System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting daily-life data; means for transmitting the collected data to a server; means for the server to generate a personalized learning plan using the received data; means for transmitting the generated learning plan to a terminal; means for the terminal to give learning guidance to a child based on the learning plan; means for collecting learning progress of the child; and means for transmitting the collected learning progress to the server to reevaluate and update the learning 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] Patent specification preparation

[0005] In modern society, parents find it difficult to find enough time to support their children's learning. While there is a need for support to help children develop the habit of studying independently, it is not easy to provide an individualized learning plan tailored to each child's interests and progress. Another challenge is to promote balanced learning without bias toward a particular area of ​​study. The present invention aims to solve these problems. [Means for solving the problem]

[0006] The present invention provides a system including a means for collecting data on a child's daily life, a means for transmitting the collected data to a server, a means for the server to generate an individualized learning plan using the data received, a means for transmitting the generated learning plan to a terminal, a means for the terminal to provide learning guidance to the child based on the learning plan, a means for collecting the child's learning progress, and a means for transmitting the collected learning progress to the server and reevaluating and updating the learning plan. The system further includes a means for balancing the generated learning plan so that it does not lean toward a specific learning area, and a means for dynamically adjusting the learning plan according to the child's interests and progress, thereby encouraging the child to develop the habit of studying independently. Furthermore, the system can efficiently support children's learning while reducing the burden on parents.

[0007] ---

[0008] Definitions of important words

[0009] "Daily life data" refers to information about a child's daily activities, including study time, study content, areas of interest, grades, and activities at home.

[0010] "Device" refers to an electronic device used by a child, including a personal computer, tablet, smartphone, etc.

[0011] "Server" refers to a centralized computing device that receives, stores, analyzes data, and generates lesson plans.

[0012] An "individualized learning plan" is a plan that defines a learning schedule and assignments tailored to a specific child based on the child's interests and progress.

[0013] "Means of collection" refers to the technology or method used to collect data via a device.

[0014] "Transmission means" refers to the technology or method used to electronically transmit collected data from one location to another.

[0015] "Generative means" refers to the techniques and methods used to create new learning plans based on data analysis.

[0016] "Means of providing learning guidance" refers to technologies and methods for encouraging children to engage in learning activities by utilizing AI chatbots and dialogue systems on devices.

[0017] "Collected learning progress" refers to data about how children are actually progressing with their learning activities.

[0018] "Means of reevaluation and updating" refers to techniques and methods for reviewing the optimal learning plan based on the collected learning progress and setting a new plan if necessary.

[0019] ---

[0020] These are the definitions of important words included in the patent claims, which clarify the specific components and functions of the system. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] MODE FOR CARRYING OUT THE INVENTION

[0043] Overall system overview

[0044] The system of the present invention aims to provide technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting their children's learning. The system consists of a series of steps: collecting daily life data, generating individualized study plans, providing study guidance, and updating study progress.

[0045] Data collection methods and means

[0046] First, the user (child) uses the device to input data about their daily learning activities and areas of interest. For example, they record their learning diary, interesting assignments, actual study time, etc. The device collects this data and sends it to the server in a secure format.

[0047] Methods and means of generating lesson plans

[0048] The received data is analyzed by a server, which then generates a personalized learning plan based on the child's daily life data. Using a generative AI model, the server creates a balanced learning plan that takes into account the child's strengths, weaknesses, and interests. The plan might include 30 minutes of math practice every morning, one science experiment per week, or story reading.

[0049] Methods and means of providing study plans

[0050] The learning plan generated by the server is sent to the device, where an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Let's practice math for 30 minutes today." This allows the child to study independently.

[0051] Learning feedback and plan updates

[0052] The user (child) inputs the progress of learning activities and feedback into the device. For example, they provide feedback such as, "Today's math practice finished on time" or "The science experiment was fun." The device collects this new data and periodically sends it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to be dynamically adjusted to match the child's interests and progress.

[0053] Specific operation example

[0054] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests that day.

[0055] ---

[0056] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan taking into account a child's interests and progress, creating an environment in which children can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[0057] The processing flow will be explained below.

[0058] Program processing steps

[0059] Step 1:

[0060] The user (child) uses the device to input data about their daily learning activities and interests, such as "I solved 10 math problems today" or "I enjoyed the science experiment."

[0061] Step 2:

[0062] The device stores the entered data locally and schedules it to be sent to the server at a specified time, for example, sending daily activity data to the server at 9 PM.

[0063] Step 3:

[0064] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[0065] Step 4:

[0066] The server inputs the received data into a generative AI model, which then generates a personalized learning plan based on the child's learning tendencies and interests, such as "do 30 minutes of math practice every day and two science experiments per week."

[0067] Step 5:

[0068] The server sends the generated learning plan to the terminal, which displays the learning plan in a format that is easy for the user to view.

[0069] Step 6:

[0070] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as "Spend 30 minutes solving math problems today."

[0071] Step 7:

[0072] The user performs learning activities and inputs progress and feedback into the device, for example, recording things like "I solved all the math problems" or "I enjoyed reading."

[0073] Step 8:

[0074] The device stores learning progress data locally and schedules it to be sent to the server periodically, for example, on weekends.

[0075] Step 9:

[0076] The server receives and securely stores the progress data, and formats it for further analysis for review.

[0077] Step 10:

[0078] The server re-evaluates the lesson plan based on new data and updates it as needed, using a generative AI model to generate an updated lesson plan that adapts to the child's new interests and progress.

[0079] Step 11:

[0080] The server sends the updated learning plan to the device, and the AI ​​chatbot again provides learning guidance to the user based on the new learning plan received by the device.

[0081] This is the flow of processing in the system's program. This creates an environment where children can learn in a balanced way while keeping their interest.

[0082] Example 1

[0083] 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."

[0084] Conventional learning support systems for children have had difficulty providing educational plans that fully consider each child's interests and progress. Furthermore, the burden on parents to manage and supervise their children's learning progress is heavy, making it difficult to create an environment in which children can study independently. For this reason, there has been a demand for a balanced, individualized learning plan that children can continue without getting bored.

[0085] 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.

[0086] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to a storage device, means for generating an individualized educational plan using the data received by the storage device, means for transmitting the generated educational plan to a terminal, means for the terminal to provide learning guidance to the user based on the educational plan, means for collecting the user's learning progress, means for transmitting the collected learning progress to the storage device and reevaluating and updating the educational plan, means for analyzing the collected data and learning progress using a generative AI model, and means for generating prompt sentences based on the collected data and learning progress and providing them to the user. This makes it possible to dynamically adjust a balanced learning plan appropriate for each child and provide an environment in which the child can independently engage in learning.

[0087] "Daily life data" refers to personal activity information including a child's daily learning activities, interests, actual study time, etc.

[0088] "Storage device" means digital storage for temporary or permanent storage of collected data.

[0089] An "individualized education plan" is a customized learning schedule and assignments based on each child's interests and learning progress.

[0090] "Devices" refers to digital devices such as tablets and smartphones used by children.

[0091] "User" refers primarily to children who use this system, but may also include their parents in some cases.

[0092] "Learning guidance" refers to educational advice and assignment suggestions provided via the device.

[0093] "Learning progress" refers to the results and feedback of learning activities carried out by a user.

[0094] A "generative AI model" is an artificial intelligence algorithm used to generate useful lesson plans and prompts from user data.

[0095] A "prompt" is a set of instructions or questions that are displayed to gather additional information from the user.

[0096] MODE FOR CARRYING OUT THE INVENTION

[0097] Overall system overview

[0098] The system of the present invention aims to provide technology that enables children to study independently and efficiently support their learning while reducing the burden on parents. This system consists of a series of steps: collecting daily life data, generating individualized learning plans, providing learning guidance, and updating learning progress.

[0099] Data collection methods and means

[0100] First, the user (child) uses a device such as a tablet or smartphone to input data about their daily life. This includes study diaries, subjects of interest, and actual study time. The device collects this data and sends it to the server in a secure format. Data transfer is encrypted using the SSL / TLS protocol.

[0101] Methods and means of generating lesson plans

[0102] The server analyzes the received data using a generative AI model (e.g., an advanced natural language processing model such as GPT-3 (registered trademark)). The server generates an individualized learning plan taking into account the child's strengths, weaknesses, and areas of interest. The generated learning plan may include, for example, "30 minutes of math practice every morning," "one science experiment per week," and "reading a story."

[0103] Methods and means of providing study plans

[0104] The learning plan generated by the server is sent to the device, and learning guidance is provided to the user through an AI chatbot (for example, a conversational AI platform such as Dialogflow) on the device. The AI ​​chatbot gives the user specific instructions such as, "Practice arithmetic for 30 minutes today."

[0105] Learning feedback and plan updates

[0106] Users input their progress and feedback on their learning activities into the device. For example, they provide feedback such as, "I finished today's math practice on time" or "I enjoyed the science experiment." The device collects this new data and securely transmits it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to dynamically adjust to the user's interests and progress.

[0107] Specific operation example

[0108] For example, one day, a user might type into their device, "I had math class at school today, so I'd like to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this additional information into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then gives specific instructions, such as, "Let's try a science experiment today."

[0109] Prompt Sentence Examples

[0110] "What subject are you interested in today?"

[0111] "Please tell me your thoughts about what you learned yesterday."

[0112] "What are your learning goals this week?"

[0113] summary

[0114] The system of the present invention allows children to receive personalized learning plans that reflect their interests and progress, enabling them to study independently. This system plays a role in efficiently supporting children's learning while reducing the burden on parents.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1:

[0117] The user inputs daily life data into the device, including study journals, subjects of interest, actual study time, etc. The input data is saved in text and numerical formats.

[0118] Step 2:

[0119] The device sends the collected data to the server. During transmission, the data is encrypted using the SSL / TLS protocol and sent to the server's API endpoint via an HTTP POST request. The input is data from the user, and the output is secure data transmission to the server.

[0120] Step 3:

[0121] The server uses a generative AI model to analyze the data it receives. The received data is passed as input to the generative AI model, which assesses the child's strengths, weaknesses, and areas of interest. The output is a personalized education plan.

[0122] Step 4:

[0123] The server sends the generated personalized education plan to the device. The transmission is again performed using an HTTP POST request, with the data sent in JSON format. The input is the generated education plan, and the output is the data sent to the device.

[0124] Step 5:

[0125] The AI ​​chatbot on the device provides learning guidance to the user based on the educational plan. For example, it may instruct the user, "Let's practice arithmetic for 30 minutes today." The input is the educational plan received from the server, and the output is instructions to the user.

[0126] Step 6:

[0127] After the user has completed the learning activity, they input their progress and feedback into the device. Specifically, they input comments such as "Today's calculation practice finished on time" or "The science experiment was fun." The input is feedback from the user, and the output is the saving of the feedback data on the device.

[0128] Step 7:

[0129] The device sends new data to the server. The transmission method is the same as in step 2, encrypted with the SSL / TLS protocol and using an HTTP POST request. The input is the user's feedback data, and the output is secure data transmission to the server.

[0130] Step 8:

[0131] The server re-evaluates the lesson plan based on new data and updates it as needed using a generative AI model: the input is new feedback data, and the output is an updated instructional plan.

[0132] Step 9:

[0133] The server sends the updated lesson plan to the device. As in step 4, the transmission is done using an HTTP POST request, with the data sent in JSON format. The input is the updated lesson plan, and the output is the data sent to the device.

[0134] Step 10:

[0135] The AI ​​chatbot on the device provides the user with further learning guidance based on the updated learning plan. For example, it might instruct the user, "Spend 15 minutes today practicing your English pronunciation." The input is the updated plan, and the output is instructions to the user.

[0136] (Application example 1)

[0137] 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."

[0138] Conventional factory robot maintenance is based on a periodic maintenance schedule, which makes it difficult to perform optimal maintenance based on the operating status and frequency of use of each robot. This results in cases of excessive maintenance or, conversely, a lack of necessary maintenance, hindering efficient operation. Another issue is that maintenance is concentrated in specific work areas, resulting in unnecessary resource consumption and reduced productivity.

[0139] 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.

[0140] In this invention, the server includes a means for generating an individualized maintenance plan, a means for transmitting the generated maintenance plan to the terminal, and a means for the terminal to provide management guidance to the robot based on the maintenance plan, thereby enabling efficient and balanced maintenance according to the operating status of the robot.

[0141] "Daily data" refers to information about the tasks and operating status that robots perform on a daily basis.

[0142] "Means of collection" refers to the means of acquiring daily data using various sensors and data acquisition devices.

[0143] The "means for transmitting to the server" refers to a means for transferring the collected data to the server via a network.

[0144] "Individualized maintenance plans" involve generating a maintenance schedule optimized for a specific robot based on collected data.

[0145] "Generating means" refers to the algorithms and processes used to analyze data and create personalized maintenance plans.

[0146] The "means for transmitting to the terminal" is a means for transferring the generated maintenance plan to a terminal in the factory.

[0147] "Means for providing management guidance" refers to providing specific maintenance instructions to the robot through an application installed on the terminal or an AI chatbot.

[0148] "Operational progress" refers to information regarding the robot's work progress and operating status.

[0149] "Re-evaluation and update measures" means the algorithms and processes used to re-evaluate and, if necessary, update the maintenance plan based on collected operational progress data.

[0150] A "work domain" refers to a specific work category or task that a robot will undertake.

[0151] A "balancing measure" is a measure to adjust the maintenance plan so that it does not favor any particular area of ​​work.

[0152] "Means for dynamic adjustment" refers to the means for updating the maintenance plan in real time based on the most recent data collected.

[0153] MODE FOR CARRYING OUT THE INVENTION

[0154] Overall system overview

[0155] The system of the present invention provides technology to support the efficient maintenance of factory robots, and aims to maximize the operational efficiency of robots by collecting daily robot data and generating and providing individualized maintenance plans based on this data. This system consists of a series of processes: data collection, maintenance plan generation, management guidance, and feedback on operational progress.

[0156] Data collection methods and means

[0157] The user (factory manager) automatically collects daily data from the robot using various sensors attached to the robot. This data includes work performance, operating hours, number of errors, etc. The collected data is sent to a server via a wireless communication module.

[0158] Methods and means of generating maintenance plans

[0159] The server analyzes the data it receives and uses a generative AI model to generate a personalized maintenance plan based on the collected daily data, such as adding lubricants to increase uptime or inspecting specific parts to reduce the number of errors.

[0160] Methods and means of providing maintenance plans

[0161] The generated maintenance plan is sent to the terminal, where an AI chatbot is installed, which provides specific maintenance instructions to the robot, such as "Add lubricant today" or "Inspect specific parts."

[0162] Feedback on operational progress and plan updates

[0163] The user (factory manager) enters the progress of maintenance work and feedback into the terminal. For example, they enter information such as "lubricant added" or "component inspection completed." The terminal collects this new data and sends it to the server. The server reevaluates and updates the maintenance plan based on the new data. This enables flexible maintenance according to the robot's operating status and progress.

[0164] Specific operation example

[0165] For example, if a robot processes 1,200 parts, operates for eight hours, and encounters two errors as operational data for a given day, this data is sent to the server. The server uses a generative AI model to generate an appropriate maintenance plan based on this information. A plan containing specific details, such as "Today's maintenance plan: Add lubricant and diagnose specific parts for errors," is sent to the device. The device's AI chatbot can then instruct the robot, saying, "Today, add lubricant and diagnose parts for errors."

[0166] Prompt Sentence Examples

[0167] "Please generate a maintenance plan for Robot 001. Today, the number of operations is 1200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps."

[0168] In this way, efficient maintenance and management of factory robots can be achieved through specific operation processes.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Program processing flow

[0171] Step 1: Data collection

[0172] Input: Daily data of the robot (work performance, operating hours, number of errors, etc.)

[0173] Output: Collected data is sent to the server

[0174] The user collects daily data from factory robots. Various sensors acquire operational data, and the information is temporarily stored on a local server. The data consists of work results (e.g., processing 1,200 parts), operating time (e.g., 8 hours), number of errors (e.g., 2), etc. This collected data is sent to the cloud server via a wireless communication module.

[0175] Step 2: Data analysis and maintenance plan generation

[0176] Input: Daily data received by the server

[0177] Output: Individualized maintenance plan

[0178] The server analyzes the received data and uses a generative AI model to generate an individualized maintenance plan. For example, the server uses a data analysis engine to generate prompts based on the collected data. The prompt might read, "Generate a maintenance plan for robot 001. Today's operations are 1,200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps." The AI ​​then creates a maintenance plan, which might include adding lubricants or diagnosing errors in specific parts.

[0179] Step 3: Submit your maintenance plan

[0180] Input: Generated maintenance plan

[0181] Output: Maintenance plan sent to the device

[0182] The generated maintenance plan is sent from the server to the terminal at the factory. At this time, the management application installed on the terminal starts up and prepares to receive the maintenance plan. The server uses a transmission protocol to send the data to the terminal safely and with high accuracy.

[0183] Step 4: Implementing maintenance instructions

[0184] Input: Maintenance plan sent to the device

[0185] Output: Specific maintenance instructions for the robot

[0186] The AI ​​chatbot on the terminal then issues specific maintenance instructions to the robot based on the generated maintenance plan. These instructions might include, for example, "Today, please add lubricant and perform an error diagnosis." The robot manager then performs the maintenance work according to these instructions.

[0187] Step 5: Feedback on operational progress

[0188] Input: Maintenance work completion status and feedback

[0189] Output: Feedback data

[0190] The user inputs the completion status of the maintenance work and other feedback into the terminal. For example, information such as "Lubricant added" or "Part inspection completed" is input. This feedback data is sent from the terminal to the server.

[0191] Step 6: Reevaluate and renew your maintenance plan

[0192] Input: Collected feedback data

[0193] Output: Updated maintenance plan

[0194] The server analyzes the feedback data and re-evaluates the maintenance plan, potentially using the generative AI model again to generate and update a new maintenance plan based on the latest data, further optimizing future maintenance.

[0195] The above processing steps enable efficient and flexible maintenance and management of factory robots.

[0196] 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.

[0197] MODE FOR CARRYING OUT THE INVENTION

[0198] Overall system overview

[0199] The system of the present invention provides technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting children's learning. The system consists of a series of steps: collecting daily life data and emotional data, generating and adjusting individualized study plans, providing study guidance, and updating study progress and emotional status.

[0200] Data collection methods and means

[0201] First, the user (child) uses the device to input data about their daily learning activities and interests. For example, they record their learning diary, subjects they are interested in, and actual study time on the device. The device's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This data is saved by the device and sent to the server at a specified time.

[0202] Methods and means for generating and adjusting lesson plans

[0203] The received data is analyzed by a server, which generates a personalized learning plan based on the child's daily life and emotional data. A generative AI model is used to create a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For example, "do 30 minutes of math practice every day and two science experiments per week." The plan is adjusted based on the collected emotional data and is designed to make learning fun.

[0204] Methods and means of providing study plans

[0205] The learning plan generated by the server is sent to the device, and an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Spend 30 minutes solving math problems today." The chatbot's interaction methods are also adjusted based on emotional data. If the child seems tired, it can respond flexibly, such as offering words of encouragement.

[0206] Learning feedback and plan updates

[0207] The user completes the learning activity and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data during the learning process. For example, it tracks feedback such as "I solved all the math problems" or "I enjoyed the science experiment," as well as emotions such as "I lost concentration while learning."

[0208] The device collects this data and periodically sends it to a server, which reevaluates the lesson plan based on the new data and updates it as needed. Using a generative AI model and an emotional data analysis engine, the server generates an updated lesson plan tailored to the child's new interests and emotional state.

[0209] Specific operation example

[0210] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing lesson plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests and emotional state that day.

[0211] ---

[0212] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan that takes into account the child's interests and emotional state, creating an environment in which the child can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[0213] The processing flow will be explained below.

[0214] Program processing steps

[0215] Step 1:

[0216] The user (child) uses the device to input data about their daily learning activities and interests. For example, the device records information such as "I did a science experiment today" and stores it on the device.

[0217] Step 2:

[0218] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotion data, for example, whether the user is smiling or tired, and records the emotion data in real time.

[0219] Step 3:

[0220] The device stores the collected learning activity data and emotional data locally and sets a schedule for sending them to the server at a specified time (e.g., 9 p.m. every day).

[0221] Step 4:

[0222] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[0223] Step 5:

[0224] The server inputs the received data into a generative AI model and an emotional data analysis engine, which then generates a personalized learning plan based on the child's learning tendencies, interests, and emotional state. For example, it creates a plan that includes 30 minutes of math practice every day and two science experiments per week.

[0225] Step 6:

[0226] The server sends the generated learning plan to the device, which receives it and displays it in an easy-to-read format for the user.

[0227] Step 7:

[0228] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as, "Let's smile and do our best on the science experiment today."

[0229] Step 8:

[0230] The user performs a learning activity and inputs progress and feedback into the device. For example, feedback such as "Today's science experiment was fun" or "I'm a little tired" is recorded.

[0231] Step 9:

[0232] The emotion engine continuously collects emotional data from users while they are learning, and if a user becomes tired or loses concentration, it collects that information in real time.

[0233] Step 10:

[0234] The device stores the collected progress and emotion data locally and schedules it to send it to the server periodically (e.g., on weekends).

[0235] Step 11:

[0236] The server receives and securely stores new data sent by the device, and prepares the received data in an analytic format for further evaluation.

[0237] Step 12:

[0238] The server reevaluates the lesson plan based on the new data and updates it as necessary. Using a generative AI model and an emotional data analysis engine, the system generates an updated lesson plan tailored to the child's new interests and emotional state. For example, if the user is feeling tired, it will recommend a gentler task to reduce strain.

[0239] Step 13:

[0240] The server sends the updated study plan to the device. Based on the new study plan received by the device, the AI ​​chatbot again provides study guidance to the user. The chatbot gives instructions such as, "Set aside some time to read something relaxing today."

[0241] ---

[0242] This is the flow of processing in the program of the system that combines the emotion engine. This processing takes into account the child's interests and emotional state, providing a balanced, individualized learning plan and creating an environment in which the child can learn independently.

[0243] Example 2

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

[0245] In modern education, there is a lack of technology that allows children to study independently. This increases the burden on parents and makes it difficult to provide effective learning support. It is also difficult to generate individually customized learning plans and dynamically adjust them based on the child's interests and emotional state. To solve this problem, a system is needed that effectively utilizes learner data and continues to provide individualized learning plans.

[0246] 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.

[0247] In this invention, the server includes means for collecting daily activity data and emotional data, means for transmitting the collected data to an information processing device, means for generating an individualized learning plan using the data received by the information processing device, means for transmitting the generated learning plan to a display device, means for the display device to provide learning guidance based on the learning plan, means for collecting the learning progress of the learner, and means for transmitting the collected learning progress and emotional data to the information processing device and reevaluating and updating the learning plan. This makes it possible to generate and adjust an individualized learning plan according to the child's interests and emotional state.

[0248] "Daily activity data" refers to information about a learner's daily learning activities and interests, including, for example, a learning diary, topics of interest, and actual study time.

[0249] "Emotional data" refers to information that indicates the emotional state of a learner, and includes, for example, emotional states analyzed from changes in facial expressions and vocal tones.

[0250] "Information processing device" refers to a device that has the ability to receive and analyze data and generate, reevaluate, and update personalized learning plans, and generally includes servers and cloud systems.

[0251] An "individualized learning plan" refers to learning content and schedules that are optimized for a learner, and is a plan that is generated taking into account the learner's strengths, weaknesses, interests, and emotional state.

[0252] "Display device" refers to a device that provides learning guidance and feedback to a learner, and examples include tablets, smartphones, and computers.

[0253] "Learning guidance" refers to educational instructions and support given to a learner through a display device, including, for example, specific instructions to encourage the learner to solve a calculation problem.

[0254] "Learning progress" refers to information about the learning activities that a learner has actually performed and the results of those activities, including, for example, the number of problems solved and progress in understanding.

[0255] "Reevaluation" refers to the process of analyzing the suitability of existing learning plans based on learning progress and emotional data, and creating new plans if necessary.

[0256] "Updating" refers to the process of adjusting and revising the learning plan to the latest state based on the results of reevaluation.

[0257] ---

[0258] MODE FOR CARRYING OUT THE INVENTION

[0259] Overall system overview

[0260] The present invention provides a system that allows learners to study independently and reduces the burden on parents. This system consists of a series of processes, including collecting daily activity data and emotional data, generating and adjusting individualized learning plans, providing learning guidance, and updating learning progress and emotional states.

[0261] Data collection methods and means

[0262] First, the user (learner) uses a device to input data about their daily learning activities and interests. This data is called "daily activity data" and specifically includes study diaries, subjects of interest, and actual study time. Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect their current emotional state ("emotional data"). The device then transmits this data to a server at a specified time.

[0263] Methods and means for generating and adjusting lesson plans

[0264] The received data is analyzed by the server, which uses a generative AI model to generate a personalized learning plan optimized for the user based on daily activity data and emotional data. For example, a learning plan can be created by inputting the following prompt sentence into the generative AI model:

[0265] "Please suggest a science lesson plan for my child to complete at home after their math class at school."

[0266] "What is the appropriate lesson plan if the emotion engine detects that my child is tired?"

[0267] The generated lesson plans take into account the learner's strengths, weaknesses, interests, and emotional state, resulting in an efficient and balanced content.

[0268] Methods and means of providing learning plans

[0269] The study plan generated by the server is sent to the device. The device is equipped with an AI chatbot that provides study guidance to the user based on the study plan. For example, it gives instructions such as, "Spend 30 minutes solving math problems today." Furthermore, the chatbot's interactions are adjusted based on emotional data. For example, if the user is tired, it can respond flexibly by offering words of encouragement.

[0270] Learning feedback and plan updates

[0271] As learning progresses, users input their progress and feedback on their learning activities into the device. The device's emotion engine continuously collects the user's emotional data, which is periodically sent to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. Using a generative AI model and emotion data analysis engine, an updated learning plan is generated that adapts to the user's latest interests and emotional state.

[0272] Specific operation example

[0273] For example, one day a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing study plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the study plan, for example, by increasing the time for science experiments or reading. The updated study plan is then sent back to the device. The chatbot on the device then instructs the user, "Let's try a science experiment today." This allows the user to engage in the study that best suits their interests and emotional state that day.

[0274] ---

[0275] The above is an embodiment of the present invention. This system provides effective learning support by considering the learner's interests and emotional state and providing an individualized learning plan. It can also reduce the burden on parents.

[0276] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0277] ---

[0278] Program processing flow

[0279] Step 1: Collecting daily activity and emotion data

[0280] 1-1. Data entry

[0281] Users use the device to input data about their daily learning activities and interests, such as "I spent 30 minutes today doing math problems."

[0282] 1-2. Collecting emotion data

[0283] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotional data. The input is from a camera or microphone, and the analyzed emotional state (e.g., joy, fatigue, concentration, etc.) is obtained as output.

[0284] 1-3. Data transmission

[0285] The device sends the collected daily activity data and emotion data to the server at a specified time. The input is the daily activity data and emotion data, and the output is the data sent to the server.

[0286] Step 2: Generate a lesson plan

[0287] 2-1. Data analysis

[0288] The server analyzes the received daily activity and emotional data and uses a generative AI model to evaluate the learner's strengths, weaknesses, interests, and emotional state based on the input data, thereby creating a user profile as a result of the analysis.

[0289] 2-2. Creating a learning plan

[0290] The server inputs a prompt to the generative AI model to generate a personalized lesson plan, for example, "Please suggest a science lesson plan for my child to complete at home after their math class at school," and outputs the generated lesson plan.

[0291] 2-3. Adjusting your study plan

[0292] Based on the emotion data, the server dynamically adjusts the generated lesson plan. For example, it receives a prompt such as "What lesson plan would be appropriate if the emotion engine detected that my child is tired?" and outputs a lesson plan that matches the child's emotional state.

[0293] Step 3: Provide a learning plan

[0294] 3-1. Submitting your study plan

[0295] The server sends the generated and adjusted training plan to the terminal. The adjusted training plan is the input, and the transmitted training plan is the output.

[0296] 3-2. Implementation of learning guidance

[0297] The AI ​​chatbot on the device will provide guidance to the user based on the learning plan, outputting specific instructions such as "Spend 30 minutes solving math problems today." It will also adjust the chatbot's interactions based on emotional data, offering words of encouragement if the user appears tired.

[0298] Step 4: Learning feedback and plan updates

[0299] 4-1. Entering progress

[0300] The user performs a learning activity and inputs their progress and feedback into the terminal. For example, the terminal outputs the progress status, such as "all calculation problems solved."

[0301] 4-2. Continuous collection of emotional data

[0302] The device's emotion engine continuously collects emotional data during learning, and outputs emotional data such as "my concentration decreased while learning."

[0303] 4-3. Data transmission and analysis

[0304] The terminal sends the collected progress and emotion data to the server, which then reevaluates the data. The input is the progress and emotion data, and the output is the reevaluated information.

[0305] 4-4. Update your study plan

[0306] The server uses the generative AI model and the sentiment data analysis engine to update the lesson plan based on the latest data. For example, it inputs a new prompt sentence into the generative AI model and outputs an updated lesson plan.

[0307] ---

[0308] This is the specific processing flow of the program for this system, which allows learners to engage in optimal learning tailored to their interests and emotional state on that day.

[0309] (Application example 2)

[0310] 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."

[0311] Conventional learning support systems and factory robot work schedule management systems can only provide one-way plans and schedules, and have the problem of being unable to dynamically adjust them to take into account children's emotions and interests, or the robot's work data and emotional state. This makes it difficult to provide efficient learning support and work management that is optimized for individual situations.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0313] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to the server, means for generating an individualized learning plan using the received data, means for transmitting the generated learning plan to the terminal, means for the terminal to provide learning guidance to the child based on the learning plan, means for collecting the child's learning progress, means for transmitting the collected learning progress to the server and reevaluating and updating the learning plan, means for collecting work data and emotional data of the factory robot, means for optimizing a work schedule using a generative AI model based on the collected work data and emotional data, and means for transmitting the optimized schedule to the terminal and adjusting the robot's work. This makes it possible to optimize the child's learning plan to suit the interests and emotional state of the day, and to dynamically adjust the factory robot's work schedule based on the work data and emotional data.

[0314] "Daily life data" refers to information about a child's daily activities, specifically including a study diary, study time, and subjects of interest.

[0315] "Server" refers to the computer system that analyzes the collected data and generates personalized learning plans and work schedules.

[0316] "Terminal" refers to a device operated by a user and used to input collected data and present learning instructions.

[0317] A "generative AI model" refers to an artificial intelligence algorithm that generates personalized learning plans and work schedules based on collected data.

[0318] "Emotional data" refers to information that analyzes the emotional state of a user or robot, and specifically includes facial expressions, vocal tone, stress levels, etc.

[0319] "Study Plan" refers to an individualized learning plan created for a child's learning, including specific learning content and schedule.

[0320] A "factory robot" refers to a robot used to automate work in a factory, performing tasks such as welding, assembly, and inspection.

[0321] "Work data" refers to information about the work performed by factory robots, and specifically includes the task ID, task type, required time, etc.

[0322] A "work schedule" refers to a plan for factory robots to work efficiently, and includes specific work orders and break times.

[0323] "Dynamic adjustment" refers to changing and optimizing a child's study plan or a factory robot's work schedule in real time.

[0324] MODE FOR CARRYING OUT THE INVENTION

[0325] Overall system overview

[0326] The system of the present invention supports children's learning and manages the work of factory robots. The system consists of a series of steps: collecting daily life data and emotional data, generating individualized learning plans and work schedules, providing learning guidance and work management, and updating progress and emotional status.

[0327] Data collection methods and means

[0328] The user (child or factory robot) uses a terminal to collect data. In the case of a child, they enter their study diary, subjects of interest, actual study time, etc. into the terminal. In the case of a factory robot, work data such as task ID, task type, and required time is collected. In addition, an emotion engine installed in the terminal analyzes the user's facial expressions and voice tone to collect emotional data. This data is saved by the terminal and sent to the server at a specified time.

[0329] Generate study plans and work schedules

[0330] The server analyzes the received data and generates personalized learning plans and work schedules. Using a generative AI model, it creates a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For factory robots, it also optimizes their work schedules based on the collected work and emotional data. Examples include "perform 30 minutes of math practice every day and two science experiments per week" and "reallocate tasks because the robot is showing high levels of fatigue."

[0331] Providing study plans and work schedules

[0332] The generated learning plan and work schedule are sent to the device, where an AI chatbot or work management application on the device provides instructions to the user. The chatbot can give specific instructions, such as "Solve 30 minutes of math problems today." In the case of factory robots, the system adjusts their work based on the optimized schedule.

[0333] Learning feedback and progress updates

[0334] The user performs learning activities and inputs progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while learning or working. The collected data is periodically sent to the server, which reevaluates the learning plan or work schedule based on the new data and updates it as necessary. The generative AI model and emotion data analysis engine are used to generate an updated plan tailored to new interests and emotional situations.

[0335] Specific operation example

[0336] For example, a child might input into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the child is feeling tired from their facial expression when they input this information. The device then sends this information to the server, which then reevaluates the existing lesson plan. Through the generative AI model and emotion data analysis engine, the server dynamically adjusts the lesson plan, such as increasing time for science experiments or reading, and sends the updated plan back to the device. The chatbot on the device then gives instructions like, "Let's try a science experiment today," allowing the child to engage in learning that suits their interests and emotional state that day.

[0337] Similarly, when a factory robot completes a series of tasks, it sends data such as "Task ID: 1234, Task Type: Welding, Duration: 25 minutes, High Fatigue, Stress Level: Medium" to the server. The server analyzes this data and uses a generative AI model to regenerate an optimal work schedule. This prompt sentence can be used as a sample.

[0338] Example prompt sentence:

[0339] For example, the following prompt is input to the generative AI model:

[0340] The robot completed the following tasks:

[0341] Task ID: 1234

[0342] Task Type: Welding

[0343] Duration: 25 minutes

[0344] Robot emotional state:

[0345] Fatigue level: High

[0346] Stress level: Medium

[0347] Generate a new work schedule.

[0348] This allows for the generation of dynamically optimized schedules based on the emotional state and work data of factory robots, enabling efficient work management of robots.

[0349] Hardware and Software Use Cases

[0350] This system uses the following hardware and software:

[0351] Hardware: User devices (smartphones, tablets, PCs, etc.), factory robots, servers

[0352] Software: Emotion engine (EmotionAnalyzer module), generative AI model (TaskOptimizer module), AI chatbot, work management application

[0353] Combining these features can effectively support users' learning and work management.

[0354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0355] Step 1:

[0356] The user inputs daily life data and emotional data into the device. The input data includes study diaries, subjects of interest, and study time. In the case of factory robots, work data such as task ID, task type, and required time are collected. In addition, an emotion engine is used to analyze and collect emotional data (facial expressions, voice tone, stress level, etc.) of children and robots. This allows for a detailed understanding of the user's situation and emotional state.

[0357] Input: learning diary, interesting tasks, study time, task ID, task type, time required, emotional data

[0358] Output: Collected daily life data and emotion data

[0359] Step 2:

[0360] The device sends the collected daily life data and emotion data to the server at the specified time. The data is sent using a secure communication protocol (e.g., HTTPS), which ensures the accuracy and confidentiality of the data.

[0361] Input: Collected daily life data and emotional data

[0362] Output: Data sent to the server

[0363] Step 3:

[0364] The server analyzes the received data and generates a personalized learning plan and work schedule. The server uses a generative AI model (e.g., TaskOptimizer module) to create a balanced plan that takes into account the strengths, weaknesses, interests, and emotional state of the child and robot. Machine learning algorithms are used to analyze the data and generate an appropriate plan.

[0365] Input: Data sent to the server

[0366] Output: personalized study plan and work schedule

[0367] Step 4:

[0368] The server sends the generated learning plan and work schedule to the terminal, which receives the data and displays it on the user interface, thereby providing the user with appropriate instructions and schedules.

[0369] Input: Personalized study plan and work schedule

[0370] Output: Data sent to the terminal

[0371] Step 5:

[0372] An AI chatbot or work management application on the device will give instructions to the user. The chatbot will give specific instructions such as "Solve 30 minutes of math problems today" based on the collected learning plan. In the case of a factory robot, it will adjust its work based on an optimized schedule and display instructions such as "Task ID: 1234, please start welding work."

[0373] Input: Data sent to the terminal

[0374] Output: Specific instructions to the user

[0375] Step 6:

[0376] The user performs a learning activity or task and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while they are learning or working, allowing the user's progress and emotional state to be collected in real time.

[0377] Input: Progress and feedback, emotion data

[0378] Output: Collected progress and emotion data

[0379] Step 7:

[0380] The device periodically sends collected progress and emotion data to a server, which reevaluates the learning plan and work schedule based on the new data and updates them as needed. A generative AI model and emotion data analysis engine are used to generate the updated plan.

[0381] Input: Collected progress and emotion data

[0382] Output: Reassessed study plan and work schedule

[0383] Step 8:

[0384] The updated study plan and work schedule are sent to the terminal, and the latest instructions are given to the user again, so that the user can always act based on the optimal study and work plan.

[0385] Input: Reassessed study plan and work schedule

[0386] Output: Update data sent to the device

[0387] This allows a child's learning plan to be optimized to their interests and emotional state on that day, while the work schedule of a factory robot is dynamically adjusted based on work and emotional data.

[0388] 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.

[0389] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0390] 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.

[0391] [Second embodiment]

[0392] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0393] 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.

[0394] 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).

[0395] 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.

[0396] 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.

[0397] 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).

[0398] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0399] 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.

[0400] 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.

[0401] 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.

[0402] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0403] 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."

[0404] MODE FOR CARRYING OUT THE INVENTION

[0405] Overall system overview

[0406] The system of the present invention aims to provide technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting their children's learning. The system consists of a series of steps: collecting daily life data, generating individualized study plans, providing study guidance, and updating study progress.

[0407] Data collection methods and means

[0408] First, the user (child) uses the device to input data about their daily learning activities and areas of interest. For example, they record their learning diary, interesting assignments, actual study time, etc. The device collects this data and sends it to the server in a secure format.

[0409] Methods and means of generating lesson plans

[0410] The received data is analyzed by a server, which then generates a personalized learning plan based on the child's daily life data. Using a generative AI model, the server creates a balanced learning plan that takes into account the child's strengths, weaknesses, and interests. The plan might include 30 minutes of math practice every morning, one science experiment per week, or story reading.

[0411] Methods and means of providing study plans

[0412] The learning plan generated by the server is sent to the device, where an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Let's practice math for 30 minutes today." This allows the child to study independently.

[0413] Learning feedback and plan updates

[0414] The user (child) inputs the progress of learning activities and feedback into the device. For example, they provide feedback such as, "Today's math practice finished on time" or "The science experiment was fun." The device collects this new data and periodically sends it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to be dynamically adjusted to match the child's interests and progress.

[0415] Specific operation example

[0416] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests that day.

[0417] ---

[0418] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan taking into account a child's interests and progress, creating an environment in which children can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[0419] The processing flow will be explained below.

[0420] Program processing steps

[0421] Step 1:

[0422] The user (child) uses the device to input data about their daily learning activities and interests, such as "I solved 10 math problems today" or "I enjoyed the science experiment."

[0423] Step 2:

[0424] The device stores the entered data locally and schedules it to be sent to the server at a specified time, for example, sending daily activity data to the server at 9 PM.

[0425] Step 3:

[0426] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[0427] Step 4:

[0428] The server inputs the received data into a generative AI model, which then generates a personalized learning plan based on the child's learning tendencies and interests, such as "do 30 minutes of math practice every day and two science experiments per week."

[0429] Step 5:

[0430] The server sends the generated learning plan to the terminal, which displays the learning plan in a format that is easy for the user to view.

[0431] Step 6:

[0432] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as "Spend 30 minutes solving math problems today."

[0433] Step 7:

[0434] The user performs learning activities and inputs progress and feedback into the device, for example, recording things like "I solved all the math problems" or "I enjoyed reading."

[0435] Step 8:

[0436] The device stores learning progress data locally and schedules it to be sent to the server periodically, for example, on weekends.

[0437] Step 9:

[0438] The server receives and securely stores the progress data, and formats it for further analysis for review.

[0439] Step 10:

[0440] The server re-evaluates the lesson plan based on new data and updates it as needed, using a generative AI model to generate an updated lesson plan that adapts to the child's new interests and progress.

[0441] Step 11:

[0442] The server sends the updated learning plan to the device, and the AI ​​chatbot again provides learning guidance to the user based on the new learning plan received by the device.

[0443] This is the flow of processing in the system's program. This creates an environment where children can learn in a balanced way while keeping their interest.

[0444] Example 1

[0445] 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."

[0446] Conventional learning support systems for children have had difficulty providing educational plans that fully consider each child's interests and progress. Furthermore, the burden on parents to manage and supervise their children's learning progress is heavy, making it difficult to create an environment in which children can study independently. For this reason, there has been a demand for a balanced, individualized learning plan that children can continue without getting bored.

[0447] 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.

[0448] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to a storage device, means for generating an individualized educational plan using the data received by the storage device, means for transmitting the generated educational plan to a terminal, means for the terminal to provide learning guidance to the user based on the educational plan, means for collecting the user's learning progress, means for transmitting the collected learning progress to the storage device and reevaluating and updating the educational plan, means for analyzing the collected data and learning progress using a generative AI model, and means for generating prompt sentences based on the collected data and learning progress and providing them to the user. This makes it possible to dynamically adjust a balanced learning plan appropriate for each child and provide an environment in which the child can independently engage in learning.

[0449] "Daily life data" refers to personal activity information including a child's daily learning activities, interests, actual study time, etc.

[0450] "Storage device" means digital storage for temporary or permanent storage of collected data.

[0451] An "individualized education plan" is a customized learning schedule and assignments based on each child's interests and learning progress.

[0452] "Devices" refers to digital devices such as tablets and smartphones used by children.

[0453] "User" refers primarily to children who use this system, but may also include their parents in some cases.

[0454] "Learning guidance" refers to educational advice and assignment suggestions provided via the device.

[0455] "Learning progress" refers to the results and feedback of learning activities carried out by a user.

[0456] A "generative AI model" is an artificial intelligence algorithm used to generate useful lesson plans and prompts from user data.

[0457] A "prompt" is a set of instructions or questions that are displayed to gather additional information from the user.

[0458] MODE FOR CARRYING OUT THE INVENTION

[0459] Overall system overview

[0460] The system of the present invention aims to provide technology that enables children to study independently and efficiently support their learning while reducing the burden on parents. This system consists of a series of steps: collecting daily life data, generating individualized learning plans, providing learning guidance, and updating learning progress.

[0461] Data collection methods and means

[0462] First, the user (child) uses a device such as a tablet or smartphone to input data about their daily life. This includes study diaries, subjects of interest, and actual study time. The device collects this data and sends it to the server in a secure format. Data transfer is encrypted using the SSL / TLS protocol.

[0463] Methods and means of generating lesson plans

[0464] The server analyzes the received data using a generative AI model (e.g., an advanced natural language processing model such as GPT-3). The server generates a personalized learning plan taking into account the child's strengths, weaknesses, and areas of interest. The generated learning plan includes such things as "30 minutes of math practice every morning," "one science experiment per week," and "reading a story."

[0465] Methods and means of providing study plans

[0466] The learning plan generated by the server is sent to the device, and learning guidance is provided to the user through an AI chatbot (for example, a conversational AI platform such as Dialogflow) on the device. The AI ​​chatbot gives the user specific instructions such as, "Practice arithmetic for 30 minutes today."

[0467] Learning feedback and plan updates

[0468] Users input their progress and feedback on their learning activities into the device. For example, they provide feedback such as, "I finished today's math practice on time" or "I enjoyed the science experiment." The device collects this new data and securely transmits it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to dynamically adjust to the user's interests and progress.

[0469] Specific operation example

[0470] For example, one day, a user might type into their device, "I had math class at school today, so I'd like to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this additional information into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then gives specific instructions, such as, "Let's try a science experiment today."

[0471] Prompt Sentence Examples

[0472] "What subject are you interested in today?"

[0473] "Please tell me your thoughts about what you learned yesterday."

[0474] "What are your learning goals this week?"

[0475] summary

[0476] The system of the present invention allows children to receive personalized learning plans that reflect their interests and progress, enabling them to study independently. This system plays a role in efficiently supporting children's learning while reducing the burden on parents.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1:

[0479] The user inputs daily life data into the device, including study journals, subjects of interest, actual study time, etc. The input data is saved in text and numerical formats.

[0480] Step 2:

[0481] The device sends the collected data to the server. During transmission, the data is encrypted using the SSL / TLS protocol and sent to the server's API endpoint via an HTTP POST request. The input is data from the user, and the output is secure data transmission to the server.

[0482] Step 3:

[0483] The server uses a generative AI model to analyze the data it receives. The received data is passed as input to the generative AI model, which assesses the child's strengths, weaknesses, and areas of interest. The output is a personalized education plan.

[0484] Step 4:

[0485] The server sends the generated personalized education plan to the device. The transmission is again performed using an HTTP POST request, with the data sent in JSON format. The input is the generated education plan, and the output is the data sent to the device.

[0486] Step 5:

[0487] The AI ​​chatbot on the device provides learning guidance to the user based on the educational plan. For example, it may instruct the user, "Let's practice arithmetic for 30 minutes today." The input is the educational plan received from the server, and the output is instructions to the user.

[0488] Step 6:

[0489] After the user has completed the learning activity, they input their progress and feedback into the device. Specifically, they input comments such as "Today's calculation practice finished on time" or "The science experiment was fun." The input is feedback from the user, and the output is the saving of the feedback data on the device.

[0490] Step 7:

[0491] The device sends new data to the server. The transmission method is the same as in step 2, encrypted with the SSL / TLS protocol and using an HTTP POST request. The input is the user's feedback data, and the output is secure data transmission to the server.

[0492] Step 8:

[0493] The server re-evaluates the lesson plan based on new data and updates it as needed using a generative AI model: the input is new feedback data, and the output is an updated instructional plan.

[0494] Step 9:

[0495] The server sends the updated lesson plan to the device. As in step 4, the transmission is done using an HTTP POST request, with the data sent in JSON format. The input is the updated lesson plan, and the output is the data sent to the device.

[0496] Step 10:

[0497] The AI ​​chatbot on the device provides the user with further learning guidance based on the updated learning plan. For example, it might instruct the user, "Spend 15 minutes today practicing your English pronunciation." The input is the updated plan, and the output is instructions to the user.

[0498] (Application example 1)

[0499] 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."

[0500] Conventional factory robot maintenance is based on a periodic maintenance schedule, which makes it difficult to perform optimal maintenance based on the operating status and frequency of use of each robot. This results in cases of excessive maintenance or, conversely, a lack of necessary maintenance, hindering efficient operation. Another issue is that maintenance is concentrated in specific work areas, resulting in unnecessary resource consumption and reduced productivity.

[0501] 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.

[0502] In this invention, the server includes a means for generating an individualized maintenance plan, a means for transmitting the generated maintenance plan to the terminal, and a means for the terminal to provide management guidance to the robot based on the maintenance plan, thereby enabling efficient and balanced maintenance according to the operating status of the robot.

[0503] "Daily data" refers to information about the tasks and operating status that robots perform on a daily basis.

[0504] "Means of collection" refers to the means of acquiring daily data using various sensors and data acquisition devices.

[0505] The "means for transmitting to the server" refers to a means for transferring the collected data to the server via a network.

[0506] "Individualized maintenance plans" involve generating a maintenance schedule optimized for a specific robot based on collected data.

[0507] "Generating means" refers to the algorithms and processes used to analyze data and create personalized maintenance plans.

[0508] The "means for transmitting to the terminal" is a means for transferring the generated maintenance plan to a terminal in the factory.

[0509] "Means for providing management guidance" refers to providing specific maintenance instructions to the robot through an application installed on the terminal or an AI chatbot.

[0510] "Operational progress" refers to information regarding the robot's work progress and operating status.

[0511] "Re-evaluation and update measures" means the algorithms and processes used to re-evaluate and, if necessary, update the maintenance plan based on collected operational progress data.

[0512] A "work domain" refers to a specific work category or task that a robot will undertake.

[0513] A "balancing measure" is a measure to adjust the maintenance plan so that it does not favor any particular area of ​​work.

[0514] "Means for dynamic adjustment" refers to the means for updating the maintenance plan in real time based on the most recent data collected.

[0515] MODE FOR CARRYING OUT THE INVENTION

[0516] Overall system overview

[0517] The system of the present invention provides technology to support the efficient maintenance of factory robots, and aims to maximize the operational efficiency of robots by collecting daily robot data and generating and providing individualized maintenance plans based on this data. This system consists of a series of processes: data collection, maintenance plan generation, management guidance, and feedback on operational progress.

[0518] Data collection methods and means

[0519] The user (factory manager) automatically collects daily data from the robot using various sensors attached to the robot. This data includes work performance, operating hours, number of errors, etc. The collected data is sent to a server via a wireless communication module.

[0520] Methods and means of generating maintenance plans

[0521] The server analyzes the data it receives and uses a generative AI model to generate a personalized maintenance plan based on the collected daily data, such as adding lubricants to increase uptime or inspecting specific parts to reduce the number of errors.

[0522] Methods and means of providing maintenance plans

[0523] The generated maintenance plan is sent to the terminal, where an AI chatbot is installed, which provides specific maintenance instructions to the robot, such as "Add lubricant today" or "Inspect specific parts."

[0524] Feedback on operational progress and plan updates

[0525] The user (factory manager) enters the progress of maintenance work and feedback into the terminal. For example, they enter information such as "lubricant added" or "component inspection completed." The terminal collects this new data and sends it to the server. The server reevaluates and updates the maintenance plan based on the new data. This enables flexible maintenance according to the robot's operating status and progress.

[0526] Specific operation example

[0527] For example, if a robot processes 1,200 parts, operates for eight hours, and encounters two errors as operational data for a given day, this data is sent to the server. The server uses a generative AI model to generate an appropriate maintenance plan based on this information. A plan containing specific details, such as "Today's maintenance plan: Add lubricant and diagnose specific parts for errors," is sent to the device. The device's AI chatbot can then instruct the robot, saying, "Today, add lubricant and diagnose parts for errors."

[0528] Prompt Sentence Examples

[0529] "Please generate a maintenance plan for Robot 001. Today, the number of operations is 1200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps."

[0530] In this way, efficient maintenance and management of factory robots can be achieved through specific operation processes.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Program processing flow

[0533] Step 1: Data collection

[0534] Input: Daily data of the robot (work performance, operating hours, number of errors, etc.)

[0535] Output: Collected data is sent to the server

[0536] The user collects daily data from factory robots. Various sensors acquire operational data, and the information is temporarily stored on a local server. The data consists of work results (e.g., processing 1,200 parts), operating time (e.g., 8 hours), number of errors (e.g., 2), etc. This collected data is sent to the cloud server via a wireless communication module.

[0537] Step 2: Data analysis and maintenance plan generation

[0538] Input: Daily data received by the server

[0539] Output: Individualized maintenance plan

[0540] The server analyzes the received data and uses a generative AI model to generate an individualized maintenance plan. For example, the server uses a data analysis engine to generate prompts based on the collected data. The prompt might read, "Generate a maintenance plan for robot 001. Today's operations are 1,200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps." The AI ​​then creates a maintenance plan, which might include adding lubricants or diagnosing errors in specific parts.

[0541] Step 3: Submit your maintenance plan

[0542] Input: Generated maintenance plan

[0543] Output: Maintenance plan sent to the device

[0544] The generated maintenance plan is sent from the server to the terminal at the factory. At this time, the management application installed on the terminal starts up and prepares to receive the maintenance plan. The server uses a transmission protocol to send the data to the terminal safely and with high accuracy.

[0545] Step 4: Implementing maintenance instructions

[0546] Input: Maintenance plan sent to the device

[0547] Output: Specific maintenance instructions for the robot

[0548] The AI ​​chatbot on the terminal then issues specific maintenance instructions to the robot based on the generated maintenance plan. These instructions might include, for example, "Today, please add lubricant and perform an error diagnosis." The robot manager then performs the maintenance work according to these instructions.

[0549] Step 5: Feedback on operational progress

[0550] Input: Maintenance work completion status and feedback

[0551] Output: Feedback data

[0552] The user inputs the completion status of the maintenance work and other feedback into the terminal. For example, information such as "Lubricant added" or "Part inspection completed" is input. This feedback data is sent from the terminal to the server.

[0553] Step 6: Reevaluate and renew your maintenance plan

[0554] Input: Collected feedback data

[0555] Output: Updated maintenance plan

[0556] The server analyzes the feedback data and re-evaluates the maintenance plan, potentially using the generative AI model again to generate and update a new maintenance plan based on the latest data, further optimizing future maintenance.

[0557] The above processing steps enable efficient and flexible maintenance and management of factory robots.

[0558] 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.

[0559] MODE FOR CARRYING OUT THE INVENTION

[0560] Overall system overview

[0561] The system of the present invention provides technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting children's learning. The system consists of a series of steps: collecting daily life data and emotional data, generating and adjusting individualized study plans, providing study guidance, and updating study progress and emotional status.

[0562] Data collection methods and means

[0563] First, the user (child) uses the device to input data about their daily learning activities and interests. For example, they record their learning diary, subjects they are interested in, and actual study time on the device. The device's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This data is saved by the device and sent to the server at a specified time.

[0564] Methods and means for generating and adjusting lesson plans

[0565] The received data is analyzed by a server, which generates a personalized learning plan based on the child's daily life and emotional data. A generative AI model is used to create a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For example, "do 30 minutes of math practice every day and two science experiments per week." The plan is adjusted based on the collected emotional data and is designed to make learning fun.

[0566] Methods and means of providing study plans

[0567] The learning plan generated by the server is sent to the device, and an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Spend 30 minutes solving math problems today." The chatbot's interaction methods are also adjusted based on emotional data. If the child seems tired, it can respond flexibly, such as offering words of encouragement.

[0568] Learning feedback and plan updates

[0569] The user completes the learning activity and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data during the learning process. For example, it tracks feedback such as "I solved all the math problems" or "I enjoyed the science experiment," as well as emotions such as "I lost concentration while learning."

[0570] The device collects this data and periodically sends it to a server, which reevaluates the lesson plan based on the new data and updates it as needed. Using a generative AI model and an emotional data analysis engine, the server generates an updated lesson plan tailored to the child's new interests and emotional state.

[0571] Specific operation example

[0572] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing lesson plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests and emotional state that day.

[0573] ---

[0574] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan that takes into account the child's interests and emotional state, creating an environment in which the child can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[0575] The processing flow will be explained below.

[0576] Program processing steps

[0577] Step 1:

[0578] The user (child) uses the device to input data about their daily learning activities and interests. For example, the device records information such as "I did a science experiment today" and stores it on the device.

[0579] Step 2:

[0580] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotion data, for example, whether the user is smiling or tired, and records the emotion data in real time.

[0581] Step 3:

[0582] The device stores the collected learning activity data and emotional data locally and sets a schedule for sending them to the server at a specified time (e.g., 9 p.m. every day).

[0583] Step 4:

[0584] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[0585] Step 5:

[0586] The server inputs the received data into a generative AI model and an emotional data analysis engine, which then generates a personalized learning plan based on the child's learning tendencies, interests, and emotional state. For example, it creates a plan that includes 30 minutes of math practice every day and two science experiments per week.

[0587] Step 6:

[0588] The server sends the generated learning plan to the device, which receives it and displays it in an easy-to-read format for the user.

[0589] Step 7:

[0590] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as, "Let's smile and do our best on the science experiment today."

[0591] Step 8:

[0592] The user performs a learning activity and inputs progress and feedback into the device. For example, feedback such as "Today's science experiment was fun" or "I'm a little tired" is recorded.

[0593] Step 9:

[0594] The emotion engine continuously collects emotional data from users while they are learning, and if a user becomes tired or loses concentration, it collects that information in real time.

[0595] Step 10:

[0596] The device stores the collected progress and emotion data locally and schedules it to send it to the server periodically (e.g., on weekends).

[0597] Step 11:

[0598] The server receives and securely stores new data sent by the device, and prepares the received data in an analytic format for further evaluation.

[0599] Step 12:

[0600] The server reevaluates the lesson plan based on the new data and updates it as necessary. Using a generative AI model and an emotional data analysis engine, the system generates an updated lesson plan tailored to the child's new interests and emotional state. For example, if the user is feeling tired, it will recommend a gentler task to reduce strain.

[0601] Step 13:

[0602] The server sends the updated study plan to the device. Based on the new study plan received by the device, the AI ​​chatbot again provides study guidance to the user. The chatbot gives instructions such as, "Set aside some time to read something relaxing today."

[0603] ---

[0604] This is the flow of processing in the program of the system that combines the emotion engine. This processing takes into account the child's interests and emotional state, providing a balanced, individualized learning plan and creating an environment in which the child can learn independently.

[0605] Example 2

[0606] 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."

[0607] In modern education, there is a lack of technology that allows children to study independently. This increases the burden on parents and makes it difficult to provide effective learning support. It is also difficult to generate individually customized learning plans and dynamically adjust them based on the child's interests and emotional state. To solve this problem, a system is needed that effectively utilizes learner data and continues to provide individualized learning plans.

[0608] 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.

[0609] In this invention, the server includes means for collecting daily activity data and emotional data, means for transmitting the collected data to an information processing device, means for generating an individualized learning plan using the data received by the information processing device, means for transmitting the generated learning plan to a display device, means for the display device to provide learning guidance based on the learning plan, means for collecting the learning progress of the learner, and means for transmitting the collected learning progress and emotional data to the information processing device and reevaluating and updating the learning plan. This makes it possible to generate and adjust an individualized learning plan according to the child's interests and emotional state.

[0610] "Daily activity data" refers to information about a learner's daily learning activities and interests, including, for example, a learning diary, topics of interest, and actual study time.

[0611] "Emotional data" refers to information that indicates the emotional state of a learner, and includes, for example, emotional states analyzed from changes in facial expressions and vocal tones.

[0612] "Information processing device" refers to a device that has the ability to receive and analyze data and generate, reevaluate, and update personalized learning plans, and generally includes servers and cloud systems.

[0613] An "individualized learning plan" refers to learning content and schedules that are optimized for a learner, and is a plan that is generated taking into account the learner's strengths, weaknesses, interests, and emotional state.

[0614] "Display device" refers to a device that provides learning guidance and feedback to a learner, and examples include tablets, smartphones, and computers.

[0615] "Learning guidance" refers to educational instructions and support given to a learner through a display device, including, for example, specific instructions to encourage the learner to solve a calculation problem.

[0616] "Learning progress" refers to information about the learning activities that a learner has actually performed and the results of those activities, including, for example, the number of problems solved and progress in understanding.

[0617] "Reevaluation" refers to the process of analyzing the suitability of existing learning plans based on learning progress and emotional data, and creating new plans if necessary.

[0618] "Updating" refers to the process of adjusting and revising the learning plan to the latest state based on the results of reevaluation.

[0619] ---

[0620] MODE FOR CARRYING OUT THE INVENTION

[0621] Overall system overview

[0622] The present invention provides a system that allows learners to study independently and reduces the burden on parents. This system consists of a series of processes, including collecting daily activity data and emotional data, generating and adjusting individualized learning plans, providing learning guidance, and updating learning progress and emotional states.

[0623] Data collection methods and means

[0624] First, the user (learner) uses a device to input data about their daily learning activities and interests. This data is called "daily activity data" and specifically includes study diaries, subjects of interest, and actual study time. Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect their current emotional state ("emotional data"). The device then transmits this data to a server at a specified time.

[0625] Methods and means for generating and adjusting lesson plans

[0626] The received data is analyzed by the server, which uses a generative AI model to generate a personalized learning plan optimized for the user based on daily activity data and emotional data. For example, a learning plan can be created by inputting the following prompt sentence into the generative AI model:

[0627] "Please suggest a science lesson plan for my child to complete at home after their math class at school."

[0628] "What is the appropriate lesson plan if the emotion engine detects that my child is tired?"

[0629] The generated lesson plans take into account the learner's strengths, weaknesses, interests, and emotional state, resulting in an efficient and balanced content.

[0630] Methods and means of providing learning plans

[0631] The study plan generated by the server is sent to the device. The device is equipped with an AI chatbot that provides study guidance to the user based on the study plan. For example, it gives instructions such as, "Spend 30 minutes solving math problems today." Furthermore, the chatbot's interactions are adjusted based on emotional data. For example, if the user is tired, it can respond flexibly by offering words of encouragement.

[0632] Learning feedback and plan updates

[0633] As learning progresses, users input their progress and feedback on their learning activities into the device. The device's emotion engine continuously collects the user's emotional data, which is periodically sent to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. Using a generative AI model and emotion data analysis engine, an updated learning plan is generated that adapts to the user's latest interests and emotional state.

[0634] Specific operation example

[0635] For example, one day a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing study plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the study plan, for example, by increasing the time for science experiments or reading. The updated study plan is then sent back to the device. The chatbot on the device then instructs the user, "Let's try a science experiment today." This allows the user to engage in the study that best suits their interests and emotional state that day.

[0636] ---

[0637] The above is an embodiment of the present invention. This system provides effective learning support by considering the learner's interests and emotional state and providing an individualized learning plan. It can also reduce the burden on parents.

[0638] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0639] ---

[0640] Program processing flow

[0641] Step 1: Collecting daily activity and emotion data

[0642] 1-1. Data entry

[0643] Users use the device to input data about their daily learning activities and interests, such as "I spent 30 minutes today doing math problems."

[0644] 1-2. Collecting emotion data

[0645] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotional data. The input is from a camera or microphone, and the analyzed emotional state (e.g., joy, fatigue, concentration, etc.) is obtained as output.

[0646] 1-3. Data transmission

[0647] The device sends the collected daily activity data and emotion data to the server at a specified time. The input is the daily activity data and emotion data, and the output is the data sent to the server.

[0648] Step 2: Generate a lesson plan

[0649] 2-1. Data analysis

[0650] The server analyzes the received daily activity and emotional data and uses a generative AI model to evaluate the learner's strengths, weaknesses, interests, and emotional state based on the input data, thereby creating a user profile as a result of the analysis.

[0651] 2-2. Creating a learning plan

[0652] The server inputs a prompt to the generative AI model to generate a personalized lesson plan, for example, "Please suggest a science lesson plan for my child to complete at home after their math class at school," and outputs the generated lesson plan.

[0653] 2-3. Adjusting your study plan

[0654] Based on the emotion data, the server dynamically adjusts the generated lesson plan. For example, it receives a prompt such as "What lesson plan would be appropriate if the emotion engine detected that my child is tired?" and outputs a lesson plan that matches the child's emotional state.

[0655] Step 3: Provide a learning plan

[0656] 3-1. Submitting your study plan

[0657] The server sends the generated and adjusted training plan to the terminal. The adjusted training plan is the input, and the transmitted training plan is the output.

[0658] 3-2. Implementation of learning guidance

[0659] The AI ​​chatbot on the device will provide guidance to the user based on the learning plan, outputting specific instructions such as "Spend 30 minutes solving math problems today." It will also adjust the chatbot's interactions based on emotional data, offering words of encouragement if the user appears tired.

[0660] Step 4: Learning feedback and plan updates

[0661] 4-1. Entering progress

[0662] The user performs a learning activity and inputs their progress and feedback into the terminal. For example, the terminal outputs the progress status, such as "all calculation problems solved."

[0663] 4-2. Continuous collection of emotional data

[0664] The device's emotion engine continuously collects emotional data during learning, and outputs emotional data such as "my concentration decreased while learning."

[0665] 4-3. Data transmission and analysis

[0666] The terminal sends the collected progress and emotion data to the server, which then reevaluates the data. The input is the progress and emotion data, and the output is the reevaluated information.

[0667] 4-4. Update your study plan

[0668] The server uses the generative AI model and the sentiment data analysis engine to update the lesson plan based on the latest data. For example, it inputs a new prompt sentence into the generative AI model and outputs an updated lesson plan.

[0669] ---

[0670] This is the specific processing flow of the program for this system, which allows learners to engage in optimal learning tailored to their interests and emotional state on that day.

[0671] (Application example 2)

[0672] 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."

[0673] Conventional learning support systems and factory robot work schedule management systems can only provide one-way plans and schedules, and have the problem of being unable to dynamically adjust them to take into account children's emotions and interests, or the robot's work data and emotional state. This makes it difficult to provide efficient learning support and work management that is optimized for individual situations.

[0674] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0675] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to the server, means for generating an individualized learning plan using the received data, means for transmitting the generated learning plan to the terminal, means for the terminal to provide learning guidance to the child based on the learning plan, means for collecting the child's learning progress, means for transmitting the collected learning progress to the server and reevaluating and updating the learning plan, means for collecting work data and emotional data of the factory robot, means for optimizing a work schedule using a generative AI model based on the collected work data and emotional data, and means for transmitting the optimized schedule to the terminal and adjusting the robot's work. This makes it possible to optimize the child's learning plan to suit the interests and emotional state of the day, and to dynamically adjust the factory robot's work schedule based on the work data and emotional data.

[0676] "Daily life data" refers to information about a child's daily activities, specifically including a study diary, study time, and subjects of interest.

[0677] "Server" refers to the computer system that analyzes the collected data and generates personalized learning plans and work schedules.

[0678] "Terminal" refers to a device operated by a user and used to input collected data and present learning instructions.

[0679] A "generative AI model" refers to an artificial intelligence algorithm that generates personalized learning plans and work schedules based on collected data.

[0680] "Emotional data" refers to information that analyzes the emotional state of a user or robot, and specifically includes facial expressions, vocal tone, stress levels, etc.

[0681] "Study Plan" refers to an individualized learning plan created for a child's learning, including specific learning content and schedule.

[0682] A "factory robot" refers to a robot used to automate work in a factory, performing tasks such as welding, assembly, and inspection.

[0683] "Work data" refers to information about the work performed by factory robots, and specifically includes the task ID, task type, required time, etc.

[0684] A "work schedule" refers to a plan for factory robots to work efficiently, and includes specific work orders and break times.

[0685] "Dynamic adjustment" refers to changing and optimizing a child's study plan or a factory robot's work schedule in real time.

[0686] MODE FOR CARRYING OUT THE INVENTION

[0687] Overall system overview

[0688] The system of the present invention supports children's learning and manages the work of factory robots. The system consists of a series of steps: collecting daily life data and emotional data, generating individualized learning plans and work schedules, providing learning guidance and work management, and updating progress and emotional status.

[0689] Data collection methods and means

[0690] The user (child or factory robot) uses a terminal to collect data. In the case of a child, they enter their study diary, subjects of interest, actual study time, etc. into the terminal. In the case of a factory robot, work data such as task ID, task type, and required time is collected. In addition, an emotion engine installed in the terminal analyzes the user's facial expressions and voice tone to collect emotional data. This data is saved by the terminal and sent to the server at a specified time.

[0691] Generate study plans and work schedules

[0692] The server analyzes the received data and generates personalized learning plans and work schedules. Using a generative AI model, it creates a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For factory robots, it also optimizes their work schedules based on the collected work and emotional data. Examples include "perform 30 minutes of math practice every day and two science experiments per week" and "reallocate tasks because the robot is showing high levels of fatigue."

[0693] Providing study plans and work schedules

[0694] The generated learning plan and work schedule are sent to the device, where an AI chatbot or work management application on the device provides instructions to the user. The chatbot can give specific instructions, such as "Solve 30 minutes of math problems today." In the case of factory robots, the system adjusts their work based on the optimized schedule.

[0695] Learning feedback and progress updates

[0696] The user performs learning activities and inputs progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while learning or working. The collected data is periodically sent to the server, which reevaluates the learning plan or work schedule based on the new data and updates it as necessary. The generative AI model and emotion data analysis engine are used to generate an updated plan tailored to new interests and emotional situations.

[0697] Specific operation example

[0698] For example, a child might input into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the child is feeling tired from their facial expression when they input this information. The device then sends this information to the server, which then reevaluates the existing lesson plan. Through the generative AI model and emotion data analysis engine, the server dynamically adjusts the lesson plan, such as increasing time for science experiments or reading, and sends the updated plan back to the device. The chatbot on the device then gives instructions like, "Let's try a science experiment today," allowing the child to engage in learning that suits their interests and emotional state that day.

[0699] Similarly, when a factory robot completes a series of tasks, it sends data such as "Task ID: 1234, Task Type: Welding, Duration: 25 minutes, High Fatigue, Stress Level: Medium" to the server. The server analyzes this data and uses a generative AI model to regenerate an optimal work schedule. This prompt sentence can be used as a sample.

[0700] Example prompt sentence:

[0701] For example, the following prompt is input to the generative AI model:

[0702] The robot completed the following tasks:

[0703] Task ID: 1234

[0704] Task Type: Welding

[0705] Duration: 25 minutes

[0706] Robot emotional state:

[0707] Fatigue level: High

[0708] Stress level: Medium

[0709] Generate a new work schedule.

[0710] This allows for the generation of dynamically optimized schedules based on the emotional state and work data of factory robots, enabling efficient work management of robots.

[0711] Hardware and Software Use Cases

[0712] This system uses the following hardware and software:

[0713] Hardware: User devices (smartphones, tablets, PCs, etc.), factory robots, servers

[0714] Software: Emotion engine (EmotionAnalyzer module), generative AI model (TaskOptimizer module), AI chatbot, work management application

[0715] Combining these features can effectively support users' learning and work management.

[0716] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0717] Step 1:

[0718] The user inputs daily life data and emotional data into the device. The input data includes study diaries, subjects of interest, and study time. In the case of factory robots, work data such as task ID, task type, and required time are collected. In addition, an emotion engine is used to analyze and collect emotional data (facial expressions, voice tone, stress level, etc.) of children and robots. This allows for a detailed understanding of the user's situation and emotional state.

[0719] Input: learning diary, interesting tasks, study time, task ID, task type, time required, emotional data

[0720] Output: Collected daily life data and emotion data

[0721] Step 2:

[0722] The device sends the collected daily life data and emotion data to the server at the specified time. The data is sent using a secure communication protocol (e.g., HTTPS), which ensures the accuracy and confidentiality of the data.

[0723] Input: Collected daily life data and emotional data

[0724] Output: Data sent to the server

[0725] Step 3:

[0726] The server analyzes the received data and generates a personalized learning plan and work schedule. The server uses a generative AI model (e.g., TaskOptimizer module) to create a balanced plan that takes into account the strengths, weaknesses, interests, and emotional state of the child and robot. Machine learning algorithms are used to analyze the data and generate an appropriate plan.

[0727] Input: Data sent to the server

[0728] Output: personalized study plan and work schedule

[0729] Step 4:

[0730] The server sends the generated learning plan and work schedule to the terminal, which receives the data and displays it on the user interface, thereby providing the user with appropriate instructions and schedules.

[0731] Input: Personalized study plan and work schedule

[0732] Output: Data sent to the terminal

[0733] Step 5:

[0734] An AI chatbot or work management application on the device will give instructions to the user. The chatbot will give specific instructions such as "Solve 30 minutes of math problems today" based on the collected learning plan. In the case of a factory robot, it will adjust its work based on an optimized schedule and display instructions such as "Task ID: 1234, please start welding work."

[0735] Input: Data sent to the terminal

[0736] Output: Specific instructions to the user

[0737] Step 6:

[0738] The user performs a learning activity or task and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while they are learning or working, allowing the user's progress and emotional state to be collected in real time.

[0739] Input: Progress and feedback, emotion data

[0740] Output: Collected progress and emotion data

[0741] Step 7:

[0742] The device periodically sends collected progress and emotion data to a server, which reevaluates the learning plan and work schedule based on the new data and updates them as needed. A generative AI model and emotion data analysis engine are used to generate the updated plan.

[0743] Input: Collected progress and emotion data

[0744] Output: Reassessed study plan and work schedule

[0745] Step 8:

[0746] The updated study plan and work schedule are sent to the terminal, and the latest instructions are given to the user again, so that the user can always act based on the optimal study and work plan.

[0747] Input: Reassessed study plan and work schedule

[0748] Output: Update data sent to the device

[0749] This allows a child's learning plan to be optimized to their interests and emotional state on that day, while the work schedule of a factory robot is dynamically adjusted based on work and emotional data.

[0750] 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.

[0751] 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.

[0752] 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.

[0753] [Third embodiment]

[0754] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0755] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0756] 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).

[0757] 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.

[0758] 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.

[0759] 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).

[0760] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0761] 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.

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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."

[0766] MODE FOR CARRYING OUT THE INVENTION

[0767] Overall system overview

[0768] The system of the present invention aims to provide technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting their children's learning. The system consists of a series of steps: collecting daily life data, generating individualized study plans, providing study guidance, and updating study progress.

[0769] Data collection methods and means

[0770] First, the user (child) uses the device to input data about their daily learning activities and areas of interest. For example, they record their learning diary, interesting assignments, actual study time, etc. The device collects this data and sends it to the server in a secure format.

[0771] Methods and means of generating lesson plans

[0772] The received data is analyzed by a server, which then generates a personalized learning plan based on the child's daily life data. Using a generative AI model, the server creates a balanced learning plan that takes into account the child's strengths, weaknesses, and interests. The plan might include 30 minutes of math practice every morning, one science experiment per week, or story reading.

[0773] Methods and means of providing study plans

[0774] The learning plan generated by the server is sent to the device, where an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Let's practice math for 30 minutes today." This allows the child to study independently.

[0775] Learning feedback and plan updates

[0776] The user (child) inputs the progress of learning activities and feedback into the device. For example, they provide feedback such as, "Today's math practice finished on time" or "The science experiment was fun." The device collects this new data and periodically sends it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to be dynamically adjusted to match the child's interests and progress.

[0777] Specific operation example

[0778] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests that day.

[0779] ---

[0780] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan taking into account a child's interests and progress, creating an environment in which children can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[0781] The processing flow will be explained below.

[0782] Program processing steps

[0783] Step 1:

[0784] The user (child) uses the device to input data about their daily learning activities and interests, such as "I solved 10 math problems today" or "I enjoyed the science experiment."

[0785] Step 2:

[0786] The device stores the entered data locally and schedules it to be sent to the server at a specified time, for example, sending daily activity data to the server at 9 PM.

[0787] Step 3:

[0788] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[0789] Step 4:

[0790] The server inputs the received data into a generative AI model, which then generates a personalized learning plan based on the child's learning tendencies and interests, such as "do 30 minutes of math practice every day and two science experiments per week."

[0791] Step 5:

[0792] The server sends the generated learning plan to the terminal, which displays the learning plan in a format that is easy for the user to view.

[0793] Step 6:

[0794] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as "Spend 30 minutes solving math problems today."

[0795] Step 7:

[0796] The user performs learning activities and inputs progress and feedback into the device, for example, recording things like "I solved all the math problems" or "I enjoyed reading."

[0797] Step 8:

[0798] The device stores learning progress data locally and schedules it to be sent to the server periodically, for example, on weekends.

[0799] Step 9:

[0800] The server receives and securely stores the progress data, and formats it for further analysis for review.

[0801] Step 10:

[0802] The server re-evaluates the lesson plan based on new data and updates it as needed, using a generative AI model to generate an updated lesson plan that adapts to the child's new interests and progress.

[0803] Step 11:

[0804] The server sends the updated learning plan to the device, and the AI ​​chatbot again provides learning guidance to the user based on the new learning plan received by the device.

[0805] This is the flow of processing in the system's program. This creates an environment where children can learn in a balanced way while keeping their interest.

[0806] Example 1

[0807] 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."

[0808] Conventional learning support systems for children have had difficulty providing educational plans that fully consider each child's interests and progress. Furthermore, the burden on parents to manage and supervise their children's learning progress is heavy, making it difficult to create an environment in which children can study independently. For this reason, there has been a demand for a balanced, individualized learning plan that children can continue without getting bored.

[0809] 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.

[0810] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to a storage device, means for generating an individualized educational plan using the data received by the storage device, means for transmitting the generated educational plan to a terminal, means for the terminal to provide learning guidance to the user based on the educational plan, means for collecting the user's learning progress, means for transmitting the collected learning progress to the storage device and reevaluating and updating the educational plan, means for analyzing the collected data and learning progress using a generative AI model, and means for generating prompt sentences based on the collected data and learning progress and providing them to the user. This makes it possible to dynamically adjust a balanced learning plan appropriate for each child and provide an environment in which the child can independently engage in learning.

[0811] "Daily life data" refers to personal activity information including a child's daily learning activities, interests, actual study time, etc.

[0812] "Storage device" means digital storage for temporary or permanent storage of collected data.

[0813] An "individualized education plan" is a customized learning schedule and assignments based on each child's interests and learning progress.

[0814] "Devices" refers to digital devices such as tablets and smartphones used by children.

[0815] "User" refers primarily to children who use this system, but may also include their parents in some cases.

[0816] "Learning guidance" refers to educational advice and assignment suggestions provided via the device.

[0817] "Learning progress" refers to the results and feedback of learning activities carried out by a user.

[0818] A "generative AI model" is an artificial intelligence algorithm used to generate useful lesson plans and prompts from user data.

[0819] A "prompt" is a set of instructions or questions that are displayed to gather additional information from the user.

[0820] MODE FOR CARRYING OUT THE INVENTION

[0821] Overall system overview

[0822] The system of the present invention aims to provide technology that enables children to study independently and efficiently support their learning while reducing the burden on parents. This system consists of a series of steps: collecting daily life data, generating individualized learning plans, providing learning guidance, and updating learning progress.

[0823] Data collection methods and means

[0824] First, the user (child) uses a device such as a tablet or smartphone to input data about their daily life. This includes study diaries, subjects of interest, and actual study time. The device collects this data and sends it to the server in a secure format. Data transfer is encrypted using the SSL / TLS protocol.

[0825] Methods and means of generating lesson plans

[0826] The server analyzes the received data using a generative AI model (e.g., an advanced natural language processing model such as GPT-3). The server generates a personalized learning plan taking into account the child's strengths, weaknesses, and areas of interest. The generated learning plan includes such things as "30 minutes of math practice every morning," "one science experiment per week," and "reading a story."

[0827] Methods and means of providing study plans

[0828] The learning plan generated by the server is sent to the device, and learning guidance is provided to the user through an AI chatbot (for example, a conversational AI platform such as Dialogflow) on the device. The AI ​​chatbot gives the user specific instructions such as, "Practice arithmetic for 30 minutes today."

[0829] Learning feedback and plan updates

[0830] Users input their progress and feedback on their learning activities into the device. For example, they provide feedback such as, "I finished today's math practice on time" or "I enjoyed the science experiment." The device collects this new data and securely transmits it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to dynamically adjust to the user's interests and progress.

[0831] Specific operation example

[0832] For example, one day, a user might type into their device, "I had math class at school today, so I'd like to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this additional information into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then gives specific instructions, such as, "Let's try a science experiment today."

[0833] Prompt Sentence Examples

[0834] "What subject are you interested in today?"

[0835] "Please tell me your thoughts about what you learned yesterday."

[0836] "What are your learning goals this week?"

[0837] summary

[0838] The system of the present invention allows children to receive personalized learning plans that reflect their interests and progress, enabling them to study independently. This system plays a role in efficiently supporting children's learning while reducing the burden on parents.

[0839] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0840] Step 1:

[0841] The user inputs daily life data into the device, including study journals, subjects of interest, actual study time, etc. The input data is saved in text and numerical formats.

[0842] Step 2:

[0843] The device sends the collected data to the server. During transmission, the data is encrypted using the SSL / TLS protocol and sent to the server's API endpoint via an HTTP POST request. The input is data from the user, and the output is secure data transmission to the server.

[0844] Step 3:

[0845] The server uses a generative AI model to analyze the data it receives. The received data is passed as input to the generative AI model, which assesses the child's strengths, weaknesses, and areas of interest. The output is a personalized education plan.

[0846] Step 4:

[0847] The server sends the generated personalized education plan to the device. The transmission is again performed using an HTTP POST request, with the data sent in JSON format. The input is the generated education plan, and the output is the data sent to the device.

[0848] Step 5:

[0849] The AI ​​chatbot on the device provides learning guidance to the user based on the educational plan. For example, it may instruct the user, "Let's practice arithmetic for 30 minutes today." The input is the educational plan received from the server, and the output is instructions to the user.

[0850] Step 6:

[0851] After the user has completed the learning activity, they input their progress and feedback into the device. Specifically, they input comments such as "Today's calculation practice finished on time" or "The science experiment was fun." The input is feedback from the user, and the output is the saving of the feedback data on the device.

[0852] Step 7:

[0853] The device sends new data to the server. The transmission method is the same as in step 2, encrypted with the SSL / TLS protocol and using an HTTP POST request. The input is the user's feedback data, and the output is secure data transmission to the server.

[0854] Step 8:

[0855] The server re-evaluates the lesson plan based on new data and updates it as needed using a generative AI model: the input is new feedback data, and the output is an updated instructional plan.

[0856] Step 9:

[0857] The server sends the updated lesson plan to the device. As in step 4, the transmission is done using an HTTP POST request, with the data sent in JSON format. The input is the updated lesson plan, and the output is the data sent to the device.

[0858] Step 10:

[0859] The AI ​​chatbot on the device provides the user with further learning guidance based on the updated learning plan. For example, it might instruct the user, "Spend 15 minutes today practicing your English pronunciation." The input is the updated plan, and the output is instructions to the user.

[0860] (Application example 1)

[0861] 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."

[0862] Conventional factory robot maintenance is based on a periodic maintenance schedule, which makes it difficult to perform optimal maintenance based on the operating status and frequency of use of each robot. This results in cases of excessive maintenance or, conversely, a lack of necessary maintenance, hindering efficient operation. Another issue is that maintenance is concentrated in specific work areas, resulting in unnecessary resource consumption and reduced productivity.

[0863] 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.

[0864] In this invention, the server includes a means for generating an individualized maintenance plan, a means for transmitting the generated maintenance plan to the terminal, and a means for the terminal to provide management guidance to the robot based on the maintenance plan, thereby enabling efficient and balanced maintenance according to the operating status of the robot.

[0865] "Daily data" refers to information about the tasks and operating status that robots perform on a daily basis.

[0866] "Means of collection" refers to the means of acquiring daily data using various sensors and data acquisition devices.

[0867] The "means for transmitting to the server" refers to a means for transferring the collected data to the server via a network.

[0868] "Individualized maintenance plans" involve generating a maintenance schedule optimized for a specific robot based on collected data.

[0869] "Generating means" refers to the algorithms and processes used to analyze data and create personalized maintenance plans.

[0870] The "means for transmitting to the terminal" is a means for transferring the generated maintenance plan to a terminal in the factory.

[0871] "Means for providing management guidance" refers to providing specific maintenance instructions to the robot through an application installed on the terminal or an AI chatbot.

[0872] "Operational progress" refers to information regarding the robot's work progress and operating status.

[0873] "Re-evaluation and update measures" means the algorithms and processes used to re-evaluate and, if necessary, update the maintenance plan based on collected operational progress data.

[0874] A "work domain" refers to a specific work category or task that a robot will undertake.

[0875] A "balancing measure" is a measure to adjust the maintenance plan so that it does not favor any particular area of ​​work.

[0876] "Means for dynamic adjustment" refers to the means for updating the maintenance plan in real time based on the most recent data collected.

[0877] MODE FOR CARRYING OUT THE INVENTION

[0878] Overall system overview

[0879] The system of the present invention provides technology to support the efficient maintenance of factory robots, and aims to maximize the operational efficiency of robots by collecting daily robot data and generating and providing individualized maintenance plans based on this data. This system consists of a series of processes: data collection, maintenance plan generation, management guidance, and feedback on operational progress.

[0880] Data collection methods and means

[0881] The user (factory manager) automatically collects daily data from the robot using various sensors attached to the robot. This data includes work performance, operating hours, number of errors, etc. The collected data is sent to a server via a wireless communication module.

[0882] Methods and means of generating maintenance plans

[0883] The server analyzes the data it receives and uses a generative AI model to generate a personalized maintenance plan based on the collected daily data, such as adding lubricants to increase uptime or inspecting specific parts to reduce the number of errors.

[0884] Methods and means of providing maintenance plans

[0885] The generated maintenance plan is sent to the terminal, where an AI chatbot is installed, which provides specific maintenance instructions to the robot, such as "Add lubricant today" or "Inspect specific parts."

[0886] Feedback on operational progress and plan updates

[0887] The user (factory manager) enters the progress of maintenance work and feedback into the terminal. For example, they enter information such as "lubricant added" or "component inspection completed." The terminal collects this new data and sends it to the server. The server reevaluates and updates the maintenance plan based on the new data. This enables flexible maintenance according to the robot's operating status and progress.

[0888] Specific operation example

[0889] For example, if a robot processes 1,200 parts, operates for eight hours, and encounters two errors as operational data for a given day, this data is sent to the server. The server uses a generative AI model to generate an appropriate maintenance plan based on this information. A plan containing specific details, such as "Today's maintenance plan: Add lubricant and diagnose specific parts for errors," is sent to the device. The device's AI chatbot can then instruct the robot, saying, "Today, add lubricant and diagnose parts for errors."

[0890] Prompt Sentence Examples

[0891] "Please generate a maintenance plan for Robot 001. Today, the number of operations is 1200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps."

[0892] In this way, efficient maintenance and management of factory robots can be achieved through specific operation processes.

[0893] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0894] Program processing flow

[0895] Step 1: Data collection

[0896] Input: Daily data of the robot (work performance, operating hours, number of errors, etc.)

[0897] Output: Collected data is sent to the server

[0898] The user collects daily data from factory robots. Various sensors acquire operational data, and the information is temporarily stored on a local server. The data consists of work results (e.g., processing 1,200 parts), operating time (e.g., 8 hours), number of errors (e.g., 2), etc. This collected data is sent to the cloud server via a wireless communication module.

[0899] Step 2: Data analysis and maintenance plan generation

[0900] Input: Daily data received by the server

[0901] Output: Individualized maintenance plan

[0902] The server analyzes the received data and uses a generative AI model to generate an individualized maintenance plan. For example, the server uses a data analysis engine to generate prompts based on the collected data. The prompt might read, "Generate a maintenance plan for robot 001. Today's operations are 1,200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps." The AI ​​then creates a maintenance plan, which might include adding lubricants or diagnosing errors in specific parts.

[0903] Step 3: Submit your maintenance plan

[0904] Input: Generated maintenance plan

[0905] Output: Maintenance plan sent to the device

[0906] The generated maintenance plan is sent from the server to the terminal at the factory. At this time, the management application installed on the terminal starts up and prepares to receive the maintenance plan. The server uses a transmission protocol to send the data to the terminal safely and with high accuracy.

[0907] Step 4: Implementing maintenance instructions

[0908] Input: Maintenance plan sent to the device

[0909] Output: Specific maintenance instructions for the robot

[0910] The AI ​​chatbot on the terminal then issues specific maintenance instructions to the robot based on the generated maintenance plan. These instructions might include, for example, "Today, please add lubricant and perform an error diagnosis." The robot manager then performs the maintenance work according to these instructions.

[0911] Step 5: Feedback on operational progress

[0912] Input: Maintenance work completion status and feedback

[0913] Output: Feedback data

[0914] The user inputs the completion status of the maintenance work and other feedback into the terminal. For example, information such as "Lubricant added" or "Part inspection completed" is input. This feedback data is sent from the terminal to the server.

[0915] Step 6: Reevaluate and renew your maintenance plan

[0916] Input: Collected feedback data

[0917] Output: Updated maintenance plan

[0918] The server analyzes the feedback data and re-evaluates the maintenance plan, potentially using the generative AI model again to generate and update a new maintenance plan based on the latest data, further optimizing future maintenance.

[0919] The above processing steps enable efficient and flexible maintenance and management of factory robots.

[0920] 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.

[0921] MODE FOR CARRYING OUT THE INVENTION

[0922] Overall system overview

[0923] The system of the present invention provides technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting children's learning. The system consists of a series of steps: collecting daily life data and emotional data, generating and adjusting individualized study plans, providing study guidance, and updating study progress and emotional status.

[0924] Data collection methods and means

[0925] First, the user (child) uses the device to input data about their daily learning activities and interests. For example, they record their learning diary, subjects they are interested in, and actual study time on the device. The device's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This data is saved by the device and sent to the server at a specified time.

[0926] Methods and means for generating and adjusting lesson plans

[0927] The received data is analyzed by a server, which generates a personalized learning plan based on the child's daily life and emotional data. A generative AI model is used to create a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For example, "do 30 minutes of math practice every day and two science experiments per week." The plan is adjusted based on the collected emotional data and is designed to make learning fun.

[0928] Methods and means of providing study plans

[0929] The learning plan generated by the server is sent to the device, and an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Spend 30 minutes solving math problems today." The chatbot's interaction methods are also adjusted based on emotional data. If the child seems tired, it can respond flexibly, such as offering words of encouragement.

[0930] Learning feedback and plan updates

[0931] The user completes the learning activity and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data during the learning process. For example, it tracks feedback such as "I solved all the math problems" or "I enjoyed the science experiment," as well as emotions such as "I lost concentration while learning."

[0932] The device collects this data and periodically sends it to a server, which reevaluates the lesson plan based on the new data and updates it as needed. Using a generative AI model and an emotional data analysis engine, the server generates an updated lesson plan tailored to the child's new interests and emotional state.

[0933] Specific operation example

[0934] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing lesson plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests and emotional state that day.

[0935] ---

[0936] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan that takes into account the child's interests and emotional state, creating an environment in which the child can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[0937] The processing flow will be explained below.

[0938] Program processing steps

[0939] Step 1:

[0940] The user (child) uses the device to input data about their daily learning activities and interests. For example, the device records information such as "I did a science experiment today" and stores it on the device.

[0941] Step 2:

[0942] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotion data, for example, whether the user is smiling or tired, and records the emotion data in real time.

[0943] Step 3:

[0944] The device stores the collected learning activity data and emotion data locally and sets a schedule for sending them to the server at a specified time (e.g., 9 p.m. every day).

[0945] Step 4:

[0946] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[0947] Step 5:

[0948] The server inputs the received data into a generative AI model and an emotional data analysis engine, which then generates a personalized learning plan based on the child's learning tendencies, interests, and emotional state. For example, it creates a plan that includes 30 minutes of math practice every day and two science experiments per week.

[0949] Step 6:

[0950] The server sends the generated learning plan to the device, which receives it and displays it in an easy-to-read format for the user.

[0951] Step 7:

[0952] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as, "Let's smile and do our best on the science experiment today."

[0953] Step 8:

[0954] The user performs a learning activity and inputs progress and feedback into the device. For example, feedback such as "Today's science experiment was fun" or "I'm a little tired" is recorded.

[0955] Step 9:

[0956] The emotion engine continuously collects emotional data from users while they are learning, and if a user becomes tired or loses concentration, it collects that information in real time.

[0957] Step 10:

[0958] The device stores the collected progress and emotion data locally and schedules it to send it to the server periodically (e.g., on weekends).

[0959] Step 11:

[0960] The server receives and securely stores new data sent by the device, and prepares the received data in an analytic format for further evaluation.

[0961] Step 12:

[0962] The server reevaluates the lesson plan based on the new data and updates it as necessary. Using a generative AI model and an emotional data analysis engine, the system generates an updated lesson plan tailored to the child's new interests and emotional state. For example, if the user is feeling tired, it will recommend a gentler task to reduce strain.

[0963] Step 13:

[0964] The server sends the updated study plan to the device. Based on the new study plan received by the device, the AI ​​chatbot again provides study guidance to the user. The chatbot gives instructions such as, "Set aside some time to read something relaxing today."

[0965] ---

[0966] This is the flow of processing in the program of the system that combines the emotion engine. This processing takes into account the child's interests and emotional state, providing a balanced, individualized learning plan and creating an environment in which the child can learn independently.

[0967] Example 2

[0968] 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."

[0969] In modern education, there is a lack of technology that allows children to study independently. This increases the burden on parents and makes it difficult to provide effective learning support. It is also difficult to generate individually customized learning plans and dynamically adjust them based on the child's interests and emotional state. To solve this problem, a system is needed that effectively utilizes learner data and continues to provide individualized learning plans.

[0970] 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.

[0971] In this invention, the server includes means for collecting daily activity data and emotional data, means for transmitting the collected data to an information processing device, means for generating an individualized learning plan using the data received by the information processing device, means for transmitting the generated learning plan to a display device, means for the display device to provide learning guidance based on the learning plan, means for collecting the learning progress of the learner, and means for transmitting the collected learning progress and emotional data to the information processing device and reevaluating and updating the learning plan. This makes it possible to generate and adjust an individualized learning plan according to the child's interests and emotional state.

[0972] "Daily activity data" refers to information about a learner's daily learning activities and interests, including, for example, a learning diary, topics of interest, and actual study time.

[0973] "Emotional data" refers to information that indicates the emotional state of a learner, and includes, for example, emotional states analyzed from changes in facial expressions and vocal tones.

[0974] "Information processing device" refers to a device that has the ability to receive and analyze data and generate, reevaluate, and update personalized learning plans, and generally includes servers and cloud systems.

[0975] An "individualized learning plan" refers to learning content and schedules that are optimized for a learner, and is a plan that is generated taking into account the learner's strengths, weaknesses, interests, and emotional state.

[0976] "Display device" refers to a device that provides learning guidance and feedback to a learner, and examples include tablets, smartphones, and computers.

[0977] "Learning guidance" refers to educational instructions and support given to a learner through a display device, including, for example, specific instructions to encourage the learner to solve a calculation problem.

[0978] "Learning progress" refers to information about the learning activities that a learner has actually performed and the results of those activities, including, for example, the number of problems solved and progress in understanding.

[0979] "Reevaluation" refers to the process of analyzing the suitability of existing learning plans based on learning progress and emotional data, and creating new plans if necessary.

[0980] "Updating" refers to the process of adjusting and revising the learning plan to the latest state based on the results of reevaluation.

[0981] ---

[0982] MODE FOR CARRYING OUT THE INVENTION

[0983] Overall system overview

[0984] The present invention provides a system that allows learners to study independently and reduces the burden on parents. This system consists of a series of processes, including collecting daily activity data and emotional data, generating and adjusting individualized learning plans, providing learning guidance, and updating learning progress and emotional states.

[0985] Data collection methods and means

[0986] First, the user (learner) uses a device to input data about their daily learning activities and interests. This data is called "daily activity data" and specifically includes study diaries, subjects of interest, and actual study time. Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect their current emotional state ("emotional data"). The device then transmits this data to a server at a specified time.

[0987] Methods and means for generating and adjusting lesson plans

[0988] The received data is analyzed by the server, which uses a generative AI model to generate a personalized learning plan optimized for the user based on daily activity data and emotional data. For example, a learning plan can be created by inputting the following prompt sentence into the generative AI model:

[0989] "Please suggest a science lesson plan for my child to complete at home after their math class at school."

[0990] "What is the appropriate lesson plan if the emotion engine detects that my child is tired?"

[0991] The generated lesson plans take into account the learner's strengths, weaknesses, interests, and emotional state, resulting in an efficient and balanced content.

[0992] Methods and means of providing learning plans

[0993] The study plan generated by the server is sent to the device. The device is equipped with an AI chatbot that provides study guidance to the user based on the study plan. For example, it gives instructions such as, "Spend 30 minutes solving math problems today." Furthermore, the chatbot's interactions are adjusted based on emotional data. For example, if the user is tired, it can respond flexibly by offering words of encouragement.

[0994] Learning feedback and plan updates

[0995] As learning progresses, users input their progress and feedback on their learning activities into the device. The device's emotion engine continuously collects the user's emotional data, which is periodically sent to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. Using a generative AI model and emotion data analysis engine, an updated learning plan is generated that adapts to the user's latest interests and emotional state.

[0996] Specific operation example

[0997] For example, one day a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing study plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the study plan, for example, by increasing the time for science experiments or reading. The updated study plan is then sent back to the device. The chatbot on the device then instructs the user, "Let's try a science experiment today." This allows the user to engage in the study that best suits their interests and emotional state that day.

[0998] ---

[0999] The above is an embodiment of the present invention. This system provides effective learning support by considering the learner's interests and emotional state and providing an individualized learning plan. It can also reduce the burden on parents.

[1000] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1001] ---

[1002] Program processing flow

[1003] Step 1: Collecting daily activity and emotion data

[1004] 1-1. Data entry

[1005] Users use the device to input data about their daily learning activities and interests, such as "I spent 30 minutes today doing math problems."

[1006] 1-2. Collecting emotion data

[1007] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotional data. The input is from a camera or microphone, and the analyzed emotional state (e.g., joy, fatigue, concentration, etc.) is obtained as output.

[1008] 1-3. Data transmission

[1009] The device sends the collected daily activity data and emotion data to the server at a specified time. The input is the daily activity data and emotion data, and the output is the data sent to the server.

[1010] Step 2: Generate a lesson plan

[1011] 2-1. Data analysis

[1012] The server analyzes the received daily activity and emotional data and uses a generative AI model to evaluate the learner's strengths, weaknesses, interests, and emotional state based on the input data, thereby creating a user profile as a result of the analysis.

[1013] 2-2. Creating a learning plan

[1014] The server inputs a prompt to the generative AI model to generate a personalized lesson plan, for example, "Please suggest a science lesson plan for my child to complete at home after their math class at school," and outputs the generated lesson plan.

[1015] 2-3. Adjusting your study plan

[1016] Based on the emotion data, the server dynamically adjusts the generated lesson plan. For example, it receives a prompt such as "What lesson plan would be appropriate if the emotion engine detected that my child is tired?" and outputs a lesson plan that matches the child's emotional state.

[1017] Step 3: Provide a learning plan

[1018] 3-1. Submitting your study plan

[1019] The server sends the generated and adjusted training plan to the terminal. The adjusted training plan is the input, and the transmitted training plan is the output.

[1020] 3-2. Implementation of learning guidance

[1021] The AI ​​chatbot on the device will provide guidance to the user based on the learning plan, outputting specific instructions such as "Spend 30 minutes solving math problems today." It will also adjust the chatbot's interactions based on emotional data, offering words of encouragement if the user appears tired.

[1022] Step 4: Learning feedback and plan updates

[1023] 4-1. Entering progress

[1024] The user performs a learning activity and inputs their progress and feedback into the terminal. For example, the terminal outputs the progress status, such as "all calculation problems solved."

[1025] 4-2. Continuous collection of emotional data

[1026] The device's emotion engine continuously collects emotional data during learning, and outputs emotional data such as "my concentration decreased while learning."

[1027] 4-3. Data transmission and analysis

[1028] The terminal sends the collected progress and emotion data to the server, which then reevaluates the data. The input is the progress and emotion data, and the output is the reevaluated information.

[1029] 4-4. Update your study plan

[1030] The server uses the generative AI model and the sentiment data analysis engine to update the lesson plan based on the latest data. For example, it inputs a new prompt sentence into the generative AI model and outputs an updated lesson plan.

[1031] ---

[1032] This is the specific processing flow of the program for this system, which allows learners to engage in optimal learning tailored to their interests and emotional state on that day.

[1033] (Application example 2)

[1034] 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."

[1035] Conventional learning support systems and factory robot work schedule management systems can only provide one-way plans and schedules, and have the problem of being unable to dynamically adjust them to take into account children's emotions and interests, or the robot's work data and emotional state. This makes it difficult to provide efficient learning support and work management that is optimized for individual situations.

[1036] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1037] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to the server, means for generating an individualized learning plan using the received data, means for transmitting the generated learning plan to the terminal, means for the terminal to provide learning guidance to the child based on the learning plan, means for collecting the child's learning progress, means for transmitting the collected learning progress to the server and reevaluating and updating the learning plan, means for collecting work data and emotional data of the factory robot, means for optimizing a work schedule using a generative AI model based on the collected work data and emotional data, and means for transmitting the optimized schedule to the terminal and adjusting the robot's work. This makes it possible to optimize the child's learning plan to suit the interests and emotional state of the day, and to dynamically adjust the factory robot's work schedule based on the work data and emotional data.

[1038] "Daily life data" refers to information about a child's daily activities, specifically including a study diary, study time, and subjects of interest.

[1039] "Server" refers to the computer system that analyzes the collected data and generates personalized learning plans and work schedules.

[1040] "Terminal" refers to a device operated by a user and used to input collected data and present learning instructions.

[1041] A "generative AI model" refers to an artificial intelligence algorithm that generates personalized learning plans and work schedules based on collected data.

[1042] "Emotional data" refers to information that analyzes the emotional state of a user or robot, and specifically includes facial expressions, vocal tone, stress levels, etc.

[1043] "Study Plan" refers to an individualized learning plan created for a child's learning, including specific learning content and schedule.

[1044] A "factory robot" refers to a robot used to automate work in a factory, performing tasks such as welding, assembly, and inspection.

[1045] "Work data" refers to information about the work performed by factory robots, and specifically includes the task ID, task type, required time, etc.

[1046] A "work schedule" refers to a plan for factory robots to work efficiently, and includes specific work orders and break times.

[1047] "Dynamic adjustment" refers to changing and optimizing a child's study plan or a factory robot's work schedule in real time.

[1048] MODE FOR CARRYING OUT THE INVENTION

[1049] Overall system overview

[1050] The system of the present invention supports children's learning and manages the work of factory robots. The system consists of a series of steps: collecting daily life data and emotional data, generating individualized learning plans and work schedules, providing learning guidance and work management, and updating progress and emotional status.

[1051] Data collection methods and means

[1052] The user (child or factory robot) uses a terminal to collect data. In the case of a child, they enter their study diary, subjects of interest, actual study time, etc. into the terminal. In the case of a factory robot, work data such as task ID, task type, and required time is collected. In addition, an emotion engine installed in the terminal analyzes the user's facial expressions and voice tone to collect emotional data. This data is saved by the terminal and sent to the server at a specified time.

[1053] Generate study plans and work schedules

[1054] The server analyzes the received data and generates personalized learning plans and work schedules. Using a generative AI model, it creates a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For factory robots, it also optimizes their work schedules based on the collected work and emotional data. Examples include "perform 30 minutes of math practice every day and two science experiments per week" and "reallocate tasks because the robot is showing high levels of fatigue."

[1055] Providing study plans and work schedules

[1056] The generated learning plan and work schedule are sent to the device, where an AI chatbot or work management application on the device provides instructions to the user. The chatbot can give specific instructions, such as "Solve 30 minutes of math problems today." In the case of factory robots, the system adjusts their work based on the optimized schedule.

[1057] Learning feedback and progress updates

[1058] The user performs learning activities and inputs progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while learning or working. The collected data is periodically sent to the server, which reevaluates the learning plan or work schedule based on the new data and updates it as necessary. The generative AI model and emotion data analysis engine are used to generate an updated plan tailored to new interests and emotional situations.

[1059] Specific operation example

[1060] For example, a child might input into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the child is feeling tired from their facial expression when they input this information. The device then sends this information to the server, which then reevaluates the existing lesson plan. Through the generative AI model and emotion data analysis engine, the server dynamically adjusts the lesson plan, such as increasing time for science experiments or reading, and sends the updated plan back to the device. The chatbot on the device then gives instructions like, "Let's try a science experiment today," allowing the child to engage in learning that suits their interests and emotional state that day.

[1061] Similarly, when a factory robot completes a series of tasks, it sends data such as "Task ID: 1234, Task Type: Welding, Duration: 25 minutes, High Fatigue, Stress Level: Medium" to the server. The server analyzes this data and uses a generative AI model to regenerate an optimal work schedule. This prompt sentence can be used as a sample.

[1062] Example prompt sentence:

[1063] For example, the following prompt is input to the generative AI model:

[1064] The robot completed the following tasks:

[1065] Task ID: 1234

[1066] Task Type: Welding

[1067] Duration: 25 minutes

[1068] Robot emotional state:

[1069] Fatigue level: High

[1070] Stress level: Medium

[1071] Generate a new work schedule.

[1072] This allows for the generation of dynamically optimized schedules based on the emotional state and work data of factory robots, enabling efficient work management of robots.

[1073] Hardware and Software Use Cases

[1074] This system uses the following hardware and software:

[1075] Hardware: User devices (smartphones, tablets, PCs, etc.), factory robots, servers

[1076] Software: Emotion engine (EmotionAnalyzer module), generative AI model (TaskOptimizer module), AI chatbot, work management application

[1077] Combining these features can effectively support users' learning and work management.

[1078] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1079] Step 1:

[1080] The user inputs daily life data and emotional data into the device. The input data includes study diaries, subjects of interest, and study time. In the case of factory robots, work data such as task ID, task type, and required time are collected. In addition, an emotion engine is used to analyze and collect emotional data (facial expressions, voice tone, stress level, etc.) of children and robots. This allows for a detailed understanding of the user's situation and emotional state.

[1081] Input: learning diary, interesting tasks, study time, task ID, task type, time required, emotional data

[1082] Output: Collected daily life data and emotion data

[1083] Step 2:

[1084] The device sends the collected daily life data and emotion data to the server at the specified time. The data is sent using a secure communication protocol (e.g., HTTPS), which ensures the accuracy and confidentiality of the data.

[1085] Input: Collected daily life data and emotional data

[1086] Output: Data sent to the server

[1087] Step 3:

[1088] The server analyzes the received data and generates a personalized learning plan and work schedule. The server uses a generative AI model (e.g., TaskOptimizer module) to create a balanced plan that takes into account the strengths, weaknesses, interests, and emotional state of the child and robot. Machine learning algorithms are used to analyze the data and generate an appropriate plan.

[1089] Input: Data sent to the server

[1090] Output: personalized study plan and work schedule

[1091] Step 4:

[1092] The server sends the generated learning plan and work schedule to the terminal, which receives the data and displays it on the user interface, thereby providing the user with appropriate instructions and schedules.

[1093] Input: Personalized study plan and work schedule

[1094] Output: Data sent to the terminal

[1095] Step 5:

[1096] An AI chatbot or work management application on the device will give instructions to the user. The chatbot will give specific instructions such as "Solve 30 minutes of math problems today" based on the collected learning plan. In the case of a factory robot, it will adjust its work based on an optimized schedule and display instructions such as "Task ID: 1234, please start welding work."

[1097] Input: Data sent to the terminal

[1098] Output: Specific instructions to the user

[1099] Step 6:

[1100] The user performs a learning activity or task and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while they are learning or working, allowing the user's progress and emotional state to be collected in real time.

[1101] Input: Progress and feedback, emotion data

[1102] Output: Collected progress and emotion data

[1103] Step 7:

[1104] The device periodically sends collected progress and emotion data to a server, which reevaluates the learning plan and work schedule based on the new data and updates them as needed. A generative AI model and emotion data analysis engine are used to generate the updated plan.

[1105] Input: Collected progress and emotion data

[1106] Output: Reassessed study plan and work schedule

[1107] Step 8:

[1108] The updated study plan and work schedule are sent to the terminal, and the latest instructions are given to the user again, so that the user can always act based on the optimal study and work plan.

[1109] Input: Reassessed study plan and work schedule

[1110] Output: Update data sent to the device

[1111] This allows a child's learning plan to be optimized to their interests and emotional state on that day, while the work schedule of a factory robot is dynamically adjusted based on work and emotional data.

[1112] 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.

[1113] 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.

[1114] 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.

[1115] [Fourth embodiment]

[1116] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1117] 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.

[1118] 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).

[1119] 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.

[1120] 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.

[1121] 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).

[1122] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1123] 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.

[1124] 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.

[1125] 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.

[1126] 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.

[1127] 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.

[1128] 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."

[1129] MODE FOR CARRYING OUT THE INVENTION

[1130] Overall system overview

[1131] The system of the present invention aims to provide technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting their children's learning. The system consists of a series of steps: collecting daily life data, generating individualized study plans, providing study guidance, and updating study progress.

[1132] Data collection methods and means

[1133] First, the user (child) uses the device to input data about their daily learning activities and areas of interest. For example, they record their learning diary, interesting assignments, actual study time, etc. The device collects this data and sends it to the server in a secure format.

[1134] Methods and means of generating lesson plans

[1135] The received data is analyzed by a server, which then generates a personalized learning plan based on the child's daily life data. Using a generative AI model, the server creates a balanced learning plan that takes into account the child's strengths, weaknesses, and interests. The plan might include 30 minutes of math practice every morning, one science experiment per week, or story reading.

[1136] Methods and means of providing study plans

[1137] The learning plan generated by the server is sent to the device, where an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Let's practice math for 30 minutes today." This allows the child to study independently.

[1138] Learning feedback and plan updates

[1139] The user (child) inputs the progress of learning activities and feedback into the device. For example, they provide feedback such as, "Today's math practice finished on time" or "The science experiment was fun." The device collects this new data and periodically sends it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to be dynamically adjusted to match the child's interests and progress.

[1140] Specific operation example

[1141] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests that day.

[1142] ---

[1143] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan taking into account a child's interests and progress, creating an environment in which children can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[1144] The processing flow will be explained below.

[1145] Program processing steps

[1146] Step 1:

[1147] The user (child) uses the device to input data about their daily learning activities and interests, such as "I solved 10 math problems today" or "I enjoyed the science experiment."

[1148] Step 2:

[1149] The device stores the entered data locally and schedules it to be sent to the server at a specified time, for example, sending daily activity data to the server at 9 PM.

[1150] Step 3:

[1151] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[1152] Step 4:

[1153] The server inputs the received data into a generative AI model, which then generates a personalized learning plan based on the child's learning tendencies and interests, such as "do 30 minutes of math practice every day and two science experiments per week."

[1154] Step 5:

[1155] The server sends the generated learning plan to the terminal, which displays the learning plan in a format that is easy for the user to view.

[1156] Step 6:

[1157] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as "Spend 30 minutes solving math problems today."

[1158] Step 7:

[1159] The user performs learning activities and inputs progress and feedback into the device, for example, recording things like "I solved all the math problems" or "I enjoyed reading."

[1160] Step 8:

[1161] The device stores learning progress data locally and schedules it to be sent to the server periodically, for example, on weekends.

[1162] Step 9:

[1163] The server receives and securely stores the progress data, and formats it for further analysis for review.

[1164] Step 10:

[1165] The server re-evaluates the lesson plan based on new data and updates it as needed, using a generative AI model to generate an updated lesson plan that adapts to the child's new interests and progress.

[1166] Step 11:

[1167] The server sends the updated learning plan to the device, and the AI ​​chatbot again provides learning guidance to the user based on the new learning plan received by the device.

[1168] This is the flow of processing in the system's program. This creates an environment where children can learn in a balanced way while keeping their interest.

[1169] Example 1

[1170] 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."

[1171] Conventional learning support systems for children have had difficulty providing educational plans that fully consider each child's interests and progress. Furthermore, the burden on parents to manage and supervise their children's learning progress is heavy, making it difficult to create an environment in which children can study independently. For this reason, there has been a demand for a balanced, individualized learning plan that children can continue without getting bored.

[1172] 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.

[1173] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to a storage device, means for generating an individualized educational plan using the data received by the storage device, means for transmitting the generated educational plan to a terminal, means for the terminal to provide learning guidance to the user based on the educational plan, means for collecting the user's learning progress, means for transmitting the collected learning progress to the storage device and reevaluating and updating the educational plan, means for analyzing the collected data and learning progress using a generative AI model, and means for generating prompt sentences based on the collected data and learning progress and providing them to the user. This makes it possible to dynamically adjust a balanced learning plan appropriate for each child and provide an environment in which the child can independently engage in learning.

[1174] "Daily life data" refers to personal activity information including a child's daily learning activities, interests, actual study time, etc.

[1175] "Storage device" means digital storage for temporary or permanent storage of collected data.

[1176] An "individualized education plan" is a customized learning schedule and assignments based on each child's interests and learning progress.

[1177] "Devices" refers to digital devices such as tablets and smartphones used by children.

[1178] "User" refers primarily to children who use this system, but may also include their parents in some cases.

[1179] "Learning guidance" refers to educational advice and assignment suggestions provided via the device.

[1180] "Learning progress" refers to the results and feedback of learning activities carried out by a user.

[1181] A "generative AI model" is an artificial intelligence algorithm used to generate useful lesson plans and prompts from user data.

[1182] A "prompt" is a set of instructions or questions that are displayed to gather additional information from the user.

[1183] MODE FOR CARRYING OUT THE INVENTION

[1184] Overall system overview

[1185] The system of the present invention aims to provide technology that enables children to study independently and efficiently support their learning while reducing the burden on parents. This system consists of a series of steps: collecting daily life data, generating individualized learning plans, providing learning guidance, and updating learning progress.

[1186] Data collection methods and means

[1187] First, the user (child) uses a device such as a tablet or smartphone to input data about their daily life. This includes study diaries, subjects of interest, and actual study time. The device collects this data and sends it to the server in a secure format. Data transfer is encrypted using the SSL / TLS protocol.

[1188] Methods and means of generating lesson plans

[1189] The server analyzes the received data using a generative AI model (e.g., an advanced natural language processing model such as GPT-3). The server generates a personalized learning plan taking into account the child's strengths, weaknesses, and areas of interest. The generated learning plan includes such things as "30 minutes of math practice every morning," "one science experiment per week," and "reading a story."

[1190] Methods and means of providing study plans

[1191] The learning plan generated by the server is sent to the device, and learning guidance is provided to the user through an AI chatbot (for example, a conversational AI platform such as Dialogflow) on the device. The AI ​​chatbot gives the user specific instructions such as, "Practice arithmetic for 30 minutes today."

[1192] Learning feedback and plan updates

[1193] Users input their progress and feedback on their learning activities into the device. For example, they provide feedback such as, "I finished today's math practice on time" or "I enjoyed the science experiment." The device collects this new data and securely transmits it to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. This allows the learning plan to dynamically adjust to the user's interests and progress.

[1194] Specific operation example

[1195] For example, one day, a user might type into their device, "I had math class at school today, so I'd like to study science at home." The device sends this information to the server, which reevaluates the existing lesson plan. The generative AI model takes this additional information into account and dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then gives specific instructions, such as, "Let's try a science experiment today."

[1196] Prompt Sentence Examples

[1197] "What subject are you interested in today?"

[1198] "Please tell me your thoughts about what you learned yesterday."

[1199] "What are your learning goals this week?"

[1200] summary

[1201] The system of the present invention allows children to receive personalized learning plans that reflect their interests and progress, enabling them to study independently. This system plays a role in efficiently supporting children's learning while reducing the burden on parents.

[1202] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1203] Step 1:

[1204] The user inputs daily life data into the device, including study journals, subjects of interest, actual study time, etc. The input data is saved in text and numerical formats.

[1205] Step 2:

[1206] The device sends the collected data to the server. During transmission, the data is encrypted using the SSL / TLS protocol and sent to the server's API endpoint via an HTTP POST request. The input is data from the user, and the output is secure data transmission to the server.

[1207] Step 3:

[1208] The server uses a generative AI model to analyze the data it receives. The received data is passed as input to the generative AI model, which assesses the child's strengths, weaknesses, and areas of interest. The output is a personalized education plan.

[1209] Step 4:

[1210] The server sends the generated personalized education plan to the device. The transmission is again performed using an HTTP POST request, with the data sent in JSON format. The input is the generated education plan, and the output is the data sent to the device.

[1211] Step 5:

[1212] The AI ​​chatbot on the device provides learning guidance to the user based on the educational plan. For example, it may instruct the user, "Let's practice arithmetic for 30 minutes today." The input is the educational plan received from the server, and the output is instructions to the user.

[1213] Step 6:

[1214] After the user has completed the learning activity, they input their progress and feedback into the device. Specifically, they input comments such as "Today's calculation practice finished on time" or "The science experiment was fun." The input is feedback from the user, and the output is the saving of the feedback data on the device.

[1215] Step 7:

[1216] The device sends new data to the server. The transmission method is the same as in step 2, encrypted with the SSL / TLS protocol and using an HTTP POST request. The input is the user's feedback data, and the output is secure data transmission to the server.

[1217] Step 8:

[1218] The server re-evaluates the lesson plan based on new data and updates it as needed using a generative AI model: the input is new feedback data, and the output is an updated instructional plan.

[1219] Step 9:

[1220] The server sends the updated lesson plan to the device. As in step 4, the transmission is done using an HTTP POST request, with the data sent in JSON format. The input is the updated lesson plan, and the output is the data sent to the device.

[1221] Step 10:

[1222] The AI ​​chatbot on the device provides the user with further learning guidance based on the updated learning plan. For example, it might instruct the user, "Spend 15 minutes today practicing your English pronunciation." The input is the updated plan, and the output is instructions to the user.

[1223] (Application example 1)

[1224] 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."

[1225] Conventional factory robot maintenance is based on a periodic maintenance schedule, which makes it difficult to perform optimal maintenance based on the operating status and frequency of use of each robot. This results in cases of excessive maintenance or, conversely, a lack of necessary maintenance, hindering efficient operation. Another issue is that maintenance is concentrated in specific work areas, resulting in unnecessary resource consumption and reduced productivity.

[1226] 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.

[1227] In this invention, the server includes a means for generating an individualized maintenance plan, a means for transmitting the generated maintenance plan to the terminal, and a means for the terminal to provide management guidance to the robot based on the maintenance plan, thereby enabling efficient and balanced maintenance according to the operating status of the robot.

[1228] "Daily data" refers to information about the tasks and operating status that robots perform on a daily basis.

[1229] "Means of collection" refers to the means of acquiring daily data using various sensors and data acquisition devices.

[1230] The "means for transmitting to the server" refers to a means for transferring the collected data to the server via a network.

[1231] "Individualized maintenance plans" involve generating a maintenance schedule optimized for a specific robot based on collected data.

[1232] "Generating means" refers to the algorithms and processes used to analyze data and create personalized maintenance plans.

[1233] The "means for transmitting to the terminal" is a means for transferring the generated maintenance plan to a terminal in the factory.

[1234] "Means for providing management guidance" refers to providing specific maintenance instructions to the robot through an application installed on the terminal or an AI chatbot.

[1235] "Operational progress" refers to information regarding the robot's work progress and operating status.

[1236] "Re-evaluation and update measures" means the algorithms and processes used to re-evaluate and, if necessary, update the maintenance plan based on collected operational progress data.

[1237] A "work domain" refers to a specific work category or task that a robot will undertake.

[1238] A "balancing measure" is a measure to adjust the maintenance plan so that it does not favor any particular area of ​​work.

[1239] "Means for dynamic adjustment" refers to the means for updating the maintenance plan in real time based on the most recent data collected.

[1240] MODE FOR CARRYING OUT THE INVENTION

[1241] Overall system overview

[1242] The system of the present invention provides technology to support the efficient maintenance of factory robots, and aims to maximize the operational efficiency of robots by collecting daily robot data and generating and providing individualized maintenance plans based on this data. This system consists of a series of processes: data collection, maintenance plan generation, management guidance, and feedback on operational progress.

[1243] Data collection methods and means

[1244] The user (factory manager) automatically collects daily data from the robot using various sensors attached to the robot. This data includes work performance, operating hours, number of errors, etc. The collected data is sent to a server via a wireless communication module.

[1245] Methods and means of generating maintenance plans

[1246] The server analyzes the data it receives and uses a generative AI model to generate a personalized maintenance plan based on the collected daily data, such as adding lubricants to increase uptime or inspecting specific parts to reduce the number of errors.

[1247] Methods and means of providing maintenance plans

[1248] The generated maintenance plan is sent to the terminal, where an AI chatbot is installed, which provides specific maintenance instructions to the robot, such as "Add lubricant today" or "Inspect specific parts."

[1249] Feedback on operational progress and plan updates

[1250] The user (factory manager) enters the progress of maintenance work and feedback into the terminal. For example, they enter information such as "lubricant added" or "component inspection completed." The terminal collects this new data and sends it to the server. The server reevaluates and updates the maintenance plan based on the new data. This enables flexible maintenance according to the robot's operating status and progress.

[1251] Specific operation example

[1252] For example, if a robot processes 1,200 parts, operates for eight hours, and encounters two errors as operational data for a given day, this data is sent to the server. The server uses a generative AI model to generate an appropriate maintenance plan based on this information. A plan containing specific details, such as "Today's maintenance plan: Add lubricant and diagnose specific parts for errors," is sent to the device. The device's AI chatbot can then instruct the robot, saying, "Today, add lubricant and diagnose parts for errors."

[1253] Prompt Sentence Examples

[1254] "Please generate a maintenance plan for Robot 001. Today, the number of operations is 1200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps."

[1255] In this way, efficient maintenance and management of factory robots can be achieved through specific operation processes.

[1256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1257] Program processing flow

[1258] Step 1: Data collection

[1259] Input: Daily data of the robot (work performance, operating hours, number of errors, etc.)

[1260] Output: Collected data is sent to the server

[1261] The user collects daily data from factory robots. Various sensors acquire operational data, and the information is temporarily stored on a local server. The data consists of work results (e.g., processing 1,200 parts), operating time (e.g., 8 hours), number of errors (e.g., 2), etc. This collected data is sent to the cloud server via a wireless communication module.

[1262] Step 2: Data analysis and maintenance plan generation

[1263] Input: Daily data received by the server

[1264] Output: Individualized maintenance plan

[1265] The server analyzes the received data and uses a generative AI model to generate an individualized maintenance plan. For example, the server uses a data analysis engine to generate prompts based on the collected data. The prompt might read, "Generate a maintenance plan for robot 001. Today's operations are 1,200, the operating time is 8 hours, and the number of errors is 2. Please suggest appropriate maintenance steps." The AI ​​then creates a maintenance plan, which might include adding lubricants or diagnosing errors in specific parts.

[1266] Step 3: Submit your maintenance plan

[1267] Input: Generated maintenance plan

[1268] Output: Maintenance plan sent to the device

[1269] The generated maintenance plan is sent from the server to the terminal at the factory. At this time, the management application installed on the terminal starts up and prepares to receive the maintenance plan. The server uses a transmission protocol to send the data to the terminal safely and with high accuracy.

[1270] Step 4: Implementing maintenance instructions

[1271] Input: Maintenance plan sent to the device

[1272] Output: Specific maintenance instructions for the robot

[1273] The AI ​​chatbot on the terminal then issues specific maintenance instructions to the robot based on the generated maintenance plan. These instructions might include, for example, "Today, please add lubricant and perform an error diagnosis." The robot manager then performs the maintenance work according to these instructions.

[1274] Step 5: Feedback on operational progress

[1275] Input: Maintenance work completion status and feedback

[1276] Output: Feedback data

[1277] The user inputs the completion status of the maintenance work and other feedback into the terminal. For example, information such as "Lubricant added" or "Part inspection completed" is input. This feedback data is sent from the terminal to the server.

[1278] Step 6: Reevaluate and renew your maintenance plan

[1279] Input: Collected feedback data

[1280] Output: Updated maintenance plan

[1281] The server analyzes the feedback data and re-evaluates the maintenance plan, potentially using the generative AI model again to generate and update a new maintenance plan based on the latest data, further optimizing future maintenance.

[1282] The above processing steps enable efficient and flexible maintenance and management of factory robots.

[1283] 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.

[1284] MODE FOR CARRYING OUT THE INVENTION

[1285] Overall system overview

[1286] The system of the present invention provides technology that enables children to study independently, thereby reducing the burden on parents and efficiently supporting children's learning. The system consists of a series of steps: collecting daily life data and emotional data, generating and adjusting individualized study plans, providing study guidance, and updating study progress and emotional status.

[1287] Data collection methods and means

[1288] First, the user (child) uses the device to input data about their daily learning activities and interests. For example, they record their learning diary, subjects they are interested in, and actual study time on the device. The device's emotion engine also analyzes the user's facial expressions and tone of voice to collect emotional data. This data is saved by the device and sent to the server at a specified time.

[1289] Methods and means for generating and adjusting lesson plans

[1290] The received data is analyzed by a server, which generates a personalized learning plan based on the child's daily life and emotional data. A generative AI model is used to create a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For example, "do 30 minutes of math practice every day and two science experiments per week." The plan is adjusted based on the collected emotional data and is designed to make learning fun.

[1291] Methods and means of providing study plans

[1292] The learning plan generated by the server is sent to the device, and an AI chatbot on the device provides learning guidance to the child. The chatbot gives the child specific instructions, such as "Spend 30 minutes solving math problems today." The chatbot's interaction methods are also adjusted based on emotional data. If the child seems tired, it can respond flexibly, such as offering words of encouragement.

[1293] Learning feedback and plan updates

[1294] The user completes the learning activity and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data during the learning process. For example, it tracks feedback such as "I solved all the math problems" or "I enjoyed the science experiment," as well as emotions such as "I lost concentration while learning."

[1295] The device collects this data and periodically sends it to a server, which reevaluates the lesson plan based on the new data and updates it as needed. Using a generative AI model and an emotional data analysis engine, the server generates an updated lesson plan tailored to the child's new interests and emotional state.

[1296] Specific operation example

[1297] For example, one day, a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing lesson plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the lesson plan, such as adding more time for science experiments or reading. The updated lesson plan is then sent back to the device. The chatbot on the device then instructs the child, "Let's try a science experiment today." This allows the child to engage in learning that matches their interests and emotional state that day.

[1298] ---

[1299] The above is an embodiment of the present invention. This system provides a balanced, personalized learning plan that takes into account the child's interests and emotional state, creating an environment in which the child can learn independently. It is possible to efficiently support children's learning while reducing the burden on parents.

[1300] The processing flow will be explained below.

[1301] Program processing steps

[1302] Step 1:

[1303] The user (child) uses the device to input data about their daily learning activities and interests. For example, the device records information such as "I did a science experiment today" and stores it on the device.

[1304] Step 2:

[1305] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotion data, for example, whether the user is smiling or tired, and records the emotion data in real time.

[1306] Step 3:

[1307] The device stores the collected learning activity data and emotion data locally and sets a schedule for sending them to the server at a specified time (e.g., 9 p.m. every day).

[1308] Step 4:

[1309] The server receives the data sent from the device, stores it securely, and formats it for analysis.

[1310] Step 5:

[1311] The server inputs the received data into a generative AI model and an emotional data analysis engine, which then generates a personalized learning plan based on the child's learning tendencies, interests, and emotional state. For example, it creates a plan that includes 30 minutes of math practice every day and two science experiments per week.

[1312] Step 6:

[1313] The server sends the generated learning plan to the device, which receives it and displays it in an easy-to-read format for the user.

[1314] Step 7:

[1315] Based on the learning plan received by the device, the AI ​​chatbot will begin providing learning guidance to the user, for example, giving instructions such as, "Let's smile and do our best on the science experiment today."

[1316] Step 8:

[1317] The user performs a learning activity and inputs progress and feedback into the device. For example, feedback such as "Today's science experiment was fun" or "I'm a little tired" is recorded.

[1318] Step 9:

[1319] The emotion engine continuously collects emotional data from users while they are learning, and if a user becomes tired or loses concentration, it collects that information in real time.

[1320] Step 10:

[1321] The device stores the collected progress and emotion data locally and schedules it to send it to the server periodically (e.g., on weekends).

[1322] Step 11:

[1323] The server receives and securely stores new data sent by the device, and prepares the received data in an analytic format for further evaluation.

[1324] Step 12:

[1325] The server reevaluates the lesson plan based on the new data and updates it as necessary. Using a generative AI model and an emotional data analysis engine, the system generates an updated lesson plan tailored to the child's new interests and emotional state. For example, if the user is feeling tired, it will recommend a gentler task to reduce strain.

[1326] Step 13:

[1327] The server sends the updated study plan to the device. Based on the new study plan received by the device, the AI ​​chatbot again provides study guidance to the user. The chatbot gives instructions such as, "Set aside some time to read something relaxing today."

[1328] ---

[1329] This is the flow of processing in the program of the system that combines the emotion engine. This processing takes into account the child's interests and emotional state, providing a balanced, individualized learning plan and creating an environment in which the child can learn independently.

[1330] Example 2

[1331] 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."

[1332] In modern education, there is a lack of technology that allows children to study independently. This increases the burden on parents and makes it difficult to provide effective learning support. It is also difficult to generate individually customized learning plans and dynamically adjust them based on the child's interests and emotional state. To solve this problem, a system is needed that effectively utilizes learner data and continues to provide individualized learning plans.

[1333] 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.

[1334] In this invention, the server includes means for collecting daily activity data and emotional data, means for transmitting the collected data to an information processing device, means for generating an individualized learning plan using the data received by the information processing device, means for transmitting the generated learning plan to a display device, means for the display device to provide learning guidance based on the learning plan, means for collecting the learning progress of the learner, and means for transmitting the collected learning progress and emotional data to the information processing device and reevaluating and updating the learning plan. This makes it possible to generate and adjust an individualized learning plan according to the child's interests and emotional state.

[1335] "Daily activity data" refers to information about a learner's daily learning activities and interests, including, for example, a learning diary, topics of interest, and actual study time.

[1336] "Emotional data" refers to information that indicates the emotional state of a learner, and includes, for example, emotional states analyzed from changes in facial expressions and vocal tones.

[1337] "Information processing device" refers to a device that has the ability to receive and analyze data and generate, reevaluate, and update personalized learning plans, and generally includes servers and cloud systems.

[1338] An "individualized learning plan" refers to learning content and schedules that are optimized for a learner, and is a plan that is generated taking into account the learner's strengths, weaknesses, interests, and emotional state.

[1339] "Display device" refers to a device that provides learning guidance and feedback to a learner, and examples include tablets, smartphones, and computers.

[1340] "Learning guidance" refers to educational instructions and support given to a learner through a display device, including, for example, specific instructions to encourage the learner to solve a calculation problem.

[1341] "Learning progress" refers to information about the learning activities that a learner has actually performed and the results of those activities, including, for example, the number of problems solved and progress in understanding.

[1342] "Reevaluation" refers to the process of analyzing the suitability of existing learning plans based on learning progress and emotional data, and creating new plans if necessary.

[1343] "Updating" refers to the process of adjusting and revising the learning plan to the latest state based on the results of reevaluation.

[1344] ---

[1345] MODE FOR CARRYING OUT THE INVENTION

[1346] Overall system overview

[1347] The present invention provides a system that allows learners to study independently and reduces the burden on parents. This system consists of a series of processes, including collecting daily activity data and emotional data, generating and adjusting individualized learning plans, providing learning guidance, and updating learning progress and emotional states.

[1348] Data collection methods and means

[1349] First, the user (learner) uses a device to input data about their daily learning activities and interests. This data is called "daily activity data" and specifically includes study diaries, subjects of interest, and actual study time. Furthermore, the device's built-in emotion engine analyzes the user's facial expressions and tone of voice to collect their current emotional state ("emotional data"). The device then transmits this data to a server at a specified time.

[1350] Methods and means for generating and adjusting lesson plans

[1351] The received data is analyzed by the server, which uses a generative AI model to generate a personalized learning plan optimized for the user based on daily activity data and emotional data. For example, a learning plan can be created by inputting the following prompt sentence into the generative AI model:

[1352] "Please suggest a science lesson plan for my child to complete at home after their math class at school."

[1353] "What is the appropriate lesson plan if the emotion engine detects that my child is tired?"

[1354] The generated lesson plans take into account the learner's strengths, weaknesses, interests, and emotional state, resulting in an efficient and balanced content.

[1355] Methods and means of providing learning plans

[1356] The study plan generated by the server is sent to the device. The device is equipped with an AI chatbot that provides study guidance to the user based on the study plan. For example, it gives instructions such as, "Spend 30 minutes solving math problems today." Furthermore, the chatbot's interactions are adjusted based on emotional data. For example, if the user is tired, it can respond flexibly by offering words of encouragement.

[1357] Learning feedback and plan updates

[1358] As learning progresses, users input their progress and feedback on their learning activities into the device. The device's emotion engine continuously collects the user's emotional data, which is periodically sent to the server. The server reevaluates the learning plan based on the new data and updates it as necessary. Using a generative AI model and emotion data analysis engine, an updated learning plan is generated that adapts to the user's latest interests and emotional state.

[1359] Specific operation example

[1360] For example, one day a user might type into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the user is feeling tired from their facial expression when they type this. The device then sends this information to the server, which then reevaluates the existing study plan. Using the generative AI model and the emotion data analysis engine, the server dynamically adjusts the study plan, for example, by increasing the time for science experiments or reading. The updated study plan is then sent back to the device. The chatbot on the device then instructs the user, "Let's try a science experiment today." This allows the user to engage in the study that best suits their interests and emotional state that day.

[1361] ---

[1362] The above is an embodiment of the present invention. This system provides effective learning support by considering the learner's interests and emotional state and providing an individualized learning plan. It can also reduce the burden on parents.

[1363] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1364] ---

[1365] Program processing flow

[1366] Step 1: Collecting daily activity and emotion data

[1367] 1-1. Data entry

[1368] Users use the device to input data about their daily learning activities and interests, such as "I spent 30 minutes today doing math problems."

[1369] 1-2. Collecting emotion data

[1370] The emotion engine installed in the device analyzes the user's facial expressions and voice tone to collect emotional data. The input is from a camera or microphone, and the analyzed emotional state (e.g., joy, fatigue, concentration, etc.) is obtained as output.

[1371] 1-3. Data transmission

[1372] The device sends the collected daily activity data and emotion data to the server at a specified time. The input is the daily activity data and emotion data, and the output is the data sent to the server.

[1373] Step 2: Generate a lesson plan

[1374] 2-1. Data analysis

[1375] The server analyzes the received daily activity and emotional data and uses a generative AI model to evaluate the learner's strengths, weaknesses, interests, and emotional state based on the input data, thereby creating a user profile as a result of the analysis.

[1376] 2-2. Creating a learning plan

[1377] The server inputs a prompt to the generative AI model to generate a personalized lesson plan, for example, "Please suggest a science lesson plan for my child to complete at home after their math class at school," and outputs the generated lesson plan.

[1378] 2-3. Adjusting your study plan

[1379] Based on the emotion data, the server dynamically adjusts the generated lesson plan. For example, it receives a prompt such as "What lesson plan would be appropriate if the emotion engine detected that my child is tired?" and outputs a lesson plan that matches the child's emotional state.

[1380] Step 3: Provide a learning plan

[1381] 3-1. Submitting your study plan

[1382] The server sends the generated and adjusted training plan to the terminal. The adjusted training plan is the input, and the transmitted training plan is the output.

[1383] 3-2. Implementation of learning guidance

[1384] The AI ​​chatbot on the device will provide guidance to the user based on the learning plan, outputting specific instructions such as "Spend 30 minutes solving math problems today." It will also adjust the chatbot's interactions based on emotional data, offering words of encouragement if the user appears tired.

[1385] Step 4: Learning feedback and plan updates

[1386] 4-1. Entering progress

[1387] The user performs a learning activity and inputs their progress and feedback into the terminal. For example, the terminal outputs the progress status, such as "all calculation problems solved."

[1388] 4-2. Continuous collection of emotional data

[1389] The device's emotion engine continuously collects emotional data during learning, and outputs emotional data such as "my concentration decreased while learning."

[1390] 4-3. Data transmission and analysis

[1391] The terminal sends the collected progress and emotion data to the server, which then reevaluates the data. The input is the progress and emotion data, and the output is the reevaluated information.

[1392] 4-4. Update your study plan

[1393] The server uses the generative AI model and the sentiment data analysis engine to update the lesson plan based on the latest data. For example, it inputs a new prompt sentence into the generative AI model and outputs an updated lesson plan.

[1394] ---

[1395] This is the specific processing flow of the program for this system, which allows learners to engage in optimal learning tailored to their interests and emotional state on that day.

[1396] (Application example 2)

[1397] 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."

[1398] Conventional learning support systems and factory robot work schedule management systems can only provide one-way plans and schedules, and have the problem of being unable to dynamically adjust them to take into account children's emotions and interests, or the robot's work data and emotional state. This makes it difficult to provide efficient learning support and work management that is optimized for individual situations.

[1399] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1400] In this invention, the server includes means for collecting daily life data, means for transmitting the collected data to the server, means for generating an individualized learning plan using the received data, means for transmitting the generated learning plan to the terminal, means for the terminal to provide learning guidance to the child based on the learning plan, means for collecting the child's learning progress, means for transmitting the collected learning progress to the server and reevaluating and updating the learning plan, means for collecting work data and emotional data of the factory robot, means for optimizing a work schedule using a generative AI model based on the collected work data and emotional data, and means for transmitting the optimized schedule to the terminal and adjusting the robot's work. This makes it possible to optimize the child's learning plan to suit the interests and emotional state of the day, and to dynamically adjust the factory robot's work schedule based on the work data and emotional data.

[1401] "Daily life data" refers to information about a child's daily activities, specifically including a study diary, study time, and subjects of interest.

[1402] "Server" refers to the computer system that analyzes the collected data and generates personalized learning plans and work schedules.

[1403] "Terminal" refers to a device operated by a user and used to input collected data and present learning instructions.

[1404] A "generative AI model" refers to an artificial intelligence algorithm that generates personalized learning plans and work schedules based on collected data.

[1405] "Emotional data" refers to information that analyzes the emotional state of a user or robot, and specifically includes facial expressions, vocal tone, stress levels, etc.

[1406] "Study Plan" refers to an individualized learning plan created for a child's learning, including specific learning content and schedule.

[1407] A "factory robot" refers to a robot used to automate work in a factory, performing tasks such as welding, assembly, and inspection.

[1408] "Work data" refers to information about the work performed by factory robots, and specifically includes the task ID, task type, required time, etc.

[1409] A "work schedule" refers to a plan for factory robots to work efficiently, and includes specific work orders and break times.

[1410] "Dynamic adjustment" refers to changing and optimizing a child's study plan or a factory robot's work schedule in real time.

[1411] MODE FOR CARRYING OUT THE INVENTION

[1412] Overall system overview

[1413] The system of the present invention supports children's learning and manages the work of factory robots. The system consists of a series of steps: collecting daily life data and emotional data, generating individualized learning plans and work schedules, providing learning guidance and work management, and updating progress and emotional status.

[1414] Data collection methods and means

[1415] The user (child or factory robot) uses a terminal to collect data. In the case of a child, they enter their study diary, subjects of interest, actual study time, etc. into the terminal. In the case of a factory robot, work data such as task ID, task type, and required time is collected. In addition, an emotion engine installed in the terminal analyzes the user's facial expressions and voice tone to collect emotional data. This data is saved by the terminal and sent to the server at a specified time.

[1416] Generate study plans and work schedules

[1417] The server analyzes the received data and generates personalized learning plans and work schedules. Using a generative AI model, it creates a balanced learning plan that takes into account the child's strengths, weaknesses, interests, and emotional state. For factory robots, it also optimizes their work schedules based on the collected work and emotional data. Examples include "perform 30 minutes of math practice every day and two science experiments per week" and "reallocate tasks because the robot is showing high levels of fatigue."

[1418] Providing study plans and work schedules

[1419] The generated learning plan and work schedule are sent to the device, where an AI chatbot or work management application on the device provides instructions to the user. The chatbot can give specific instructions, such as "Solve 30 minutes of math problems today." In the case of factory robots, the system adjusts their work based on the optimized schedule.

[1420] Learning feedback and progress updates

[1421] The user performs learning activities and inputs progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while learning or working. The collected data is periodically sent to the server, which reevaluates the learning plan or work schedule based on the new data and updates it as necessary. The generative AI model and emotion data analysis engine are used to generate an updated plan tailored to new interests and emotional situations.

[1422] Specific operation example

[1423] For example, a child might input into their device, "I had math class at school today, so I want to study science at home." The emotion engine detects that the child is feeling tired from their facial expression when they input this information. The device then sends this information to the server, which then reevaluates the existing lesson plan. Through the generative AI model and emotion data analysis engine, the server dynamically adjusts the lesson plan, such as increasing time for science experiments or reading, and sends the updated plan back to the device. The chatbot on the device then gives instructions like, "Let's try a science experiment today," allowing the child to engage in learning that suits their interests and emotional state that day.

[1424] Similarly, when a factory robot completes a series of tasks, it sends data such as "Task ID: 1234, Task Type: Welding, Duration: 25 minutes, High Fatigue, Stress Level: Medium" to the server. The server analyzes this data and uses a generative AI model to regenerate an optimal work schedule. This prompt sentence can be used as a sample.

[1425] Example prompt sentence:

[1426] For example, the following prompt is input to the generative AI model:

[1427] The robot completed the following tasks:

[1428] Task ID: 1234

[1429] Task Type: Welding

[1430] Duration: 25 minutes

[1431] Robot emotional state:

[1432] Fatigue level: High

[1433] Stress level: Medium

[1434] Generate a new work schedule.

[1435] This allows for the generation of dynamically optimized schedules based on the emotional state and work data of factory robots, enabling efficient work management of robots.

[1436] Hardware and Software Use Cases

[1437] This system uses the following hardware and software:

[1438] Hardware: User devices (smartphones, tablets, PCs, etc.), factory robots, servers

[1439] Software: Emotion engine (EmotionAnalyzer module), generative AI model (TaskOptimizer module), AI chatbot, work management application

[1440] Combining these features can effectively support users' learning and work management.

[1441] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1442] Step 1:

[1443] The user inputs daily life data and emotional data into the device. The input data includes study diaries, subjects of interest, and study time. In the case of factory robots, work data such as task ID, task type, and required time are collected. In addition, an emotion engine is used to analyze and collect emotional data (facial expressions, voice tone, stress level, etc.) of children and robots. This allows for a detailed understanding of the user's situation and emotional state.

[1444] Input: learning diary, interesting tasks, study time, task ID, task type, time required, emotional data

[1445] Output: Collected daily life data and emotion data

[1446] Step 2:

[1447] The device sends the collected daily life data and emotion data to the server at the specified time. The data is sent using a secure communication protocol (e.g., HTTPS), which ensures the accuracy and confidentiality of the data.

[1448] Input: Collected daily life data and emotional data

[1449] Output: Data sent to the server

[1450] Step 3:

[1451] The server analyzes the received data and generates a personalized learning plan and work schedule. The server uses a generative AI model (e.g., TaskOptimizer module) to create a balanced plan that takes into account the strengths, weaknesses, interests, and emotional state of the child and robot. Machine learning algorithms are used to analyze the data and generate an appropriate plan.

[1452] Input: Data sent to the server

[1453] Output: personalized study plan and work schedule

[1454] Step 4:

[1455] The server sends the generated learning plan and work schedule to the terminal, which receives the data and displays it on the user interface, thereby providing the user with appropriate instructions and schedules.

[1456] Input: Personalized study plan and work schedule

[1457] Output: Data sent to the terminal

[1458] Step 5:

[1459] An AI chatbot or work management application on the device will give instructions to the user. The chatbot will give specific instructions such as "Solve 30 minutes of math problems today" based on the collected learning plan. In the case of a factory robot, it will adjust its work based on an optimized schedule and display instructions such as "Task ID: 1234, please start welding work."

[1460] Input: Data sent to the terminal

[1461] Output: Specific instructions to the user

[1462] Step 6:

[1463] The user performs a learning activity or task and inputs their progress and feedback into the device. In addition, the emotion engine continuously collects emotional data while they are learning or working, allowing the user's progress and emotional state to be collected in real time.

[1464] Input: Progress and feedback, emotion data

[1465] Output: Collected progress and emotion data

[1466] Step 7:

[1467] The device periodically sends collected progress and emotion data to a server, which reevaluates the learning plan and work schedule based on the new data and updates them as needed. A generative AI model and emotion data analysis engine are used to generate the updated plan.

[1468] Input: Collected progress and emotion data

[1469] Output: Reassessed study plan and work schedule

[1470] Step 8:

[1471] The updated study plan and work schedule are sent to the terminal, and the latest instructions are given to the user again, so that the user can always act based on the optimal study and work plan.

[1472] Input: Reassessed study plan and work schedule

[1473] Output: Update data sent to the device

[1474] This allows a child's learning plan to be optimized to their interests and emotional state on that day, while the work schedule of a factory robot is dynamically adjusted based on work and emotional data.

[1475] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1476] 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.

[1477] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1478] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1479] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1480] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1481] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1482] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1483] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1484] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1485] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1486] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1487] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1488] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1489] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1490] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1491] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1492] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1493] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1494] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1495] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1496] The following is further disclosed regarding the above embodiment.

[1497] Claims

[1498] (Claim 1)

[1499] a means of collecting daily life data;

[1500] means for transmitting the collected data to a server;

[1501] means for generating a personalized learning plan using the data received by the server;

[1502] A means for transmitting the generated learning plan to the terminal;

[1503] A means for the terminal to provide learning guidance to the child based on the learning plan;

[1504] a means of collecting information on children's learning progress;

[1505] a means for transmitting the collected learning progress to a server and reevaluating and updating the learning plan;

[1506] A system including:

[1507] (Claim 2)

[1508] 2. The system according to claim 1, further comprising means for balancing the generated study plan so that it is not biased toward a particular study area.

[1509] (Claim 3)

[1510] 10. The system of claim 1, further comprising means for dynamically adjusting the learning plan according to the child's interests and progress.

[1511] ---

[1512] The above is a draft of the patent claim for the distinctive parts of the system. If necessary, you can add more detailed functions or unique technical features to establish a more robust patent scope.

[1513] "Example 1"

[1514] (Claim 1)

[1515] a means of collecting daily life data;

[1516] means for transmitting the collected data to a storage device;

[1517] means for generating a personalized education plan using the data received by the storage device;

[1518] means for transmitting the generated training plan to a terminal;

[1519] a means for the terminal to provide learning guidance to the user based on the educational plan;

[1520] means for collecting user learning progress;

[1521] means for transmitting the collected learning progress to a storage device and reevaluating and updating the educational plan;

[1522] a means for analyzing the collected data and learning progress using the generative AI model; and

[1523] means for generating and providing prompt sentences to the user based on the collected data and learning progress;

[1524] A system including:

[1525] (Claim 2)

[1526] 2. The system according to claim 1, further comprising means for balancing the generated study plan so that it is not biased toward a particular study area.

[1527] (Claim 3)

[1528] 10. The system of claim 1, further comprising means for dynamically adjusting the learning plan according to the user's interests and progress.

[1529] "Application Example 1"

[1530] (Claim 1)

[1531] a means of collecting routine data;

[1532] means for transmitting the collected data to a server;

[1533] means for generating a personalized maintenance plan using the data received by the server;

[1534] A means for transmitting the generated maintenance plan to the terminal;

[1535] a means for the terminal to provide management guidance to the robot based on the maintenance plan;

[1536] a means for collecting operational progress information of the robot;

[1537] A means for transmitting the collected operational progress to a server and reevaluating and updating the maintenance plan;

[1538] A system including:

[1539] (Claim 2)

[1540] 2. The system according to claim 1, further comprising means for balancing the generated maintenance plan so that it is not biased towards a particular work area.

[1541] (Claim 3)

[1542] 10. The system of claim 1, further comprising means for dynamically adjusting the maintenance plan according to the interests and progress of the robot.

[1543] "Example 2: Combining Emotion Engines"

[1544] (Claim 1)

[1545] means for collecting daily activity data and emotion data;

[1546] means for transmitting the collected data to an information processing device;

[1547] means for generating an individualized learning plan using the data received by the information processing device;

[1548] means for transmitting the generated lesson plan to a display device;

[1549] A means for the display device to provide learning guidance based on the learning plan;

[1550] a means of collecting information on the learner's learning progress;

[1551] means for transmitting the collected learning progress and emotion data to an information processing device and reevaluating and updating the learning plan;

[1552] A system including:

[1553] (Claim 2)

[1554] 2. The system according to claim 1, further comprising means for balancing the generated learning plan so that it is not biased toward a particular learning field.

[1555] (Claim 3)

[1556] 10. The system of claim 1, further comprising means for dynamically adjusting the learning plan according to the learner's interests and progress.

[1557] "Application example 2 when combining emotion engines"

[1558] (Claim 1)

[1559] a means of collecting daily life data;

[1560] means for transmitting the collected data to a server;

[1561] means for generating a personalized learning plan using the data received by the server;

[1562] A means for transmitting the generated learning plan to the terminal;

[1563] A means for the terminal to provide learning guidance to the child based on the learning plan;

[1564] a means of collecting information on children's learning progress;

[1565] a means for transmitting the collected learning progress to a server and reevaluating and updating the learning plan;

[1566] A means for collecting work data and emotion data of a factory robot;

[1567] A means for optimizing work schedules using a generative AI model based on collected work data and emotion data; and

[1568] a means for transmitting the optimized schedule to a terminal and adjusting the work of the robot;

[1569] A system including:

[1570] (Claim 2)

[1571] 2. The system according to claim 1, further comprising means for balancing the generated study plan so that it is not biased toward a particular study area.

[1572] (Claim 3)

[1573] 10. The system of claim 1, further comprising: means for dynamically adjusting the learning plan according to the child's interests and progress; and means for dynamically adjusting the work schedule according to the emotional state of the factory robot. [Explanation of symbols]

[1574] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting daily life data; means for transmitting the collected data to a server; means for generating a personalized learning plan using the data received by the server; A means for transmitting the generated learning plan to the terminal; A means for the terminal to provide learning guidance to the child based on the learning plan; a means of collecting information on children's learning progress; a means for transmitting the collected learning progress to a server and reevaluating and updating the learning plan; A system including:

2. 2. The system according to claim 1, further comprising means for balancing the generated study plan so that it is not biased toward a particular study field.

3. 10. The system of claim 1, further comprising means for dynamically adjusting the lesson plan according to the child's interests and progress.

Images