smart glasses enters a store, the camera will capture their facial expressions in real time and analyze their emotions. The system will display the most appropriate content on the screen along with the progress data obtained from the server."

[1037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1038] Step 1:

[1039] The server collects students' learning progress data (test results, assignment submission status, learning history) and emotional data (facial expressions, voice, etc.) in real time. This involves the student's device capturing data using a camera or microphone and sending the data to the server. The input is the student's learning progress data and emotional data, and the output is processed data that is stored in a database on the server.

[1040] Step 2:

[1041] The server stores the collected data in a database. This database stores learning progress data and emotional data for each student. The input is the data collected in step 1, and the output is updated information for the database.

[1042] Step 3:

[1043] The server analyzes the learning progress data and emotion data stored in the database using the generative model and emotion engine. Based on the analysis, a customized learning program for each student is generated. The input is the data stored in the database, and the output is the generated learning program.

[1044] Step 4:

[1045] The server sends the generated learning program to the student's terminal, which displays the received learning program and allows the student to access it. The input is the generated learning program, and the output is the customized learning content displayed on the terminal.

[1046] Step 5:

[1047] The server collects past school lunch data and local consumption data and uses this to predict food demand. It uses a generative model to predict future food demand and creates a food procurement plan based on this prediction. The input is past school lunch data and local consumption data, and the output is a procurement plan.

[1048] Step 6:

[1049] The server orders the necessary ingredients from local restaurants and retail stores based on the procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the specified delivery schedule. The input is the procurement plan, and the output is the order information and delivery instructions.

[1050] Step 7:

[1051] When a student wearing a smart device enters a physical store, the camera captures the student's facial expression, and the emotion engine analyzes the data in real time. The input is the student's facial expression data, and the output is the analyzed emotion data.

[1052] Step 8:

[1053] The server generates optimized content based on the emotional data and learning progress data analyzed in real time and displays it on the smart device. The input is the emotional data and learning progress data, and the output is customized content displayed on the smart device.

[1054] Step 9:

[1055] Students can view the customized content displayed on their smart devices, and experience learning and relaxation benefits. Here, the input is the content displayed on the smart device, and the output is the student's learning and relaxation benefits.

[1056] The above are the processing steps of this system.

[1057] 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.

[1058] 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.

[1059] 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.

[1060] [Third embodiment]

[1061] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1062] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1063] 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).

[1064] 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.

[1065] 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.

[1066] 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).

[1067] 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.

[1068] 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.

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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."

[1073] The system of this invention uses a generative model to collect and analyze students' learning progress data in real time and provide customized learning programs free of charge or at a low cost. It also uses the generative model to optimize food demand forecasting and inventory management, and works with local restaurants and retailers to provide healthy school lunches to students free of charge, thereby reducing the burden on parents and reducing food waste.

[1074] Educational support implementation form

[1075] Data collection

[1076] The server collects students' test results, assignment submission status, and learning history in real time and stores them in a database. Students use learning applications through their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data.

[1077] Create a customized learning program

[1078] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends the program to the device.

[1079] Specific examples

[1080] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. The student can then use their device to access the customized learning program and study more efficiently.

[1081] Meal support implementation form

[1082] Demand forecasting and inventory management

[1083] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[1084] Procurement and Delivery

[1085] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[1086] Specific examples

[1087] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[1088] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[1089] The processing flow will be explained below.

[1090] Educational Support Program Processing Steps

[1091] Step 1: Collect data

[1092] Device: When students complete online tests or assignments, their results and progress data are recorded and sent to the server.

[1093] Server: Stores the received data in a database.

[1094] Specific actions

[1095] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[1096] The server stores this data in a database for later analysis.

[1097] Step 2: Analyze your learning progress

[1098] Server: Provides student learning progress data stored in a database to the generative model and performs analysis.

[1099] Device: Display progress on a dashboard so users can see student progress in real time.

[1100] Specific actions

[1101] The server inputs students' test scores and assignment submission status into the generative model, and analyzes the current situation and evaluates their level of understanding.

[1102] The device displays feedback on progress and level of understanding, which users (students and parents) can check.

[1103] Step 3: Create a customized learning program

[1104] Server: Uses the generative model to create a learning program optimized for each student and sends that program to the device.

[1105] Device: Displays received learning programs and allows students to access them.

[1106] Specific actions

[1107] Based on the generative model, the server selects teaching materials and exercises to strengthen the student's weak points and generates a customized learning program.

[1108] The generated learning program is sent to the terminal, and the student can access the program and start learning.

[1109] Step 4: Tracking and feedback

[1110] Terminal: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress has been made.

[1111] Server: Analyzes progress data and updates learning programs as needed.

[1112] Specific actions

[1113] When students complete online exercises on their devices, the results are automatically sent to the server.

[1114] The server analyzes this data and adjusts the learning program accordingly based on progress and level of understanding.

[1115] Meal Assistance Program Processing Steps

[1116] Step 1: Demand forecast

[1117] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[1118] Specific actions

[1119] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[1120] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[1121] Step 2: Plan your food procurement

[1122] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[1123] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[1124] Specific actions

[1125] The server calculates how much of each ingredient is needed based on the predicted demand.

[1126] The server automatically sends ordering information to local retailers and restaurants.

[1127] Step 3: Ingredient delivery and inventory management

[1128] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[1129] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[1130] Specific actions

[1131] The server receives order confirmation from the store and plans when to deliver the ingredients.

[1132] The store terminal sends an order confirmation and delivery completion notification to the server.

[1133] Step 4: Meal delivery and feedback

[1134] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[1135] Server: Analyzes the received data and reflects it in the next demand forecast.

[1136] Specific actions

[1137] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[1138] The server analyzes this data and further optimizes the food supply plan.

[1139] Through these steps, the system provides efficient and effective support in both education and feeding.

[1140] Example 1

[1141] 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."

[1142] With conventional learning programs and school lunch delivery systems, it was difficult to customize them to suit each student's learning progress, and food demand forecasting and inventory management were insufficient, which meant that educational effectiveness and meal quality were not fully improved. For this reason, there is a need for a system that provides individually optimized learning programs and efficiently manages ingredients and provides school lunches.

[1143] 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.

[1144] In this invention, the server includes means for collecting and analyzing a learner's learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the learner's information processing device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients and providing meals in cooperation with local restaurants and retailers based on the generated procurement plan, means for providing the learner with access to the customized learning program via the learner's information processing device, and means for providing the learner with meal pickup instructions via the learner's information processing device. This enables the provision of an individually optimized learning program and the efficient and prompt procurement of ingredients and provision of meals.

[1145] A "generative model" is a system that uses machine learning algorithms to learn patterns in data and make predictions or generate new data.

[1146] "Learning progress data" refers to data that indicates the results and progress a learner has achieved through their learning activities, and specifically includes test results, assignment submission status, learning history, etc.

[1147] "Real-time" means that a process or operation occurs immediately or with very little delay.

[1148] A "customized learning program" is a program that provides learning content and materials tailored to the needs and progress of individual learners.

[1149] An "information processing device" is an electronic device that has functions such as collecting, processing, storing, and transmitting data, and specifically includes tablets and personal computers.

[1150] "Demand forecasting" is the process of predicting future demand based on past data and various factors.

[1151] "Inventory management" means understanding the stock status of necessary goods and materials and maintaining and managing them appropriately.

[1152] "Food procurement planning" refers to the process of planning the types and quantities of ingredients needed based on predicted demand and securing them.

[1153] "Food and beverage establishment" means a facility that has a place or equipment for serving food and beverages, and specifically includes restaurants and cafeterias.

[1154] "Retailer" refers to a trader or company that sells goods to the general public.

[1155] "Learner" means a person who participates in an educational program or learning activity.

[1156] "Access" means making a system or data available.

[1157] "Pickup Instructions" means notices or instructions providing information regarding the pickup of goods or services.

[1158] The system of this invention uses a generative model to collect and analyze learner progress data in real time and provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, aiming to provide learners with healthy meals in collaboration with local restaurants and retailers.

[1159] Educational support implementation form

[1160] Data collection

[1161] The server collects learners' test results, assignment submission status, and learning history in real time and stores them in a database. Learners use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. The software used is a learning management system (LMS). This allows the server to always have the latest learning progress data.

[1162] Create a customized learning program

[1163] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates a learning program optimized for each learner and sends that program to the information processing device. The generative AI model used includes, for example, a large-scale GPT-based language model.

[1164] Specific examples

[1165] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to that student. The student can then use their device to access the customized learning program and study efficiently.

[1166] Example prompts to input to a generative AI model:

[1167] "Please create additional learning materials for today based on Learner A's latest learning progress data."

[1168] Meal support implementation form

[1169] Demand forecasting and inventory management

[1170] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, an ingredient procurement plan is created. The generative AI model used includes, for example, machine learning algorithms and statistical models.

[1171] Procurement and Delivery

[1172] Based on the generated procurement plan, the server places orders for the necessary ingredients with local restaurants and retailers. Each restaurant prepares the ingredients according to the order information sent from the server and delivers them according to the specified delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the specified pickup location.

[1173] Specific examples

[1174] For example, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[1175] Example prompts to input to a generative AI model:

[1176] "Please forecast the demand for ingredients needed for school lunches next Monday and create a procurement plan."

[1177] In this way, we will create a system that provides efficient and effective services to learners in both educational and dietary support, reducing the burden on parents while supporting high-quality education and healthy eating habits.

[1178] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1179] Educational support implementation form

[1180] Data collection and storage

[1181] Step 1: Collect training data

[1182] A user (learner) logs in to a learning application using a device (e.g., a tablet or PC).

[1183] The device collects learning data such as the results of tests taken by learners, assignment submission status, and learning history.

[1184] The server issues a log data request and receives the data in real time from the terminal.

[1185] Input: Learner test results, assignment submission status, learning history, etc.

[1186] Output: Training data received in real time

[1187] Step 2: Save your data

[1188] The server stores the received learning data in a database.

[1189] Perform validation to check for data consistency and duplication.

[1190] The server performs backups to ensure data integrity.

[1191] Input: Training data received in real time

[1192] Output: Training data stored in a database

[1193] Creating and delivering customized learning programs

[1194] Step 3: Analyze the data

[1195] The server uses the generative model to analyze the learning progress data stored in the database.

[1196] Apply statistical analysis and machine learning algorithms to identify learner strengths and weaknesses.

[1197] Input: Learning progress data stored in a database

[1198] Output: Analysis results for each learner

[1199] Step 4: Generate a customized learning program

[1200] The server inputs prompts into the generative model to generate a customized learning program.

[1201] The server optimizes and organizes the generated programs for each learner.

[1202] Input: Analysis results for each learner

[1203] Output: A customized learning program

[1204] Step 5: Deliver and execute the learning program

[1205] The server transmits the generated study program to the learner's terminal.

[1206] Learners use their devices to access their customized learning programs and begin their studies.

[1207] The device again transmits the learner's progress to the server.

[1208] Input: Customized Learning Program

[1209] Output: Learning program delivered to the device and new learning progress data

[1210] Specific actions

[1211] The device receives a "fraction calculation problem set" and displays explanatory videos on the learning screen, and the user (learner) works on them.

[1212] The server generates additional learning materials using a prompt such as "Student A's weak point: Please generate additional learning materials for fraction calculations" and sends them to the terminal.

[1213] Meal support implementation form

[1214] Demand forecasting and inventory management

[1215] Step 1: Collect historical data

[1216] The server collects past school lunch data and local consumption data.

[1217] The server stores the collected data in a database.

[1218] Input: Past school lunch data and local consumption data

[1219] Output: Meal data stored in a database

[1220] Step 2: Forecast demand

[1221] The server uses a generative AI model to analyze collected past data and predict future food demand.

[1222] The server determines the amount of ingredients to be procured based on the predicted data.

[1223] Input: Meal data stored in the database

[1224] Output: Demand forecast data for ingredients

[1225] Procurement planning and execution

[1226] Step 3: Create a procurement plan

[1227] The server creates a procurement plan based on the forecast data and generates a list of required ingredients.

[1228] Store procurement plans in a database.

[1229] Input: Demand forecast data for ingredients

[1230] Output: Procurement plan and ingredients list

[1231] Step 4: Order and deliver ingredients

[1232] The server transmits food ordering information to local restaurants and retailers based on the procurement plan.

[1233] Each store prepares ingredients according to the order information from the server and delivers them according to the specified schedule.

[1234] Input: Procurement plan and ingredients list

[1235] Output: Ordering information for local restaurants and retailers

[1236] Meal provision

[1237] Step 5: Providing and managing school meals

[1238] Students receive instructions on how to collect their school lunches via their terminal.

[1239] Learners will collect their meals at designated collection points.

[1240] The server monitors the receipt status in real time and issues additional instructions as needed.

[1241] Input: Lunch information notification from the server

[1242] Output: New data generated when a learner receives a lunch.

[1243] Specific actions

[1244] The server "predicts that a large number of students will eat school lunches next Monday, plans to procure additional fresh vegetables and bread based on past data, and orders the necessary ingredients from local retailers."

[1245] The device sends a notification to the learner that "you can pick up your lunch at the school cafeteria at 8:30," and the learner picks up their lunch at the specified time.

[1246] (Application example 1)

[1247] 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."

[1248] Conventional learning support systems have difficulty monitoring students' learning progress in real time and providing individually optimized learning programs. Furthermore, there was a lack of effective methods for predicting demand for school lunches and managing inventory, making it impossible to provide healthy, waste-free school lunches. Furthermore, there was no system that could centrally manage and notify learning programs and school lunch receipt information using devices such as smartphones.

[1249] 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.

[1250] In this invention, the server includes means for collecting and analyzing student learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the student's device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches, and means for centrally managing and notifying the learning program and school lunch receipt information via the student's smartphone. This enables improved learning efficiency and the provision of healthy school lunches, while simultaneously reducing the burden on parents and reducing food waste.

[1251] A "generative model" is a model that uses machine learning algorithms to learn patterns from large datasets and generate new data.

[1252] "Learning progress data" refers to data such as the results and history of students' educational activities, test results, and assignment submission status.

[1253] "Study Program" means customized learning materials, assignments, and lesson plans to support and facilitate student learning.

[1254] "Means of collecting and analyzing in real time" refers to technologies and systems for instantly obtaining student learning progress data via a network and analyzing that data.

[1255] A "means for generating a customized learning program" is an algorithm or system for generating an optimal learning plan based on the learning progress data and characteristics of each individual student.

[1256] A "terminal" is a device that allows a user to access the system via the Internet, such as a smartphone, tablet, or PC.

[1257] "Demand forecast for ingredients" refers to predicting the amount of ingredients needed for a specific period in the future.

[1258] "Inventory management" is the act or system of understanding and appropriately managing the stock status of ingredients and other items.

[1259] A "procurement plan" is a plan that determines what items to procure, when, and in what quantities in order to meet future demand.

[1260] "Local Restaurants and Retailers" means food and beverage businesses and retailers located within the Service Area.

[1261] "Means of notification" refers to technologies and systems for informing users of information via smartphones or other devices.

[1262] This invention is a system that collects and analyzes students' learning progress data in real time, provides customized learning programs, and also provides free healthy school lunches in cooperation with local restaurants and retailers. This system aims to make students' learning more efficient and reduce the burden on parents.

[1263] First, the server uses the generative model to collect and analyze students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database and analyzed by the generative model.

[1264] The server then uses the generative model to generate a customized learning program based on the analysis results. The generated learning program is optimized for each student's learning progress and areas of weakness, and includes specific problem sets and learning materials. This program is then sent to the student's device and displayed there.

[1265] In addition to supporting learning, the server uses generative models to forecast food demand and optimize inventory management, creating food procurement plans. It predicts future food demand based on past school lunch data and local consumption data, and places orders with local restaurants and retailers based on that data.

[1266] Local restaurants and retailers prepare ingredients according to the procurement plan sent from the server and deliver them to the school or students' homes at the designated date and time. Students receive instructions on how to collect their school lunches via their smartphones and pick them up at the designated pickup location.

[1267] This series of processes is carried out using the following hardware and software.

[1268] Hardware: Smartphones (iOS / Android), tablets, PCs, servers

[1269] Software: Python, Flask (backend), React Native (frontend), generative AI model (OpenAI GPT), database (e.g., PostgreSQL)

[1270] As a specific example of use, if a student has many weak points on a math test, this data is sent to the server and analyzed. For example, a prompt such as, "This student's learning progress data is as follows. Since his math test scores are poor, please generate the most appropriate additional learning materials and review questions" is input into the generative model. The server then provides the generated learning program to the student. The student can access the program through their device and study efficiently.

[1271] Regarding school lunches, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their smartphones that they can pick up their school lunch at the school cafeteria at 8:30, allowing them to pick up their lunch free of charge at the specified location and time.

[1272] This system will improve students' learning efficiency, enable the provision of healthy school lunches, reduce the burden on parents, and reduce food waste.

[1273] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1274] Step 1:

[1275] The server collects and analyzes students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database. The input is learning progress data, and the output is the student's learning data stored in the database.

[1276] Step 2:

[1277] The server uses the generative model to analyze the learning progress data stored in the database. The server inputs the prompts and learning progress data into the generative model and obtains the analysis results. Specifically, the generative model identifies the student's weaknesses and suggests optimal additional learning materials and review questions. The inputs are the learning progress data and prompts, and the output is the analysis results.

[1278] Step 3:

[1279] The server uses the generative model to generate a customized learning program based on the analysis results. Specifically, the generative model generates an optimal learning program based on the analysis results, and the program is configured to match the student's learning goals. The input is the analysis results, and the output is a customized learning program.

[1280] Step 4:

[1281] The server provides the generated learning program to the student's terminal. Specifically, the server transmits the generated learning program to the student's terminal, and the learning program is displayed on the terminal. The input is the customized learning program, and the output is the learning program displayed on the student's terminal.

[1282] Step 5:

[1283] The server uses a generative model to optimize food ingredient demand forecasting and inventory management. The server inputs past school lunch data and local consumption data, and the generative model predicts future food ingredient demand. The inputs are past school lunch data and local consumption data, and the output is the predicted food ingredient demand.

[1284] Step 6:

[1285] The server creates a procurement plan based on the predicted food demand. Specifically, the server uses a generative model to generate an optimal procurement plan and orders ingredients from local restaurants and retailers. The input is the predicted food demand, and the output is the procurement plan and ordering information.

[1286] Step 7:

[1287] Based on the procurement plan, the server works with local restaurants and retailers to procure ingredients and provide meals. The stores prepare ingredients according to the procurement plan sent from the server and deliver them on the specified date and time. The input is the procurement plan, and the output is the delivered ingredients.

[1288] Step 8:

[1289] The user receives the school lunch pickup instructions via their smartphone and picks up the lunch at the designated pickup location. The student's smartphone receives the pickup information sent from the server and is notified to the device. The input is the pickup instructions from the server, and the output is the pickup instructions displayed on the student's smartphone.

[1290] Through the above processing steps, the system not only efficiently manages students' learning progress and provides individually optimized learning programs, but also provides healthy school lunches, reducing the burden on parents and food waste.

[1291] 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.

[1292] The system of this invention uses a generative model and an emotion engine to collect and analyze students' learning progress data and emotion data in real time to provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, and aims to reduce the burden on parents and food waste by providing healthy school lunches to students in collaboration with local restaurants and retailers.

[1293] Educational support implementation form

[1294] Data collection

[1295] The server collects students' test results, assignment submission status, learning history, and emotional data collected through the emotion engine in real time and stores them in a database. Students use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data and emotional data.

[1296] Create a customized learning program

[1297] Using the generative model and emotion engine, the server analyzes the learning progress data and emotion data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends it to the device. Emotional data is also taken into account, so for example, if a student feels stressed while studying, relaxing content will be provided.

[1298] Specific examples

[1299] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. At the same time, if the emotion engine detects that the student is feeling stressed, it will also provide relaxation content and advice. The student can then use their device to access the customized learning program and study more efficiently.

[1300] Meal support implementation form

[1301] Demand forecasting and inventory management

[1302] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[1303] Procurement and Delivery

[1304] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[1305] Specific examples

[1306] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[1307] Embodiment of Emotion Engine

[1308] Collecting and analyzing emotional data

[1309] The emotion engine recognizes emotions from students' facial expressions and voice in real time and sends this emotional data to the server, which stores it in a database and analyzes it in conjunction with learning progress data.

[1310] Specific examples

[1311] For example, if a student's facial expressions are analyzed through the camera while they are studying, and the emotion engine detects signs of fatigue or stress, this information is sent to the server, which can use this data to adjust the study program and add content or exercises that help the student relax.

[1312] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[1313] The processing flow will be explained below.

[1314] Educational Support Program Processing Steps

[1315] Step 1: Collect data

[1316] Device: When students complete online tests or assignments, the results and progress data are recorded and sent to the server. The device also collects emotional data from students' facial expressions and voices via the device's camera and microphone.

[1317] Server: Stores the received learning progress data and emotion data in a database.

[1318] Specific actions

[1319] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[1320] The device captures the student's facial expressions, collects emotional data such as stress and concentration, and sends it to a server.

[1321] The server stores this data in a database for analysis.

[1322] Step 2: Analyzing learning progress and sentiment data

[1323] Server: Provides the learning progress data and emotion data stored in the database to the generative model and emotion engine for analysis.

[1324] Device: Display information on a dashboard so users can see students' learning progress and emotional state in real time.

[1325] Specific actions

[1326] The server inputs students' test scores, assignment submission status, and emotional data into the generative model and emotion engine, and analyzes the current situation and evaluates their level of understanding and emotional state.

[1327] The device displays feedback on learning progress and emotional state, which can be checked by the user (students or parents).

[1328] Step 3: Create a customized learning program

[1329] Server: Uses generative models and emotion engines to create learning programs optimized for each student and send them to the device.

[1330] Device: Displays received learning programs and allows students to access them.

[1331] Specific actions

[1332] Based on the generative model and emotional data, the server selects teaching materials and exercises with individually tailored content, and generates a customized learning program.

[1333] The device will display this learning program so students can access it and begin learning.

[1334] Step 4: Tracking and feedback

[1335] Device: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress is reached. It also simultaneously records the student's emotional state through an emotion engine.

[1336] Server: Analyzes progress and emotion data and updates the learning program as needed.

[1337] Specific actions

[1338] When students complete online exercises on their devices, the results are automatically sent to the server.

[1339] The device also records the student's emotional state and transmits it to the server.

[1340] The server analyzes this data and adjusts the learning program accordingly based on progress, level of understanding, and emotional state.

[1341] Meal Assistance Program Processing Steps

[1342] Step 1: Demand forecast

[1343] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[1344] Specific actions

[1345] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[1346] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[1347] Step 2: Plan your food procurement

[1348] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[1349] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[1350] Specific actions

[1351] The server calculates how much of each ingredient is needed based on the predicted demand.

[1352] The server automatically sends ordering information to local retailers and restaurants.

[1353] Step 3: Ingredient delivery and inventory management

[1354] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[1355] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[1356] Specific actions

[1357] The server receives order confirmation from the store and plans when to deliver the ingredients.

[1358] The store terminal sends an order confirmation and delivery completion notification to the server.

[1359] Step 4: Meal delivery and feedback

[1360] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[1361] Server: Analyzes the received data and reflects it in the next demand forecast.

[1362] Specific actions

[1363] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[1364] The server analyzes this data and further optimizes the food supply plan.

[1365] Through these steps, the system provides efficient and effective support in both education and feeding.

[1366] Example 2

[1367] 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."

[1368] Conventional educational support systems and school lunch management systems lack the functionality to monitor students' learning progress and emotional state in real time and provide customized learning programs and meals based on that information. This has resulted in issues such as ineffective learning support and meal provision tailored to the needs of each student, reduced learning efficiency, and increased childcare burdens. Furthermore, systems lack the ability to adjust learning programs using emotional data or optimize food procurement based on local consumption patterns.

[1369] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1370] In this invention, the server includes: means for collecting and analyzing students' learning progress data and emotional data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model and an emotion engine; means for providing the generated learning program to the student's device; means for creating a procurement plan for optimizing ingredient demand forecasting and inventory management using the generative model; means for procuring ingredients in cooperation with local stores based on the generated procurement plan and providing school lunches; means for collecting and analyzing emotional data from students' facial expressions and voices using the emotion engine; and means for appropriately adjusting the learning program based on the collected emotional data. This makes it possible to provide an optimal learning program and healthy school lunches based on each student's learning progress and emotional state.

[1371] A "generative model" is a model designed based on artificial intelligence, and is a technology that learns patterns from large amounts of data and generates new data and content.

[1372] The "emotion engine" is a system that recognizes emotions in real time from students' facial expressions, voices, etc., and generates or analyzes data based on that.

[1373] "Study progress data" is a general term for data that indicates a student's learning progress, such as test results, assignment submission status, and learning history.

[1374] A "customized learning program" refers to learning plans and materials that are individually designed based on each student's learning progress and emotional data.

[1375] "Device" refers to an electronic device (e.g., tablet or PC) used by a student, on which a learning application runs.

[1376] "Food demand forecasting" is the process of predicting the amount of food ingredients that will be needed in the future based on past consumption data and regional consumption patterns.

[1377] "Inventory management" is the process of monitoring and adjusting inventory to ensure needed materials and goods are available at the right time.

[1378] "Procurement plan" refers to a schedule or action plan for appropriately procuring necessary supplies and ingredients based on predicted demand.

[1379] "Local stores" refers to organizations or individual businesses that provide or sell food ingredients, such as restaurants and retail stores located within the local area.

[1380] "Learning program adjustment" is the process of appropriately modifying and optimizing an existing learning program based on a student's latest learning progress and emotional state.

[1381] The system of this invention utilizes generative models and emotion engines to collect and analyze students' learning progress and emotion data in real time, providing individually optimized learning programs. It also has the function of optimizing food demand forecasting and inventory management, and collaborating with local stores to provide healthy school lunches to students.

[1382] Specifically, the server system is configured using the following hardware and software:

[1383] Hardware: Database server, application server, camera, microphone

[1384] Software: generative AI models, emotion engines, learning applications

[1385] Educational support implementation form

[1386] In educational support, the program is executed in the following steps.

[1387] 1. Data Collection

[1388] Devices send learning data: Students' devices (e.g., tablets or PCs) collect learning data such as test results, assignment submission status, and learning history, and send this data to the server.

[1389] The server receives emotion data: The server receives emotion data from students' facial expressions and voices collected via the emotion engine in real time and stores it in a database.

[1390] The server stores the data: The server stores the received learning data and emotion data in a database, and keeps the information up to date.

[1391] 2. Creating a customized learning program

[1392] The server analyzes the data: Using a generative AI model and emotion engine, the learning progress data and emotion data stored in the database are analyzed to understand the individual needs of students.

[1393] The server generates a learning program: Based on the analysis results, a generative AI model is used to generate a learning program optimized for each student.

[1394] The terminal receives the learning program: The generated learning program is distributed to the student's terminal, and the student can use it to advance their studies.

[1395] Specific examples

[1396] If a student has difficulty with many questions on a math test, the server analyzes the data and generates a customized learning program that includes additional practice problems and explanatory videos. At the same time, if the emotion engine detects that the student is feeling stressed, it also provides relaxing content (e.g., simple meditation videos). The student can access the new learning program through their device and study more efficiently.

[1397] "Based on students' math test results, generate additional learning materials to strengthen their weak areas. Also, suggest relaxing content based on emotional data."

[1398] Meal support implementation form

[1399] In meal assistance, the program is executed in the following steps.

[1400] 1. Demand forecasting and inventory management

[1401] Server collects historical data: The server collects historical school lunch data and local consumption data from a database.

[1402] Server predicts demand: Using a generative AI model, the server predicts future demand for ingredients. Based on the prediction results, the server determines the amount of ingredients needed.

[1403] 2. Procurement and Delivery

[1404] The server creates an ordering plan: The server creates a procurement plan for ingredients based on the predicted demand data.

[1405] The server places an order with the local store: Based on the created procurement plan, the server places an order with the local store for the necessary ingredients.

[1406] The device will notify you of the pickup instructions: The student's device will receive a pickup instruction for the school lunch.

[1407] Specific examples

[1408] If the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan additional orders for fresh vegetables and bread, and order the necessary ingredients from local stores. Students will receive a notification via their device that they can pick up their school lunch at 8:30 a.m. at the school cafeteria, allowing them to receive it free of charge.

[1409] "Predict student lunch demand for the coming week and generate a food procurement plan based on that. Consider past consumption data and current inventory to create a plan for optimal sourcing of fresh ingredients."

[1410] Embodiment of Emotion Engine

[1411] The emotion engine functions as follows:

[1412] 1. Collecting and analyzing emotional data

[1413] The device records facial expressions and voice: The student's device uses a camera and microphone to capture emotional data from facial expressions and voice.

[1414] The server receives and stores the emotion data: The acquired emotion data is sent to the server and stored in a database.

[1415] The server analyzes the emotional data: The stored emotional data is analyzed in conjunction with learning progress data and reflected in the learning program.

[1416] Specific examples

[1417] If a student feels fatigued or stressed while studying, facial expression data is captured through the device's camera and sent to the server. The server uses this data to adjust the learning program and add relaxing content (e.g., relaxation music or short exercises), thereby improving the student's learning efficiency.

[1418] As described above, this system uses a generative AI model and an emotion engine to provide optimal learning programs based on each student's learning progress and emotional state, as well as healthy school lunches based on local consumption patterns. The system aims to provide efficient and effective services in both educational and meal support, reducing the burden on parents.

[1419] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1420] Educational support processing steps

[1421] Step 1: Data collection

[1422] The device sends the learning data

[1423] Input: Student test results, assignment submission status, learning history.

[1424] Data processing: The device collects this learning data and standardizes the format.

[1425] Output: Send the organized training data to the server.

[1426] Specific operation: Every time a student submits a test or assignment, the device automatically collects data and periodically sends it to the server.

[1427] Step 2: Collect and store emotion data

[1428] The device records facial expressions and voice

[1429] Input: Real-time facial expressions and voice of students.

[1430] Data processing: The emotion engine analyzes these data and extracts the emotional state.

[1431] Output: Send the extracted emotion data to the server.

[1432] How it works: While learning, the device's camera and microphone record the student's facial expressions and voice, and an emotion engine detects signs of stress or fatigue.

[1433] Step 3: Save your data

[1434] The server receives and stores the data

[1435] Input: Training data and emotion data sent from the device.

[1436] Data processing: The server organizes the data and stores it in a database.

[1437] Output: The latest learning progress data and emotion data are stored in the database.

[1438] Specific operation: The server periodically updates the database and maintains the data in real time.

[1439] Step 4: Data analysis

[1440] The server analyzes the data

[1441] Input: Saved learning progress data and emotion data.

[1442] Data processing: Analyze data using generative AI models and emotion engines to understand individual student needs.

[1443] Output: The analytical results that form the basis of the learning program.

[1444] Specific operation: The server periodically scans and analyzes the database.

[1445] Step 5: Generate a learning program

[1446] The server generates the learning program.

[1447] Input: Results of data analysis.

[1448] Data processing: The generative AI model generates a customized learning program based on the analysis results.

[1449] Output: An individually optimized learning program.

[1450] Specific operation: Using the analysis results, additional learning materials are generated for students who need extra help with math, for example.

[1451] Step 6: Delivering the learning program

[1452] The device receives the learning program

[1453] Input: The customized learning program sent from the server.

[1454] Data processing: The learning program received by the terminal is converted into a displayable format.

[1455] Output: The learning program provided to the student.

[1456] Specific operation: When a student logs in, the latest learning program is displayed on the device.

[1457] Meal assistance processing steps

[1458] Step 1: Collect demand forecast data

[1459] The server collects historical data

[1460] Input: Past school lunch data, local consumption data.

[1461] Data processing: Read the necessary data from the database and prepare it for analysis.

[1462] Output: A historical dataset that can be analyzed.

[1463] Specific operation: The server periodically extracts the necessary data from the database and prepares it for analysis.

[1464] Step 2: Demand forecast

[1465] Server predicts demand

[1466] Input: Collected historical data.

[1467] Data processing: Using generative AI models to predict future food demand.

[1468] Output: The amount of ingredients needed.

[1469] Specific operation: Based on the generated forecast data, a list of ingredients needed for the next week is created.

[1470] Step 3: Create a procurement plan

[1471] The server creates an ordering plan

[1472] Input: Forecasted demand data.

[1473] Data processing: A procurement plan is created based on this data.

[1474] Output: A procurement plan including the order quantity and source of each ingredient.

[1475] Specific operation: Create detailed ordering instructions for local stores based on the generative model.

[1476] Step 4: Place an order

[1477] The server places an order with the local store.

[1478] Input: Procurement Plan.

[1479] Data processing: Converting procurement plans into actual order data.

[1480] Output: Purchase order email or system message.

[1481] Specific operation: The server orders ingredients from local stores based on the procurement plan.

[1482] Step 5: Notification of school lunch information

[1483] The device will notify you of the pickup instructions.

[1484] Input: Lunch guide data from the server.

[1485] Data processing: Converting data into a format that is easy for students to understand.

[1486] Output: Pickup instructions displayed on the terminal.

[1487] Specific operation: Notify students' devices of the time and location to pick up their lunch.

[1488] Emotion Engine Processing Steps

[1489] Step 1: Collecting emotion data

[1490] The device records facial expressions and voice

[1491] Input: Real-time facial expressions and voices of students as they learn.

[1492] Data processing: The emotion engine analyzes the emotional state from facial expressions and voice.

[1493] Output: Parsed emotion data.

[1494] Specific operation: The device's camera and microphone continuously monitor the student's condition, and the emotion engine analyzes the data.

[1495] Step 2: Storing emotion data

[1496] The server receives and stores emotion data.

[1497] Input: Emotion data sent from the device.

[1498] Data processing: Organize the data and store it in a database.

[1499] Output: The latest emotion data stored in the database.

[1500] Specific operation: Emotional data is recorded in a database in real time and used for analysis.

[1501] Step 3: Analyze the emotion data

[1502] The server analyzes the emotion data

[1503] Input: Stored emotion data and learning progress data.

[1504] Data processing: Using the emotion engine, emotional data is analyzed in conjunction with training data.

[1505] Output: Analysis results that are reflected in the learning program.

[1506] Specific Actions: Assess how students' emotional states affect their learning and provide feedback to their learning programs.

[1507] Step 4: Adjust your learning program

[1508] The server coordinates the learning program

[1509] Input: Analysis results of emotion data.

[1510] Data processing: Adjust the learning program as needed.

[1511] Output: A tailored learning program.

[1512] Action: If relaxation is needed, add relaxing content to your study program.

[1513] Through the above processing steps, the system can provide optimal learning programs and meal services according to the student's learning progress and emotional state.

[1514] (Application example 2)

[1515] 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."

[1516] Conventional learning support systems have difficulty grasping the emotional state of each student in real time and providing customized content according to that state. Furthermore, effective demand forecasting and inventory management are difficult when it comes to procuring and providing ingredients for school lunches, resulting in food waste. It is necessary to simultaneously provide students with an effective learning environment and healthy eating habits while reducing the burden on parents.

[1517] 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: means for collecting and analyzing students' learning progress data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model; means for providing the generated learning program to the student's device; means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management; means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches; and means for analyzing students' emotional states in real time via smart devices and displaying customized content. This enables an optimized learning environment for each student and efficient school lunch provision based on demand forecasts.

[1518] A "generative model" is an algorithm or statistical model used to generate new information or content from data.

[1519] "Learning progress data" refers to data that indicates a student's learning progress, such as their learning activities and test results.

[1520] "Analysis" is the process of examining specific data or information in detail to understand its meaning and patterns.

[1521] A "customized learning program" is learning materials or plans that are optimized for each individual student based on the student's learning progress data and emotional state.

[1522] "Terminal" refers to an electronic device for processing and displaying digital data, such as a tablet, PC, or smart device.

[1523] "Food demand forecasting" is the process of predicting the amount of food ingredients that will be needed based on future consumption trends.

[1524] "Inventory management" is the process of controlling and optimizing the quantity of goods held for sale or consumption.

[1525] "Procurement Plan" means a plan established for the purchase or acquisition of needed goods or services.

[1526] "Local restaurants and retailers" are establishments that sell food and goods within a specific geographic area.

[1527] "School lunch" refers to meals provided at schools and other facilities.

[1528] A "smart device" is an electronic device that has internet connectivity and advanced computing capabilities.

[1529] "Emotional state" refers to an individual's psychological or emotional state at a particular moment.

[1530] "Customized Content" means content that is tailored to a user's specific needs or preferences.

[1531] The system of this invention uses a generative model and emotion engine to collect and analyze students' learning progress data and emotion data in real time to provide customized learning programs. Furthermore, it aims to reduce the burden on parents in raising children and reduce food waste by optimizing food demand forecasting and inventory management and providing healthy school lunches to students in collaboration with local restaurants and retailers.

[1532] System Configuration

[1533] Hardware configuration:

[1534] Server: Executes and manages data collection, analysis, and generative models for the entire system.

[1535] Devices: Tablets, PCs, smart devices (smart glasses), etc. used by students to interactively access learning programs.

[1536] Smart devices: Collect students' emotional states in real time and use them for analysis.

[1537] Software configuration:

[1538] Generative model: An algorithm that generates new information or content from data.

[1539] Emotion engine: Software that analyzes students' facial expressions and voices via camera to recognize their emotional state in real time.

[1540] OpenCV (cv2): A library for image processing.

[1541] DeepFace: A library for emotion recognition.

[1542] TensorFlow / Keras: Deep learning frameworks for training models.

[1543] Requests: An HTTP request library for retrieving data from the server.

[1544] Processing Details

[1545] Data collection and analysis:

[1546] The server collects students' learning progress data (test results, assignment submission status, learning history) and emotional data (facial expressions, voice, etc.) in real time and stores them in a database. Using the emotion engine, emotional data collected from smart devices is also sent to the server, ensuring that the latest data is always kept.

[1547] Generate a customized learning program:

[1548] Using the generative model and emotion engine, the server analyzes the learning progress data and emotion data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends it to the device. Emotional data is also taken into account, so for example, if a student feels stressed while studying, relaxing content will be provided.

[1549] Demand forecasting and inventory management:

[1550] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan. It sends ordering information to each store and manages the preparation and delivery of appropriate ingredients.

[1551] Examples:

[1552] For example, when a student wears smart glasses and enters a physical store, the camera captures the student's facial expressions and the emotion engine analyzes the data. The server generates optimized content based on the student's emotional state and learning progress data in real time and displays it on the smart glasses. This allows students to receive content that promotes relaxation and learning on the spot.

[1553] Example prompt sentence:

[1554] "Design a system that performs sentiment analysis and displays customized content based on a student's learning progress. When a student wearing smart glasses enters a store, the camera will capture their facial expressions in real time and analyze their emotions. The system will display the most appropriate content on the screen along with the progress data obtained from the server."

[1555] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1556] Step 1:

[1557] The server collects students' learning progress data (test results, assignment submission status, learning history) and emotional data (facial expressions, voice, etc.) in real time. This involves the student's device capturing data using a camera or microphone and sending the data to the server. The input is the student's learning progress data and emotional data, and the output is processed data that is stored in a database on the server.

[1558] Step 2:

[1559] The server stores the collected data in a database. This database stores learning progress data and emotional data for each student. The input is the data collected in step 1, and the output is updated information for the database.

[1560] Step 3:

[1561] The server analyzes the learning progress data and emotion data stored in the database using the generative model and emotion engine. Based on the analysis, a customized learning program for each student is generated. The input is the data stored in the database, and the output is the generated learning program.

[1562] Step 4:

[1563] The server sends the generated learning program to the student's terminal, which displays the received learning program and allows the student to access it. The input is the generated learning program, and the output is the customized learning content displayed on the terminal.

[1564] Step 5:

[1565] The server collects past school lunch data and local consumption data and uses this to predict food demand. It uses a generative model to predict future food demand and creates a food procurement plan based on this prediction. The input is past school lunch data and local consumption data, and the output is a procurement plan.

[1566] Step 6:

[1567] The server orders the necessary ingredients from local restaurants and retail stores based on the procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the specified delivery schedule. The input is the procurement plan, and the output is the order information and delivery instructions.

[1568] Step 7:

[1569] When a student wearing a smart device enters a physical store, the camera captures the student's facial expression, and the emotion engine analyzes the data in real time. The input is the student's facial expression data, and the output is the analyzed emotion data.

[1570] Step 8:

[1571] The server generates optimized content based on the emotional data and learning progress data analyzed in real time and displays it on the smart device. The input is the emotional data and learning progress data, and the output is customized content displayed on the smart device.

[1572] Step 9:

[1573] Students can view the customized content displayed on their smart devices, and experience learning and relaxation benefits. Here, the input is the content displayed on the smart device, and the output is the student's learning and relaxation benefits.

[1574] The above are the processing steps of this system.

[1575] 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.

[1576] 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.

[1577] 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.

[1578] [Fourth embodiment]

[1579] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1580] 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.

[1581] 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).

[1582] 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.

[1583] 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.

[1584] 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).

[1585] 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.

[1586] 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.

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] 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."

[1592] The system of this invention uses a generative model to collect and analyze students' learning progress data in real time and provide customized learning programs free of charge or at a low cost. It also uses the generative model to optimize food demand forecasting and inventory management, and works with local restaurants and retailers to provide healthy school lunches to students free of charge, thereby reducing the burden on parents and reducing food waste.

[1593] Educational support implementation form

[1594] Data collection

[1595] The server collects students' test results, assignment submission status, and learning history in real time and stores them in a database. Students use learning applications through their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data.

[1596] Create a customized learning program

[1597] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends the program to the device.

[1598] Specific examples

[1599] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. The student can then use their device to access the customized learning program and study more efficiently.

[1600] Meal support implementation form

[1601] Demand forecasting and inventory management

[1602] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[1603] Procurement and Delivery

[1604] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[1605] Specific examples

[1606] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[1607] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[1608] The processing flow will be explained below.

[1609] Educational Support Program Processing Steps

[1610] Step 1: Collect data

[1611] Device: When students complete online tests or assignments, their results and progress data are recorded and sent to the server.

[1612] Server: Stores the received data in a database.

[1613] Specific actions

[1614] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[1615] The server stores this data in a database for later analysis.

[1616] Step 2: Analyze your learning progress

[1617] Server: Provides student learning progress data stored in a database to the generative model and performs analysis.

[1618] Device: Display progress on a dashboard so users can see student progress in real time.

[1619] Specific actions

[1620] The server inputs students' test scores and assignment submission status into the generative model, and analyzes the current situation and evaluates their level of understanding.

[1621] The device displays feedback on progress and level of understanding, which users (students and parents) can check.

[1622] Step 3: Create a customized learning program

[1623] Server: Uses the generative model to create a learning program optimized for each student and sends that program to the device.

[1624] Device: Displays received learning programs and allows students to access them.

[1625] Specific actions

[1626] Based on the generative model, the server selects teaching materials and exercises to strengthen the student's weak points and generates a customized learning program.

[1627] The generated learning program is sent to the terminal, and the student can access the program and start learning.

[1628] Step 4: Tracking and feedback

[1629] Terminal: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress has been made.

[1630] Server: Analyzes progress data and updates learning programs as needed.

[1631] Specific actions

[1632] When students complete online exercises on their devices, the results are automatically sent to the server.

[1633] The server analyzes this data and adjusts the learning program accordingly based on progress and level of understanding.

[1634] Meal Assistance Program Processing Steps

[1635] Step 1: Demand forecast

[1636] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[1637] Specific actions

[1638] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[1639] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[1640] Step 2: Plan your food procurement

[1641] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[1642] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[1643] Specific actions

[1644] The server calculates how much of each ingredient is needed based on the predicted demand.

[1645] The server automatically sends ordering information to local retailers and restaurants.

[1646] Step 3: Ingredient delivery and inventory management

[1647] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[1648] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[1649] Specific actions

[1650] The server receives order confirmation from the store and plans when to deliver the ingredients.

[1651] The store terminal sends an order confirmation and delivery completion notification to the server.

[1652] Step 4: Meal delivery and feedback

[1653] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[1654] Server: Analyzes the received data and reflects it in the next demand forecast.

[1655] Specific actions

[1656] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[1657] The server analyzes this data and further optimizes the food supply plan.

[1658] Through these steps, the system provides efficient and effective support in both education and feeding.

[1659] Example 1

[1660] 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."

[1661] With conventional learning programs and school lunch delivery systems, it was difficult to customize them to suit each student's learning progress, and food demand forecasting and inventory management were insufficient, which meant that educational effectiveness and meal quality were not fully improved. For this reason, there is a need for a system that provides individually optimized learning programs and efficiently manages ingredients and provides school lunches.

[1662] 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.

[1663] In this invention, the server includes means for collecting and analyzing a learner's learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the learner's information processing device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients and providing meals in cooperation with local restaurants and retailers based on the generated procurement plan, means for providing the learner with access to the customized learning program via the learner's information processing device, and means for providing the learner with meal pickup instructions via the learner's information processing device. This enables the provision of an individually optimized learning program and the efficient and prompt procurement of ingredients and provision of meals.

[1664] A "generative model" is a system that uses machine learning algorithms to learn patterns in data and make predictions or generate new data.

[1665] "Learning progress data" refers to data that indicates the results and progress a learner has achieved through their learning activities, and specifically includes test results, assignment submission status, learning history, etc.

[1666] "Real-time" means that a process or operation occurs immediately or with very little delay.

[1667] A "customized learning program" is a program that provides learning content and materials tailored to the needs and progress of individual learners.

[1668] An "information processing device" is an electronic device that has functions such as collecting, processing, storing, and transmitting data, and specifically includes tablets and personal computers.

[1669] "Demand forecasting" is the process of predicting future demand based on past data and various factors.

[1670] "Inventory management" means understanding the stock status of necessary goods and materials and maintaining and managing them appropriately.

[1671] "Food procurement planning" refers to the process of planning the types and quantities of ingredients needed based on predicted demand and securing them.

[1672] "Food and beverage establishment" means a facility that has a place or equipment for serving food and beverages, and specifically includes restaurants and cafeterias.

[1673] "Retailer" refers to a trader or company that sells goods to the general public.

[1674] "Learner" means a person who participates in an educational program or learning activity.

[1675] "Access" means making a system or data available.

[1676] "Pickup Instructions" means notices or instructions providing information regarding the pickup of goods or services.

[1677] The system of this invention uses a generative model to collect and analyze learner progress data in real time and provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, aiming to provide learners with healthy meals in collaboration with local restaurants and retailers.

[1678] Educational support implementation form

[1679] Data collection

[1680] The server collects learners' test results, assignment submission status, and learning history in real time and stores them in a database. Learners use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. The software used is a learning management system (LMS). This allows the server to always have the latest learning progress data.

[1681] Create a customized learning program

[1682] Using the generative model, the server analyzes the learning progress data stored in the database. Based on the analysis results, the generative model creates a learning program optimized for each learner and sends that program to the information processing device. The generative AI model used includes, for example, a large-scale GPT-based language model.

[1683] Specific examples

[1684] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to that student. The student can then use their device to access the customized learning program and study efficiently.

[1685] Example prompts to input to a generative AI model:

[1686] "Please create additional learning materials for today based on Learner A's latest learning progress data."

[1687] Meal support implementation form

[1688] Demand forecasting and inventory management

[1689] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, an ingredient procurement plan is created. The generative AI model used includes, for example, machine learning algorithms and statistical models.

[1690] Procurement and Delivery

[1691] Based on the generated procurement plan, the server places orders for the necessary ingredients with local restaurants and retailers. Each restaurant prepares the ingredients according to the order information sent from the server and delivers them according to the specified delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the specified pickup location.

[1692] Specific examples

[1693] For example, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[1694] Example prompts to input to a generative AI model:

[1695] "Please forecast the demand for ingredients needed for school lunches next Monday and create a procurement plan."

[1696] In this way, we will create a system that provides efficient and effective services to learners in both educational and dietary support, reducing the burden on parents while supporting high-quality education and healthy eating habits.

[1697] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1698] Educational support implementation form

[1699] Data collection and storage

[1700] Step 1: Collect training data

[1701] A user (learner) logs in to a learning application using a device (e.g., a tablet or PC).

[1702] The device collects learning data such as the results of tests taken by learners, assignment submission status, and learning history.

[1703] The server issues a log data request and receives the data in real time from the terminal.

[1704] Input: Learner test results, assignment submission status, learning history, etc.

[1705] Output: Training data received in real time

[1706] Step 2: Save your data

[1707] The server stores the received learning data in a database.

[1708] Perform validation to check for data consistency and duplication.

[1709] The server performs backups to ensure data integrity.

[1710] Input: Training data received in real time

[1711] Output: Training data stored in a database

[1712] Creating and delivering customized learning programs

[1713] Step 3: Analyze the data

[1714] The server uses the generative model to analyze the learning progress data stored in the database.

[1715] Apply statistical analysis and machine learning algorithms to identify learner strengths and weaknesses.

[1716] Input: Learning progress data stored in a database

[1717] Output: Analysis results for each learner

[1718] Step 4: Generate a customized learning program

[1719] The server inputs prompts into the generative model to generate a customized learning program.

[1720] The server optimizes and organizes the generated programs for each learner.

[1721] Input: Analysis results for each learner

[1722] Output: A customized learning program

[1723] Step 5: Deliver and execute the learning program

[1724] The server transmits the generated study program to the learner's terminal.

[1725] Learners use their devices to access their customized learning programs and begin their studies.

[1726] The device again transmits the learner's progress to the server.

[1727] Input: Customized Learning Program

[1728] Output: Learning program delivered to the device and new learning progress data

[1729] Specific actions

[1730] The device receives a "fraction calculation problem set" and displays explanatory videos on the learning screen, and the user (learner) works on them.

[1731] The server generates additional learning materials using a prompt such as "Student A's weak point: Please generate additional learning materials for fraction calculations" and sends them to the terminal.

[1732] Meal support implementation form

[1733] Demand forecasting and inventory management

[1734] Step 1: Collect historical data

[1735] The server collects past school lunch data and local consumption data.

[1736] The server stores the collected data in a database.

[1737] Input: Past school lunch data and local consumption data

[1738] Output: Meal data stored in a database

[1739] Step 2: Forecast demand

[1740] The server uses a generative AI model to analyze collected past data and predict future food demand.

[1741] The server determines the amount of ingredients to be procured based on the predicted data.

[1742] Input: Meal data stored in the database

[1743] Output: Demand forecast data for ingredients

[1744] Procurement planning and execution

[1745] Step 3: Create a procurement plan

[1746] The server creates a procurement plan based on the forecast data and generates a list of required ingredients.

[1747] Store procurement plans in a database.

[1748] Input: Demand forecast data for ingredients

[1749] Output: Procurement plan and ingredients list

[1750] Step 4: Order and deliver ingredients

[1751] The server transmits food ordering information to local restaurants and retailers based on the procurement plan.

[1752] Each store prepares ingredients according to the order information from the server and delivers them according to the specified schedule.

[1753] Input: Procurement plan and ingredients list

[1754] Output: Ordering information for local restaurants and retailers

[1755] Meal provision

[1756] Step 5: Providing and managing school meals

[1757] Students receive instructions on how to collect their school lunches via their terminal.

[1758] Learners will collect their meals at designated collection points.

[1759] The server monitors the receipt status in real time and issues additional instructions as needed.

[1760] Input: Lunch information notification from the server

[1761] Output: New data generated when a learner receives a lunch.

[1762] Specific actions

[1763] The server "predicts that a large number of students will eat school lunches next Monday, plans to procure additional fresh vegetables and bread based on past data, and orders the necessary ingredients from local retailers."

[1764] The device sends a notification to the learner that "you can pick up your lunch at the school cafeteria at 8:30," and the learner picks up their lunch at the specified time.

[1765] (Application example 1)

[1766] 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."

[1767] Conventional learning support systems have difficulty monitoring students' learning progress in real time and providing individually optimized learning programs. Furthermore, there was a lack of effective methods for predicting demand for school lunches and managing inventory, making it impossible to provide healthy, waste-free school lunches. Furthermore, there was no system that could centrally manage and notify learning programs and school lunch receipt information using devices such as smartphones.

[1768] 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.

[1769] In this invention, the server includes means for collecting and analyzing student learning progress data in real time using a generative model, means for generating a customized learning program based on the analysis results using the generative model, means for providing the generated learning program to the student's device, means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management, means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches, and means for centrally managing and notifying the learning program and school lunch receipt information via the student's smartphone. This enables improved learning efficiency and the provision of healthy school lunches, while simultaneously reducing the burden on parents and reducing food waste.

[1770] A "generative model" is a model that uses machine learning algorithms to learn patterns from large datasets and generate new data.

[1771] "Learning progress data" refers to data such as the results and history of students' educational activities, test results, and assignment submission status.

[1772] "Study Program" means customized learning materials, assignments, and lesson plans to support and facilitate student learning.

[1773] "Means of collecting and analyzing in real time" refers to technologies and systems for instantly obtaining student learning progress data via a network and analyzing that data.

[1774] A "means for generating a customized learning program" is an algorithm or system for generating an optimal learning plan based on the learning progress data and characteristics of each individual student.

[1775] A "terminal" is a device that allows a user to access the system via the Internet, such as a smartphone, tablet, or PC.

[1776] "Demand forecast for ingredients" refers to predicting the amount of ingredients needed for a specific period in the future.

[1777] "Inventory management" is the act or system of understanding and appropriately managing the stock status of ingredients and other items.

[1778] A "procurement plan" is a plan that determines what items to procure, when, and in what quantities in order to meet future demand.

[1779] "Local Restaurants and Retailers" means food and beverage businesses and retailers located within the Service Area.

[1780] "Means of notification" refers to technologies and systems for informing users of information via smartphones or other devices.

[1781] This invention is a system that collects and analyzes students' learning progress data in real time, provides customized learning programs, and also provides free healthy school lunches in cooperation with local restaurants and retailers. This system aims to make students' learning more efficient and reduce the burden on parents.

[1782] First, the server uses the generative model to collect and analyze students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database and analyzed by the generative model.

[1783] The server then uses the generative model to generate a customized learning program based on the analysis results. The generated learning program is optimized for each student's learning progress and areas of weakness, and includes specific problem sets and learning materials. This program is then sent to the student's device and displayed there.

[1784] In addition to supporting learning, the server uses generative models to forecast food demand and optimize inventory management, creating food procurement plans. It predicts future food demand based on past school lunch data and local consumption data, and places orders with local restaurants and retailers based on that data.

[1785] Local restaurants and retailers prepare ingredients according to the procurement plan sent from the server and deliver them to the school or students' homes at the designated date and time. Students receive instructions on how to collect their school lunches via their smartphones and pick them up at the designated pickup location.

[1786] This series of processes is carried out using the following hardware and software.

[1787] Hardware: Smartphones (iOS / Android), tablets, PCs, servers

[1788] Software: Python, Flask (backend), React Native (frontend), generative AI model (OpenAI GPT), database (e.g., PostgreSQL)

[1789] As a specific example of use, if a student has many weak points on a math test, this data is sent to the server and analyzed. For example, a prompt such as, "This student's learning progress data is as follows. Since his math test scores are poor, please generate the most appropriate additional learning materials and review questions" is input into the generative model. The server then provides the generated learning program to the student. The student can access the program through their device and study efficiently.

[1790] Regarding school lunches, if the server predicts that a large number of students will be eating school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their smartphones that they can pick up their school lunch at the school cafeteria at 8:30, allowing them to pick up their lunch free of charge at the specified location and time.

[1791] This system will improve students' learning efficiency, enable the provision of healthy school lunches, reduce the burden on parents, and reduce food waste.

[1792] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1793] Step 1:

[1794] The server collects and analyzes students' learning progress data in real time. Specifically, the server obtains test results, assignment submission status, and learning history from students' devices (smartphones, tablets, PCs, etc.) via the network. This data is stored in a database. The input is learning progress data, and the output is the student's learning data stored in the database.

[1795] Step 2:

[1796] The server uses the generative model to analyze the learning progress data stored in the database. The server inputs the prompts and learning progress data into the generative model and obtains the analysis results. Specifically, the generative model identifies the student's weaknesses and suggests optimal additional learning materials and review questions. The inputs are the learning progress data and prompts, and the output is the analysis results.

[1797] Step 3:

[1798] The server uses the generative model to generate a customized learning program based on the analysis results. Specifically, the generative model generates an optimal learning program based on the analysis results, and the program is configured to match the student's learning goals. The input is the analysis results, and the output is a customized learning program.

[1799] Step 4:

[1800] The server provides the generated learning program to the student's terminal. Specifically, the server transmits the generated learning program to the student's terminal, and the learning program is displayed on the terminal. The input is the customized learning program, and the output is the learning program displayed on the student's terminal.

[1801] Step 5:

[1802] The server uses a generative model to optimize food ingredient demand forecasting and inventory management. The server inputs past school lunch data and local consumption data, and the generative model predicts future food ingredient demand. The inputs are past school lunch data and local consumption data, and the output is the predicted food ingredient demand.

[1803] Step 6:

[1804] The server creates a procurement plan based on the predicted food demand. Specifically, the server uses a generative model to generate an optimal procurement plan and orders ingredients from local restaurants and retailers. The input is the predicted food demand, and the output is the procurement plan and ordering information.

[1805] Step 7:

[1806] Based on the procurement plan, the server works with local restaurants and retailers to procure ingredients and provide meals. The stores prepare ingredients according to the procurement plan sent from the server and deliver them on the specified date and time. The input is the procurement plan, and the output is the delivered ingredients.

[1807] Step 8:

[1808] The user receives the school lunch pickup instructions via their smartphone and picks up the lunch at the designated pickup location. The student's smartphone receives the pickup information sent from the server and is notified to the device. The input is the pickup instructions from the server, and the output is the pickup instructions displayed on the student's smartphone.

[1809] Through the above processing steps, the system not only efficiently manages students' learning progress and provides individually optimized learning programs, but also provides healthy school lunches, reducing the burden on parents and food waste.

[1810] 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.

[1811] The system of this invention uses a generative model and an emotion engine to collect and analyze students' learning progress data and emotion data in real time to provide customized learning programs. It also uses the generative model to optimize food demand forecasting and inventory management, and aims to reduce the burden on parents and food waste by providing healthy school lunches to students in collaboration with local restaurants and retailers.

[1812] Educational support implementation form

[1813] Data collection

[1814] The server collects students' test results, assignment submission status, learning history, and emotional data collected through the emotion engine in real time and stores them in a database. Students use learning applications on their devices (e.g., tablets or PCs), and this data is sent to the server. This allows the server to always have the latest learning progress data and emotional data.

[1815] Create a customized learning program

[1816] Using the generative model and emotion engine, the server analyzes the learning progress data and emotion data stored in the database. Based on the analysis results, the generative model creates an optimized learning program for each student and sends it to the device. Emotional data is also taken into account, so for example, if a student feels stressed while studying, relaxing content will be provided.

[1817] Specific examples

[1818] For example, if a student has difficulty with many questions on a math test, the server analyzes this data and uses a generative model to generate additional learning materials and review questions tailored to the student. At the same time, if the emotion engine detects that the student is feeling stressed, it will also provide relaxation content and advice. The student can then use their device to access the customized learning program and study more efficiently.

[1819] Meal support implementation form

[1820] Demand forecasting and inventory management

[1821] The server collects and analyzes past school lunch data and local consumption data, and uses a generative model to predict future food demand. Based on this predicted data, it creates an ingredient procurement plan.

[1822] Procurement and Delivery

[1823] The server places orders for the necessary ingredients with local restaurants and retailers based on the generated procurement plan. Each store prepares the ingredients according to the order information sent from the server and delivers them according to the designated delivery schedule. Students receive instructions for picking up their school lunches via their devices and pick up their meals at the designated pickup location.

[1824] Specific examples

[1825] For example, if the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan the procurement of additional fresh vegetables and bread, and order the necessary ingredients from local retailers. Students will receive a notification on their devices that they can pick up their school lunches at 8:30 a.m. at the school cafeteria, allowing them to receive them free of charge.

[1826] Embodiment of Emotion Engine

[1827] Collecting and analyzing emotional data

[1828] The emotion engine recognizes emotions from students' facial expressions and voice in real time and sends this emotional data to the server, which stores it in a database and analyzes it in conjunction with learning progress data.

[1829] Specific examples

[1830] For example, if a student's facial expressions are analyzed through the camera while they are studying, and the emotion engine detects signs of fatigue or stress, this information is sent to the server, which can use this data to adjust the study program and add content or exercises that help the student relax.

[1831] In this way, we will be able to provide efficient and effective services to students in both educational and meal support, realizing a system that supports high-quality education and healthy eating habits while reducing the burden on parents.

[1832] The processing flow will be explained below.

[1833] Educational Support Program Processing Steps

[1834] Step 1: Collect data

[1835] Device: When students complete online tests or assignments, the results and progress data are recorded and sent to the server. The device also collects emotional data from students' facial expressions and voices via the device's camera and microphone.

[1836] Server: Stores the received learning progress data and emotion data in a database.

[1837] Specific actions

[1838] When a student completes a math test on their device, their score and answers are automatically sent to the server.

[1839] The device captures the student's facial expressions, collects emotional data such as stress and concentration, and sends it to a server.

[1840] The server stores this data in a database for analysis.

[1841] Step 2: Analyzing learning progress and sentiment data

[1842] Server: Provides the learning progress data and emotion data stored in the database to the generative model and emotion engine for analysis.

[1843] Device: Display information on a dashboard so users can see students' learning progress and emotional state in real time.

[1844] Specific actions

[1845] The server inputs students' test scores, assignment submission status, and emotional data into the generative model and emotion engine, and analyzes the current situation and evaluates their level of understanding and emotional state.

[1846] The device displays feedback on learning progress and emotional state, which can be checked by the user (students or parents).

[1847] Step 3: Create a customized learning program

[1848] Server: Uses generative models and emotion engines to create learning programs optimized for each student and send them to the device.

[1849] Device: Displays received learning programs and allows students to access them.

[1850] Specific actions

[1851] Based on the generative model and emotional data, the server selects teaching materials and exercises with individually tailored content, and generates a customized learning program.

[1852] The device will display this learning program so students can access it and begin learning.

[1853] Step 4: Tracking and feedback

[1854] Device: Records the progress of the student's learning program and reports the progress to the server when a certain level of progress is reached. It also simultaneously records the student's emotional state through an emotion engine.

[1855] Server: Analyzes progress and emotion data and updates the learning program as needed.

[1856] Specific actions

[1857] When students complete online exercises on their devices, the results are automatically sent to the server.

[1858] The device also records the student's emotional state and transmits it to the server.

[1859] The server analyzes this data and adjusts the learning program accordingly based on progress, level of understanding, and emotional state.

[1860] Meal Assistance Program Processing Steps

[1861] Step 1: Demand forecast

[1862] Server: Analyzes past school lunch data and local consumption data using a generative model to predict future food demand.

[1863] Specific actions

[1864] The server retrieves school lunch consumption data from the database for the past year, inputs it into the generative model, and performs analysis.

[1865] The generative model predicts fluctuations in demand due to specific days of the week, weather, and seasons, and calculates demand for the following week.

[1866] Step 2: Plan your food procurement

[1867] Server: Generates an optimal food procurement plan based on demand forecast data and places orders with local restaurants and retailers.

[1868] Terminal (terminal at local restaurants and retail stores): Receives the order information sent from the server and prepares the necessary ingredients.

[1869] Specific actions

[1870] The server calculates how much of each ingredient is needed based on the predicted demand.

[1871] The server automatically sends ordering information to local retailers and restaurants.

[1872] Step 3: Ingredient delivery and inventory management

[1873] Server: Receives order confirmations from each store and creates an optimal delivery schedule.

[1874] Terminal (restaurant / retailer terminal): Sends order confirmation to the server and prepares for delivery.

[1875] Specific actions

[1876] The server receives order confirmation from the store and plans when to deliver the ingredients.

[1877] The store terminal sends an order confirmation and delivery completion notification to the server.

[1878] Step 4: Meal delivery and feedback

[1879] Terminal: Records information when students pick up their lunches at school or at designated pick-up locations and sends it to the server.

[1880] Server: Analyzes the received data and reflects it in the next demand forecast.

[1881] Specific actions

[1882] When a student receives their lunch, the device scans the QR code and sends the receipt information to the server.

[1883] The server analyzes this data and further optimizes the food supply plan.

[1884] Through these steps, the system provides efficient and effective support in both education and feeding.

[1885] Example 2

[1886] 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."

[1887] Conventional educational support systems and school lunch management systems lack the functionality to monitor students' learning progress and emotional state in real time and provide customized learning programs and meals based on that information. This has resulted in issues such as ineffective learning support and meal provision tailored to the needs of each student, reduced learning efficiency, and increased childcare burdens. Furthermore, systems lack the ability to adjust learning programs using emotional data or optimize food procurement based on local consumption patterns.

[1888] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1889] In this invention, the server includes: means for collecting and analyzing students' learning progress data and emotional data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model and an emotion engine; means for providing the generated learning program to the student's device; means for creating a procurement plan for optimizing ingredient demand forecasting and inventory management using the generative model; means for procuring ingredients in cooperation with local stores based on the generated procurement plan and providing school lunches; means for collecting and analyzing emotional data from students' facial expressions and voices using the emotion engine; and means for appropriately adjusting the learning program based on the collected emotional data. This makes it possible to provide an optimal learning program and healthy school lunches based on each student's learning progress and emotional state.

[1890] A "generative model" is a model designed based on artificial intelligence, and is a technology that learns patterns from large amounts of data and generates new data and content.

[1891] The "emotion engine" is a system that recognizes emotions in real time from students' facial expressions, voices, etc., and generates or analyzes data based on that.

[1892] "Study progress data" is a general term for data that indicates a student's learning progress, such as test results, assignment submission status, and learning history.

[1893] A "customized learning program" refers to learning plans and materials that are individually designed based on each student's learning progress and emotional data.

[1894] "Device" refers to an electronic device (e.g., tablet or PC) used by a student, on which a learning application runs.

[1895] "Food demand forecasting" is the process of predicting the amount of food ingredients that will be needed in the future based on past consumption data and regional consumption patterns.

[1896] "Inventory management" is the process of monitoring and adjusting inventory to ensure needed materials and goods are available at the right time.

[1897] "Procurement plan" refers to a schedule or action plan for appropriately procuring necessary supplies and ingredients based on predicted demand.

[1898] "Local stores" refers to organizations or individual businesses that provide or sell food ingredients, such as restaurants and retail stores located within the local area.

[1899] "Learning program adjustment" is the process of appropriately modifying and optimizing an existing learning program based on a student's latest learning progress and emotional state.

[1900] The system of this invention utilizes generative models and emotion engines to collect and analyze students' learning progress and emotion data in real time, providing individually optimized learning programs. It also has the function of optimizing food demand forecasting and inventory management, and collaborating with local stores to provide healthy school lunches to students.

[1901] Specifically, the server system is configured using the following hardware and software:

[1902] Hardware: Database server, application server, camera, microphone

[1903] Software: generative AI models, emotion engines, learning applications

[1904] Educational support implementation form

[1905] In educational support, the program is executed in the following steps.

[1906] 1. Data Collection

[1907] Devices send learning data: Students' devices (e.g., tablets or PCs) collect learning data such as test results, assignment submission status, and learning history, and send this data to the server.

[1908] The server receives emotion data: The server receives emotion data from students' facial expressions and voices collected via the emotion engine in real time and stores it in a database.

[1909] The server stores the data: The server stores the received learning data and emotion data in a database, and keeps the information up to date.

[1910] 2. Creating a customized learning program

[1911] The server analyzes the data: Using a generative AI model and emotion engine, the learning progress data and emotion data stored in the database are analyzed to understand the individual needs of students.

[1912] The server generates a learning program: Based on the analysis results, a generative AI model is used to generate a learning program optimized for each student.

[1913] The terminal receives the learning program: The generated learning program is distributed to the student's terminal, and the student can use it to advance their studies.

[1914] Specific examples

[1915] If a student has difficulty with many questions on a math test, the server analyzes the data and generates a customized learning program that includes additional practice problems and explanatory videos. At the same time, if the emotion engine detects that the student is feeling stressed, it also provides relaxing content (e.g., simple meditation videos). The student can access the new learning program through their device and study more efficiently.

[1916] "Based on students' math test results, generate additional learning materials to strengthen their weak areas. Also, suggest relaxing content based on emotional data."

[1917] Meal support implementation form

[1918] In meal assistance, the program is executed in the following steps.

[1919] 1. Demand forecasting and inventory management

[1920] Server collects historical data: The server collects historical school lunch data and local consumption data from a database.

[1921] Server predicts demand: Using a generative AI model, the server predicts future demand for ingredients. Based on the prediction results, the server determines the amount of ingredients needed.

[1922] 2. Procurement and Delivery

[1923] The server creates an ordering plan: The server creates a procurement plan for ingredients based on the predicted demand data.

[1924] The server places an order with the local store: Based on the created procurement plan, the server places an order with the local store for the necessary ingredients.

[1925] The device will notify you of the pickup instructions: The student's device will receive a pickup instruction for the school lunch.

[1926] Specific examples

[1927] If the server predicts that a large number of students will eat school lunches on the following Monday, it will use past data to plan additional orders for fresh vegetables and bread, and order the necessary ingredients from local stores. Students will receive a notification via their device that they can pick up their school lunch at 8:30 a.m. at the school cafeteria, allowing them to receive it free of charge.

[1928] "Predict student lunch demand for the coming week and generate a food procurement plan based on that. Consider past consumption data and current inventory to create a plan for optimal sourcing of fresh ingredients."

[1929] Embodiment of Emotion Engine

[1930] The emotion engine functions as follows:

[1931] 1. Collecting and analyzing emotional data

[1932] The device records facial expressions and voice: The student's device uses a camera and microphone to capture emotional data from facial expressions and voice.

[1933] The server receives and stores the emotion data: The acquired emotion data is sent to the server and stored in a database.

[1934] The server analyzes the emotional data: The stored emotional data is analyzed in conjunction with learning progress data and reflected in the learning program.

[1935] Specific examples

[1936] If a student feels fatigued or stressed while studying, facial expression data is captured through the device's camera and sent to the server. The server uses this data to adjust the learning program and add relaxing content (e.g., relaxation music or short exercises), thereby improving the student's learning efficiency.

[1937] As described above, this system uses a generative AI model and an emotion engine to provide optimal learning programs based on each student's learning progress and emotional state, as well as healthy school lunches based on local consumption patterns. The system aims to provide efficient and effective services in both educational and meal support, reducing the burden on parents.

[1938] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1939] Educational support processing steps

[1940] Step 1: Data collection

[1941] The device sends the learning data

[1942] Input: Student test results, assignment submission status, learning history.

[1943] Data processing: The device collects this learning data and standardizes the format.

[1944] Output: Send the organized training data to the server.

[1945] Specific operation: Every time a student submits a test or assignment, the device automatically collects data and periodically sends it to the server.

[1946] Step 2: Collect and store emotion data

[1947] The device records facial expressions and voice

[1948] Input: Real-time facial expressions and voice of students.

[1949] Data processing: The emotion engine analyzes these data and extracts the emotional state.

[1950] Output: Send the extracted emotion data to the server.

[1951] How it works: While learning, the device's camera and microphone record the student's facial expressions and voice, and an emotion engine detects signs of stress or fatigue.

[1952] Step 3: Save your data

[1953] The server receives and stores the data

[1954] Input: Training data and emotion data sent from the device.

[1955] Data processing: The server organizes the data and stores it in a database.

[1956] Output: The latest learning progress data and emotion data are stored in the database.

[1957] Specific operation: The server periodically updates the database and maintains the data in real time.

[1958] Step 4: Data analysis

[1959] The server analyzes the data

[1960] Input: Saved learning progress data and emotion data.

[1961] Data processing: Analyze data using generative AI models and emotion engines to understand individual student needs.

[1962] Output: The analytical results that form the basis of the learning program.

[1963] Specific operation: The server periodically scans and analyzes the database.

[1964] Step 5: Generate a learning program

[1965] The server generates the learning program.

[1966] Input: Results of data analysis.

[1967] Data processing: The generative AI model generates a customized learning program based on the analysis results.

[1968] Output: An individually optimized learning program.

[1969] Specific operation: Using the analysis results, additional learning materials are generated for students who need extra help with math, for example.

[1970] Step 6: Delivering the learning program

[1971] The device receives the learning program

[1972] Input: The customized learning program sent from the server.

[1973] Data processing: The learning program received by the terminal is converted into a displayable format.

[1974] Output: The learning program provided to the student.

[1975] Specific operation: When a student logs in, the latest learning program is displayed on the device.

[1976] Meal assistance processing steps

[1977] Step 1: Collect demand forecast data

[1978] The server collects historical data

[1979] Input: Past school lunch data, local consumption data.

[1980] Data processing: Read the necessary data from the database and prepare it for analysis.

[1981] Output: A historical dataset that can be analyzed.

[1982] Specific operation: The server periodically extracts the necessary data from the database and prepares it for analysis.

[1983] Step 2: Demand forecast

[1984] Server predicts demand

[1985] Input: Collected historical data.

[1986] Data processing: Using generative AI models to predict future food demand.

[1987] Output: The amount of ingredients needed.

[1988] Specific operation: Based on the generated forecast data, a list of ingredients needed for the next week is created.

[1989] Step 3: Create a procurement plan

[1990] The server creates an ordering plan

[1991] Input: Forecasted demand data.

[1992] Data processing: A procurement plan is created based on this data.

[1993] Output: A procurement plan including the order quantity and source of each ingredient.

[1994] Specific operation: Create detailed ordering instructions for local stores based on the generative model.

[1995] Step 4: Place an order

[1996] The server places an order with the local store.

[1997] Input: Procurement Plan.

[1998] Data processing: Converting procurement plans into actual order data.

[1999] Output: Purchase order email or system message.

[2000] Specific operation: The server orders ingredients from local stores based on the procurement plan.

[2001] Step 5: Notification of school lunch information

[2002] The device will notify you of the pickup instructions.

[2003] Input: Lunch guide data from the server.

[2004] Data processing: Converting data into a format that is easy for students to understand.

[2005] Output: Pickup instructions displayed on the terminal.

[2006] Specific operation: Notify students' devices of the time and location to pick up their lunch.

[2007] Emotion Engine Processing Steps

[2008] Step 1: Collecting emotion data

[2009] The device records facial expressions and voice

[2010] Input: Real-time facial expressions and voices of students as they learn.

[2011] Data processing: The emotion engine analyzes the emotional state from facial expressions and voice.

[2012] Output: Parsed emotion data.

[2013] Specific operation: The device's camera and microphone continuously monitor the student's condition, and the emotion engine analyzes the data.

[2014] Step 2: Storing emotion data

[2015] The server receives and stores emotion data.

[2016] Input: Emotion data sent from the device.

[2017] Data processing: Organize the data and store it in a database.

[2018] Output: The latest emotion data stored in the database.

[2019] Specific operation: Emotional data is recorded in a database in real time and used for analysis.

[2020] Step 3: Analyze the emotion data

[2021] The server analyzes the emotion data

[2022] Input: Stored emotion data and learning progress data.

[2023] Data processing: Using the emotion engine, emotional data is analyzed in conjunction with training data.

[2024] Output: Analysis results that are reflected in the learning program.

[2025] Specific Actions: Assess how students' emotional states affect their learning and provide feedback to their learning programs.

[2026] Step 4: Adjust your learning program

[2027] The server coordinates the learning program

[2028] Input: Analysis results of emotion data.

[2029] Data processing: Adjust the learning program as needed.

[2030] Output: A tailored learning program.

[2031] Action: If relaxation is needed, add relaxing content to your study program.

[2032] Through the above processing steps, the system can provide optimal learning programs and meal services according to the student's learning progress and emotional state.

[2033] (Application example 2)

[2034] 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."

[2035] Conventional learning support systems have difficulty grasping the emotional state of each student in real time and providing customized content according to that state. Furthermore, effective demand forecasting and inventory management are difficult when it comes to procuring and providing ingredients for school lunches, resulting in food waste. It is necessary to simultaneously provide students with an effective learning environment and healthy eating habits while reducing the burden on parents.

[2036] 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: means for collecting and analyzing students' learning progress data in real time using a generative model; means for generating a customized learning program based on the analysis results using the generative model; means for providing the generated learning program to the student's device; means for creating an ingredient procurement plan using a generative model for optimizing ingredient demand forecasting and inventory management; means for procuring ingredients in cooperation with local restaurants and retailers based on the generated procurement plan and providing school lunches; and means for analyzing students' emotional states in real time via smart devices and displaying customized content. This enables an optimized learning environment for each student and eff...

Claims

1. A means of collecting and analyzing student learning progress data in real time using generative models; and means for generating a customized learning program based on the analysis results using the generative model; means for providing the generated learning program to a student's terminal; A means for generating a food ingredient procurement plan using a generative model for optimizing food ingredient demand forecasting and inventory management; A means for procuring ingredients and providing meals in cooperation with local restaurants and retail stores based on the generated procurement plan; A system including:

2. 10. The system of claim 1, further comprising means for collecting and monitoring student learning progress data in real time.

3. 2. The system according to claim 1, wherein the means for optimizing the food ingredient procurement plan includes means for forecasting demand based on regional consumption patterns and historical data.

Images