System

Abstract

To provide a system capable of efficiently performing learning and a task without missing a deadline of a subject and an important schedule.SOLUTION: A system includes: means for storing registration information pre-registered by a user; means for integrating a function of an interactive machine learning model and extracting information related to a date and time from the stored registration information to set a reminder; and means for providing the related reminder according to a request of the user by a generated AI model.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] In the past, students' assignments, projects, and notebook management methods were scattered, making it difficult to find the information they needed. In addition, they often missed deadlines and important events, making it difficult to study and complete tasks efficiently. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a means for centrally storing students' assignments, projects, and notes in a cloud storage app, and integrating the functions of an interactive machine learning model.

[0006] Specifically, a user can save assignments, projects, and notes in their own database through a cloud storage app, and a generative AI function, as an example of an interactive machine learning model, can extract information about dates and times from the saved database and set reminders for at least one of assignment deadlines, exam dates, and important notes.

[0007] Moreover, users can search and retrieve relevant content from the stored database by sending requests in natural language, helping them find the information they need quickly and enabling them to learn and complete tasks more efficiently.

[0008] By using the above-mentioned means, the present invention can solve the conventional problems by making it more efficient to manage students' assignments, projects, and notes, and by realizing the centralization of information and easy access.

[0009] A "cloud storage app" is an application for centrally storing at least one of a student's assignment, project, and note information.

[0010] “Stored Database” means data that is an aggregate of at least one of student assignment, project, and notebook information that a user has stored in a cloud storage app.

[0011] "Generative AI functionality" refers to a conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0012] "Related content" refers to at least one of student assignment, project, and notebook information related to the user's request.

[0013] The above are definitions of important words included in the claims. [Brief description of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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] 4 is a sequence diagram showing a process flow of the data processing system according to the first embodiment. FIG. [Figure 12] 11 is a sequence diagram showing a process flow of the data processing system in application example 1. FIG. [Figure 13] FIG. 11 is a sequence diagram showing the flow of processing of the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 11 is a sequence diagram showing the flow of processing in the data processing system in application example 2 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

[0022] [First embodiment]

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

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

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

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

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

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

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0031] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

[0034] Next, a description will be given of the 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 a "server" and the smart device 14 will be referred to as a "terminal."

[0035] An embodiment for implementing the present invention includes the following elements.

[0036] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[0037] 2. Database: Where student assignment, project, and / or notebook information is stored.

[0038] 3. Generative AI function as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0039] 4. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[0040] 5. Server: The central processing unit where the cloud storage app, database, and generative AI functions run.

[0041] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, as well as information extraction and support.

[0042] As a concrete example, a user uses a device to access a cloud storage app and saves assignments, projects, and notes in a database. The user then sends a request to a server via the device, and the server extracts relevant information from the saved database and responds to the user's request using generative AI functions. The user receives the response from the server via the device and can obtain the information he or she needs.

[0043] In this way, by combining a cloud storage app, database, generative AI functions, terminals, and servers based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, and to extract and support information.

[0044] The process flow will be explained below.

[0045] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[0046] Step 2: The user sends a request to the server via the terminal.

[0047] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[0048] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[0049] Step 5: The server uses the generative AI capabilities to generate a response that meets the user's request based on the extracted information.

[0050] Step 6: The server sends the generated response to the terminal.

[0051] Step 7: The terminal receives the response from the server and displays it to the user.

[0052] As a specific example, a user uses a terminal to access a cloud storage app and saves math homework in a database (step 1). After that, the user sends a request to a server via the terminal, asking "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Next, the server uses the functions of generative AI to generate a response saying "Tomorrow's math homework is due at 5 p.m." (step 5). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 6 and 7). Note that the response may be output as voice instead of being displayed on the terminal.

[0053] In this way, a user sends a request to a server through a terminal, the server analyzes the request, extracts information from a database, generates a response, and sends the response to the terminal, allowing the user to obtain the information he or she needs.

[0054] Example 1

[0055] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal."

[0056] Conventional education-related information management systems have the problem that information on assignments, projects, and notes is stored in a scattered manner, making efficient management difficult. In addition, the function to remind users of important information such as deadlines and exam dates was insufficient, so users had to take a lot of time and effort to check the information. Furthermore, there was a lack of means to quickly extract the specific information that users were looking for, which resulted in low user convenience.

[0057] 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.

[0058] In this invention, the server includes a means for centrally storing at least one piece of education-related information as an example of pre-registered information in a cloud storage application, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one notification of a deadline, an event date, and an important note as an example of a reminder, and a means for utilizing a generative AI model for searching and extracting related information in response to a user request. This makes it possible to provide an environment in which education-related information can be managed efficiently in a centralized manner and users can check important information such as deadlines and exam dates in a timely manner.

[0059] A "cloud storage application" is an application that centrally stores education-related information on the Internet and allows users to access, manage, and edit information from any device.

[0060] "Education-related information" refers to information including student assignments, projects, notes, and associated time and date information.

[0061] An "interactive machine learning model" is a machine learning model used to extract, analyze, and present information through natural language interactions with a user.

[0062] "Date and time information" refers to date and time information related to assignment deadlines, exam dates, and important notes.

[0063] A "notification" is a means of communication to inform a user of important information (e.g. deadlines or event dates).

[0064] A "generative AI model" is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[0065] "Server" refers to a central processing unit such as a cloud storage application, database, or generative AI model, which processes user requests and provides the necessary information.

[0066] "Database" means a collection of education-related information collected through the Cloud Storage Application that is structured to store, search and retrieve information efficiently.

[0067] A "prompt sentence" refers to a search request or instruction sentence that a user inputs into a cloud storage application using natural language.

[0068] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0069] The present invention is a system that is constructed by elements such as a cloud storage application, education-related information, an interactive machine learning model, information on date and time, notifications, a generative AI model, a server, a database, and prompt sentences, which allows users to efficiently manage education-related information and quickly obtain the information they need.

[0070] 1. System Configuration

[0071] 1.1 Cloud storage applications:

[0072] A cloud storage application is an application that allows users to centrally store educational information on the Internet and access, manage, and edit it from any device. Educational information includes student assignments, projects, notes, and associated time and date information.

[0073] 1.2 Database:

[0074] A database is a structured collection of education-related information collected through cloud storage applications that is stored and made available for efficient search and retrieval.

[0075] 1.3 Interactive Machine Learning Models:

[0076] An interactive machine learning model is a machine learning model used to extract, analyze, and present information through natural language dialogue with a user.

[0077] 1.4 Generative AI Models:

[0078] A generative AI model is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[0079] 1.5 Server:

[0080] A server refers to a central processing unit such as a cloud storage application, database, or generative AI model, and is responsible for processing user requests and providing the necessary information.

[0081] 1.6 Terminal:

[0082] The terminal is a device such as a smartphone or a personal computer that allows a user to operate a cloud storage application. The terminal transmits input information to the server and displays the response from the server to the user.

[0083] 2. How to operate the system

[0084] 2.1 Entering and saving information:

[0085] A user uses a device to access a cloud storage application and inputs education-related information. The input information is sent through the device to a server, which stores the information in a database. Specifically, if a user inputs "Next week's math assignment: Calculus homework, due October 15, 2023," the information is stored in the database.

[0086] 2.2 Requesting and Extracting Information:

[0087] To obtain the desired information, a user inputs a prompt sentence into a cloud storage application. The device sends the input prompt sentence to the server, which uses the generative AI model to analyze and process the prompt sentence. The generative AI model extracts relevant information from the database, and the server sends the results to the device. In concrete terms, if a user inputs "When is next week's assignment due?", the generative AI model extracts information such as "The deadline for next week's math assignment is October 15, 2023," and displays it on the device.

[0088] In this way, the system of the present invention is designed to enable users to efficiently manage education-related information and quickly obtain the information they need. In addition, by utilizing an interactive machine learning model and a generative AI model, it is possible to extract and notify information according to the user's request.

[0089] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0090] Step 1:

[0091] A user inputs education-related information, such as assignments, projects, and notes, into a cloud storage application via the device.

[0092] Specifically, a user enters "Math assignment for next week: Calculus homework, due October 15, 2023." This input includes the name of the assignment, details, and the due date.

[0093] Input: A user inputs education-related information into a cloud storage application.

[0094] Output: The terminal sends the entered information to the server.

[0095] Step 2:

[0096] The terminal transmits the entered information to the server through the cloud storage application.

[0097] The server receives this information and stores it in a database.

[0098] Input: Education-related information sent from the device.

[0099] Output: The server stores the received information in a database.

[0100] Step 3:

[0101] When a user wants to obtain information, they enter a prompt sentence into the cloud storage application.

[0102] For example, a user types, "When is the assignment due next week?"

[0103] Input: The user enters the prompt text into the cloud storage application.

[0104] Output: The terminal sends the prompt text entered to the server.

[0105] Step 4:

[0106] The terminal sends the prompt text entered to the server.

[0107] The server receives the prompt and passes it to the generative AI model.

[0108] Input: The prompt text sent from the terminal.

[0109] Output: The server passes the prompt to the generative AI model.

[0110] Step 5:

[0111] A generative AI model parses the prompt and extracts relevant information from a database.

[0112] For example, in response to the prompt "When is next week's assignment due?", the information extracted is "October 15, 2023."

[0113] Input: Prompt text passed by the server and information stored in the database.

[0114] Output: The generative AI model extracts the relevant information and returns it to the server.

[0115] Step 6:

[0116] The server receives the information obtained from the generative AI model and transmits it to the terminal.

[0117] The server generates a response saying, "Next week's math assignment is due on October 15, 2023," and sends it to the device.

[0118] Input: Information extracted from a generative AI model.

[0119] Output: The server sends the generated response to the terminal.

[0120] Step 7:

[0121] The terminal receives the information sent from the server and displays it to the user through the cloud storage application.

[0122] The user sees the information, "Next week's math assignment is due on October 15, 2023."

[0123] Input: The response sent by the server.

[0124] Output: The terminal displays the response to the user.

[0125] (Application example 1)

[0126] 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."

[0127] In modern factory operations, work schedule management and preventive maintenance management of machinery and equipment are extremely important. However, when these management tasks are performed manually, there is a problem that human error is likely to occur, hindering efficient operation. In addition, in the current system, information such as each work schedule and memos is stored separately, making it difficult to manage them centrally. Furthermore, reminder and schedule management functions are not sufficiently integrated, making it difficult to notify important information in a timely manner. As a result, work efficiency is reduced and preventive maintenance is delayed, increasing risks in factory operations.

[0128] 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.

[0129] In this invention, the server includes a means for centrally storing at least one of information on a user's work, project, and memo, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one reminder of a work deadline, an inspection date, and an important memo, and a means for providing work schedule management and preventive maintenance reminders within the factory. This enables centralized management of work schedules within the factory and efficient reminder notifications, reduces human errors, prevents delays in preventive maintenance, and significantly improves the efficiency and safety of factory operations.

[0130] A "cloud storage app" is an application that stores data on a server on the Internet and can be accessed from multiple devices.

[0131] "User" refers to any individual or entity that uses the cloud storage app.

[0132] "Work" refers to the work or tasks performed in a factory or office.

[0133] "Project" refers to a set of activities planned and carried out to achieve a specific purpose.

[0134] A "memo" is a simple piece of writing or a note that contains important information or records.

[0135] "Centralized storage" refers to the integrated management and storage of multiple data in one place.

[0136] An "interactive machine learning model" refers to an AI technology that uses natural language processing and other techniques to provide information through dialogue with users.

[0137] "Date and time information" refers to information relating to a specific date and time, including work deadlines and inspection dates.

[0138] "Reminders" is a feature that notifies you in advance of important events and tasks.

[0139] "Work schedule management" refers to centralized management of work plans and progress.

[0140] "Preventive maintenance reminder" is a function that notifies users of the need to perform maintenance work on machinery and equipment at the appropriate time.

[0141] A "server" is a computer system that stores data and executes programs.

[0142] The embodiment of the present invention provides a system that manages information on a user's work, projects, and notes in an integrated manner and realizes efficient reminder notifications and schedule management. The following describes how to specifically implement the present invention.

[0143] First, the server uses a cloud storage app to centrally store at least one of the user's work, project, and memo information. The cloud storage app stores data on a server on the Internet and is accessible from multiple devices. By using this application, the user can access and update the data from anywhere.

[0144] Then, an interactive machine learning model (generative AI model) is integrated into the server to extract information about dates and times from the stored database. This model applies natural language processing technology to set at least one reminder for work deadlines, inspection dates, and important notes based on the user's requests. When generating a specific reminder, the interactive machine learning model processes the prompts and generates an appropriate reminder.

[0145] In addition, the server has the function of managing work schedules within the factory and providing preventive maintenance reminders. This function allows users to centrally manage work schedules and receive suggestions to improve the productivity of each worker. The preventive maintenance reminder function notifies users of the need for timely maintenance work on machinery and equipment, preventing breakdowns before they occur.

[0146] As specific examples, the following operations are performed. For example, the server uses AWS (registered trademark) S3 and AWS RDS to store and manage data. The generative AI model uses the OpenAI (registered trademark) ChatGPT (registered trademark) API for natural language processing. The user interface is built using ROS (Robot Operating System) within the factory, and React Native is used for smartphones and tablets. The system is operated via a browser or mobile app.

[0147] An example of a prompt sentence would be generated as follows:

[0148] Example prompt: "Generate a maintenance reminder for equipment ID: equipment_456"

[0149] Expected result: "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly."

[0150] In this way, the server can comprehensively manage users' work and schedule information and utilize the generative AI model to provide reminders and schedule management, thereby supporting efficient factory operations.

[0151] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0152] Step 1:

[0153] A user uses a device to access a cloud storage app. The user inputs and saves task, project, and note information into the app. The input can be in the form of text or files, and the data is stored in AWS S3 on the server. The output is a confirmation message indicating that the data was saved successfully.

[0154] Step 2:

[0155] The server stores the saved data in an AWS RDS database, a relational database that allows information to be organized and efficiently searched. The input is the data sent from the cloud storage app, and the output is the reflected entries in the database.

[0156] Step 3:

[0157] A user sends a reminder setting request containing certain information to the server via a terminal: the input is a natural language request such as "Please set a maintenance reminder", and the output is a confirmation message indicating that the request has been accepted.

[0158] Step 4:

[0159] When the server receives a request, it performs natural language processing using an interactive machine learning model. The input is the request from the user, which is analyzed as text. To process the data, natural language processing technology is used to perform natural language analysis to extract the request content. The output is the analyzed request content.

[0160] Step 5:

[0161] The server extracts relevant date and time information from the stored database based on the parsed request content. For example, it extracts the maintenance date of a specific machine. In this case, the input is the parsed request content, and the output is the relevant date and time information.

[0162] Step 6:

[0163] The server sends a prompt to the generative AI model (OpenAI ChatGPT) to generate an appropriate reminder message. The input is a prompt such as "Generate a maintenance reminder for equipment ID: equipment_456", and the output is the generated result such as "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly".

[0164] Step 7:

[0165] The server sends the generated reminder message to the user's terminal. The input is the generated reminder message, and the output is the notification displayed on the user's terminal.

[0166] Step 8:

[0167] The user checks the reminders on the device and adjusts their work schedule or maintenance plan as necessary, where the input is the reminder message displayed on the device and the output is the adjustment to the user's plan or schedule.

[0168] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0169] An embodiment for implementing the present invention includes the following elements.

[0170] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[0171] 2. Database: Where student assignment, project, and / or notebook information is stored.

[0172] 3. Generative AI function as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0173] 4. Emotion engine: Technology for recognizing and analyzing the user's emotions. It detects changes in tone of voice and facial expressions to understand the user's emotional state.

[0174] 5. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[0175] 6. Server: The central processing unit where the cloud storage app, database, generative AI functions, and emotion engine run.

[0176] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, extraction of information, recognition of emotions, and appropriate responses.

[0177] As a concrete example, a user uses a terminal to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Furthermore, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function customizes the generated response while taking into account the user's emotional state (step 6). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (step 7). In addition to displaying the response on the terminal, the response may be output as voice.

[0178] In this way, by combining a cloud storage app, a database, generative AI functions, an emotion engine, a terminal, and a server based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, information extraction and support, and even emotion recognition and appropriate responses.

[0179] The process flow will be explained below.

[0180] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[0181] Step 2: The user sends a request to the server via the terminal.

[0182] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[0183] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[0184] Step 5: The emotion engine recognizes the user's tone of voice and changes in facial expressions to understand the user's emotional state.

[0185] Step 6: The server leverages its generative AI capabilities to generate a customized response based on the extracted information and the user's emotional state.

[0186] Step 7: The server sends the generated response to the terminal.

[0187] Step 8: The terminal receives the response from the server and displays it to the user.

[0188] As a concrete example, a user uses a terminal to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). At the same time, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function generates a customized response based on the extracted information and the user's emotional state, such as "Tomorrow's math homework is due at 5 p.m., are you okay? Please be careful when you work on it" (step 6). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 7 and 8). In addition to displaying the response on the terminal, the response may be output as voice.

[0189] In this way, a user sends a request to the server through a terminal, the server analyzes the request, extracts information from a database to generate a response, and the emotion engine grasps the user's emotional state and provides a customized response, allowing the user to obtain the information he or she needs and receive an appropriate response.

[0190] Example 2

[0191] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart device 14 is referred to as a "terminal."

[0192] Modern students have difficulty efficiently managing assignments, projects, and note information in various educational activities and quickly retrieving the necessary information. In addition, stress and emotional fluctuations can reduce learning efficiency, so a system to solve these problems is required. Current technologies require the use of multiple applications and systems, and often lack centralized management and emotion recognition functions.

[0193] 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.

[0194] In this invention, the server includes a means for centrally storing at least one of the information of educational activities in a cloud storage app, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting reminders for important matters, and an emotion engine means for recognizing and analyzing the emotional state of a user to generate an appropriate response. This allows students to centrally manage information, quickly obtain the information they need, and receive support according to their emotional state, thereby improving the efficiency of their learning.

[0195] A "cloud storage app" is an application for centrally storing and managing information about educational activities.

[0196] "Educational activity information" refers to digital data related to learning, such as student assignments, projects, and notes.

[0197] An "interactive machine learning model" is a machine learning model that enables natural language dialogue with the user and has the ability to extract and present relevant information from a stored database.

[0198] "Date and time information" refers to data about assignment deadlines, exam dates, and dates of other important events.

[0199] "Reminder" refers to a function that notifies or warns the user to prevent them from forgetting important dates and times.

[0200] An "emotion engine" refers to technology that detects changes in the user's tone of voice and facial expressions and recognizes and analyzes their emotional state.

[0201] "Server" refers to a central high-performance computer that hosts and processes the cloud storage app, the interactive machine learning models, and the emotion engine.

[0202] "Terminal" refers to a device (such as a smartphone or PC) that a user uses to access and operate a cloud storage app.

[0203] "User request" refers to a request made by a user to confirm information such as assignment deadlines, exam dates, etc.

[0204] "Natural language processing technology" refers to technology that analyzes a user's voice or text input, understands the meaning, and extracts appropriate responses or information.

[0205] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0206] The embodiment of the present invention is composed of multiple elements: a cloud storage application, an interactive machine learning model, an emotion engine, a database, a terminal, and a server.

[0207] Cloud Storage Apps

[0208] A server hosts a cloud storage application, which users access from their devices (smartphones and PCs). As a concrete example of an application, we will use a general cloud storage service. Users use this app to upload and manage their assignments, projects, and notes in digital format.

[0209] Database

[0210] The database exists on the server and is used to centrally manage the information on educational activities saved by users. Specifically, a database management system such as MySQL (registered trademark) or PostgreSQL (registered trademark) is used. The database stores information such as deadlines for assignments, exam dates, and important notes.

[0211] Interactive Machine Learning Models

[0212] An interactive machine learning model (e.g., a generative AI model) installed on the server is used to analyze requests from users in natural language and extract and present appropriate information. The models used here include high-performance natural language processing models such as ChatGPT. For example, it generates an appropriate answer to a question such as, "What time is the deadline for my math homework tomorrow?"

[0213] Emotion Engine

[0214] The emotion engine runs on the server and detects changes in the user's tone of voice and facial expressions to recognize and analyze the user's emotional state. As a specific technology, for example, the emotion recognition API of Microsoft(R) Azure(R) Cognitive Services is used. This makes it possible to determine whether the user is feeling stressed.

[0215] Terminal

[0216] A device that allows a user to use a cloud storage app. Specifically, it can be a smartphone or a PC. The device provides an interface for the user to send requests to the server and receive and display responses from the server.

[0217] server

[0218] The server is a central high-performance computer that hosts the cloud storage app, the interactive machine learning models, the emotion engine, and the database. The server also receives user requests and performs the appropriate processing to generate a response.

[0219] Examples

[0220] For example, a user uses a smartphone to access a cloud storage app and saves his / her math homework in a database. After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?". The server receives the request, analyzes it using natural language processing technology, and extracts information about the deadline. In addition, an emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state. The generative AI model customizes the generated response while taking into account the user's emotional state. The generated response is sent from the server to the terminal, and the user can check the response on the terminal.

[0221] Through this system, users can centrally manage information about their educational activities and efficiently obtain the information they need. Furthermore, the emotion engine function allows users to receive appropriate support according to their emotional state.

[0222] Example prompt:

[0223] "Describe a scenario where a user uses their smartphone to access a cloud storage app to check deadline information and then receives a stress-based message of encouragement."

[0224] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0225] Step 1:

[0226] The user uses the device to access the cloud storage app and uploads information about educational activities to the database.

[0227] Specifically, a user uploads a file such as a math homework file called "math_homework.docx" using a smartphone or computer. The uploaded file is sent to a server via a cloud storage app, and the server receives the file and stores it in a database.

[0228] Input: File data uploaded by the user

[0229] Output: File data stored in database

[0230] Step 2:

[0231] The user sends a request from the terminal.

[0232] Specifically, the user uses the voice assistant function to ask, "What time is my math homework due tomorrow?" The device converts this voice data into text and sends it to the server via a cloud storage app.

[0233] Input: User's voice request

[0234] Output: Request data in text format

[0235] Step 3:

[0236] The server receives the request and analyzes the request using an interactive machine learning model.

[0237] Specifically, the server analyzes the text "What time is tomorrow's math homework due?" to identify the required information (the due date of the assignment). Here, a generative AI model is used to perform semantic analysis.

[0238] Input: Request data in text format

[0239] Output: Parsed request content

[0240] Step 4:

[0241] The server extracts the required information from the database.

[0242] Specifically, the database is searched for the deadline for "Math Homework" and the data "2023-10-15 17:00" is extracted. In this process, related entries are retrieved from the database based on the analysis results.

[0243] Input: Parsed request content

[0244] Output: Deadline information

[0245] Step 5:

[0246] The server uses an emotion engine to recognize the user's emotional state.

[0247] Specifically, the server analyzes the user's voice data and facial expression images to determine whether the user is feeling stressed. Here, the emotion recognition API is used.

[0248] Input: User's voice data and facial expression images

[0249] Output: Perceived emotional state

[0250] Step 6:

[0251] A generative AI model uses the analyzed data and emotional information to generate a response.

[0252] Specifically, the server uses the generated AI model to generate an appropriate response, "The deadline for your math homework is tomorrow at 5:00 p.m. Good luck!", based on the extracted deadline date and time information and the results of sentiment analysis.

[0253] Input: Deadline information and emotional state information

[0254] Output: The response message to be presented to the user

[0255] Step 7:

[0256] The server sends the generated response to the user's terminal.

[0257] Specifically, the server sends the generated response message to the user's device as a text message via the cloud storage app.

[0258] Input: The generated response message

[0259] Output: The response message displayed on the user's terminal.

[0260] Step 8:

[0261] The user checks the response and sends the request again if necessary.

[0262] Specifically, the user checks the response on their smartphone, and if additional information is needed, they send a new request to the server again using the cloud storage app.

[0263] Input: The response message received from the server.

[0264] Output: A new request by the user (if necessary).

[0265] (Application example 2)

[0266] 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."

[0267] Conventional cloud storage systems allow for centralized management of students' learning content and the setting of reminders, but in order to maximize learning effectiveness, it is necessary to recommend appropriate content according to the user's emotional state and learning situation. However, conventional systems lack the functionality to recognize the user's emotions and recommend learning materials, making it difficult to improve learning efficiency. Therefore, the present invention aims to provide a system that improves learning efficiency by recognizing the user's emotions and recommending appropriate learning materials.

[0268] 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.

[0269] In this invention, the server includes a means for centrally storing at least one of the pieces of information in the cloud storage app, a means for integrating the functions of an interactive machine learning model, extracting information on date and time from the stored database, and setting a reminder, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for recommending learning materials and generating reminders using generative AI. This makes it possible to provide optimal learning materials and generate reminders while taking into account the user's emotional state.

[0270] (definition statement)

[0271] A "cloud storage app" is an application that stores and manages data on the Internet and can be accessed from various devices.

[0272] An "interactive machine learning model" is a machine learning model that interacts with the user in a dialogue format and analyzes and generates information using natural language processing technology.

[0273] An "emotion engine" is a technology that recognizes and judges a user's emotional state by analyzing data such as their voice tone and facial expressions.

[0274] "Generative AI" is an AI technology that generates natural-looking sentences and answers in response to user requests.

[0275] "Centralized information storage" refers to the means of managing data such as assignments, projects, and notes in one place on the cloud.

[0276] "Setting a reminder" is a means for notifying the user at an appropriate time based on date and time information extracted from the database.

[0277] "Recommend learning materials" is a function that takes into account the user's learning situation and emotional state and provides the most appropriate learning videos and materials.

[0278] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[0279] The system that realizes this invention is composed of a cloud storage app, an interactive machine learning model, an emotion engine, and a generative AI. Users access it via their terminals (smartphones or PCs) and manage and recommend learning materials.

[0280] Program processing explanation

[0281] Cloud Storage:

[0282] The server runs a cloud storage app and centrally stores the data of assignments, projects, and notes uploaded by users. An SDK for cloud storage (e.g., Google Cloud Storage SDK) is used.

[0283] Interactive Machine Learning Models:

[0284] The server integrates an interactive machine learning model to analyze user requests using natural language processing techniques. The model uses generative AI (e.g. ChatGPT (registered trademark)) to generate appropriate responses to user requests.

[0285] Emotion Engine:

[0286] The server uses an emotion engine to analyze the user's emotional state from their voice tone and facial expression data. An SDK for emotion analysis (e.g. Microsoft Azure Emotion API) is used.

[0287] Generative AI:

[0288] The server uses generative AI to recommend appropriate learning materials and generate reminders based on the user's learning status and emotional state. In this process, it generates prompt sentences and inputs them into the AI ​​model.

[0289] Examples

[0290] For example, a user can use a device to access a cloud storage app, upload a biology video lecture, and then request, "Tell me about a video that will help me prepare for the exam." The server can then use generative AI to respond with, "Here's a video that will help me prepare for the exam." The emotion engine can also detect tension in the user's tone of voice and generate a response to relax the user. Reminders can also be set for upcoming exams and assignment deadlines.

[0291] Examples of prompt statements

[0292] "Can you tell me which video would be helpful for my next biology exam?"

[0293] In this way, the system of the present invention can provide users with an optimal learning experience by combining centralized data management, sentiment analysis, and natural language processing.

[0294] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0295] Program processing flow

[0296] Step 1:

[0297] A user uses a device to access a cloud storage app and uploads learning materials (e.g., video lectures and notes).

[0298] Input: Study materials (videos, notes, projects)

[0299] Output: Data stored in cloud storage

[0300] Specific operation: The user drags and drops the learning materials saved on the device to the cloud storage app and clicks the upload button. The server stores the received data in the cloud storage.

[0301] Step 2:

[0302] A user uses the device to input requests for study content and reminders (e.g., "Tell me which videos would be helpful for my next exam").

[0303] Input: User request (natural language question or instruction)

[0304] Output: The request data sent to the server.

[0305] Specific behavior: The user makes a request by voice or keyboard input, and the device sends this input to the server.

[0306] Step 3:

[0307] The server analyzes the received user request using natural language processing technology to understand the intent of the request.

[0308] Input: User request data

[0309] Output: Parsed request (intent and required information)

[0310] How it works: The server uses a natural language processing model (e.g. ChatGPT) to analyze the user's request and understand its intent, extracting keywords and important information from the request.

[0311] Step 4:

[0312] The server uses an emotion engine to analyze the user's emotional state from their tone of voice and facial expressions.

[0313] Input: User voice and facial expression data

[0314] Output: The user's emotional state.

[0315] Specific operation: The server uses an SDK for voice and facial expression analysis (e.g., Microsoft Azure Emotion API) to input the user's voice tone and facial expression data into the emotion engine for analysis. The analysis result is the user's emotional state (e.g., tension, relaxation).

[0316] Step 5:

[0317] The server uses generative AI to recommend optimal learning materials based on the analysis results (request content and emotional state).

[0318] Input: Parsed desire and emotional state

[0319] Output: Recommended learning materials

[0320] Specific operation: The server generates and inputs a prompt to the generative AI (e.g. ChatGPT). Example: "Please recommend a relaxing learning video for the next exam." The AI ​​model generates optimal learning materials based on this prompt and returns them to the server.

[0321] Step 6:

[0322] The server generates a response and sends it to the user, who can review the response via their device and access recommended learning materials and reminders.

[0323] Input: Recommended learning material information

[0324] Output: Information displayed on the user's terminal.

[0325] Specific operation: The server sends the recommended learning materials obtained from the generative AI to the user's device. The device displays this information and can read it out loud if necessary. The user checks the displayed recommended materials and uses them.

[0326] In this way, by linking cloud storage, natural language processing, sentiment analysis, and generative AI at each step, we create a system that provides users with optimal learning support.

[0327] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0328] 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<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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0329] In the above embodiment, an example has been given in which the specific process is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0330] [Second embodiment]

[0331] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0332] 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.

[0333] 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 wide area network (WAN) and / or a local area network (LAN).

[0334] 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.

[0335] 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 the voice according to instructions from the processor 46.

[0336] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0337] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0338] Fig. 4 shows an example of 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.

[0339] 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.

[0340] 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.

[0341] 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.

[0342] 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 a "server" and the smart glasses 214 will be referred to as a "terminal".

[0343] An embodiment for implementing the present invention includes the following elements.

[0344] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[0345] 2. Database: Where student assignment, project, and / or notebook information is stored.

[0346] 3. Generative AI function as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0347] 4. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[0348] 5. Server: The central processing unit where the cloud storage app, database, and generative AI functions run.

[0349] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, as well as information extraction and support.

[0350] As a concrete example, a user uses a device to access a cloud storage app and saves assignments, projects, and notes in a database. The user then sends a request to a server via the device, and the server extracts relevant information from the saved database and responds to the user's request using generative AI functions. The user receives the response from the server via the device and can obtain the information he or she needs.

[0351] In this way, by combining a cloud storage app, database, generative AI functions, terminals, and servers based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, and to extract and support information.

[0352] The process flow will be explained below.

[0353] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[0354] Step 2: The user sends a request to the server via the terminal.

[0355] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[0356] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[0357] Step 5: The server uses the generative AI capabilities to generate a response that meets the user's request based on the extracted information.

[0358] Step 6: The server sends the generated response to the terminal.

[0359] Step 7: The terminal receives the response from the server and displays it to the user.

[0360] As a specific example, a user uses a terminal to access a cloud storage app and saves math homework in a database (step 1). After that, the user sends a request to a server via the terminal, asking "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Next, the server uses the functions of generative AI to generate a response saying "Tomorrow's math homework is due at 5 p.m." (step 5). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 6 and 7). Note that the response may be output as voice instead of being displayed on the terminal.

[0361] In this way, a user sends a request to a server through a terminal, the server analyzes the request, extracts information from a database, generates a response, and sends the response to the terminal, allowing the user to obtain the information he or she needs.

[0362] Example 1

[0363] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0364] Conventional education-related information management systems have the problem that information on assignments, projects, and notes is stored in a scattered manner, making efficient management difficult. In addition, the function to remind users of important information such as deadlines and exam dates was insufficient, so users had to take a lot of time and effort to check the information. Furthermore, there was a lack of means to quickly extract the specific information that users were looking for, which resulted in low user convenience.

[0365] 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.

[0366] In this invention, the server includes a means for centrally storing at least one piece of education-related information as an example of pre-registered information in a cloud storage application, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one notification of a deadline, an event date, and an important note as an example of a reminder, and a means for utilizing a generative AI model for searching and extracting related information in response to a user request. This makes it possible to provide an environment in which education-related information can be managed efficiently in a centralized manner and users can check important information such as deadlines and exam dates in a timely manner.

[0367] A "cloud storage application" is an application that centrally stores education-related information on the Internet and allows users to access, manage, and edit information from any device.

[0368] "Education-related information" refers to information including student assignments, projects, notes, and associated time and date information.

[0369] An "interactive machine learning model" is a machine learning model used to extract, analyze, and present information through natural language interactions with a user.

[0370] "Date and time information" refers to date and time information related to assignment deadlines, exam dates, and important notes.

[0371] A "notification" is a means of communication to inform a user of important information (e.g. deadlines or event dates).

[0372] A "generative AI model" is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[0373] "Server" refers to a central processing unit such as a cloud storage application, database, or generative AI model, which processes user requests and provides the necessary information.

[0374] "Database" means a collection of education-related information collected through the Cloud Storage Application that is structured to store, search and retrieve information efficiently.

[0375] A "prompt sentence" refers to a search request or instruction sentence that a user inputs into a cloud storage application using natural language.

[0376] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0377] The present invention is a system that is constructed by elements such as a cloud storage application, education-related information, an interactive machine learning model, information on date and time, notifications, a generative AI model, a server, a database, and prompt sentences, which allows users to efficiently manage education-related information and quickly obtain the information they need.

[0378] 1. System Configuration

[0379] 1.1 Cloud storage applications:

[0380] A cloud storage application is an application that allows users to centrally store educational information on the Internet and access, manage, and edit it from any device. Educational information includes student assignments, projects, notes, and associated time and date information.

[0381] 1.2 Database:

[0382] A database is a structured collection of education-related information collected through cloud storage applications that is stored and made available for efficient search and retrieval.

[0383] 1.3 Interactive Machine Learning Models:

[0384] An interactive machine learning model is a machine learning model used to extract, analyze, and present information through natural language dialogue with a user.

[0385] 1.4 Generative AI Models:

[0386] A generative AI model is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[0387] 1.5 Server:

[0388] A server refers to a central processing unit such as a cloud storage application, database, or generative AI model, and is responsible for processing user requests and providing the necessary information.

[0389] 1.6 Terminal:

[0390] The terminal is a device such as a smartphone or a personal computer that allows a user to operate a cloud storage application. The terminal transmits input information to the server and displays the response from the server to the user.

[0391] 2. How to operate the system

[0392] 2.1 Entering and saving information:

[0393] A user uses a device to access a cloud storage application and inputs education-related information. The input information is sent through the device to a server, which stores the information in a database. Specifically, if a user inputs "Next week's math assignment: Calculus homework, due October 15, 2023," the information is stored in the database.

[0394] 2.2 Requesting and Extracting Information:

[0395] To obtain the desired information, a user inputs a prompt sentence into a cloud storage application. The device sends the input prompt sentence to the server, which uses the generative AI model to analyze and process the prompt sentence. The generative AI model extracts relevant information from the database, and the server sends the results to the device. In concrete terms, if a user inputs "When is next week's assignment due?", the generative AI model extracts information such as "The deadline for next week's math assignment is October 15, 2023," and displays it on the device.

[0396] In this way, the system of the present invention is designed to enable users to efficiently manage education-related information and quickly obtain the information they need. In addition, by utilizing an interactive machine learning model and a generative AI model, it is possible to extract and notify information according to the user's request.

[0397] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0398] Step 1:

[0399] A user inputs education-related information, such as assignments, projects, and notes, into a cloud storage application via the device.

[0400] Specifically, a user enters "Math assignment for next week: Calculus homework, due October 15, 2023." This input includes the name of the assignment, details, and the due date.

[0401] Input: A user inputs education-related information into a cloud storage application.

[0402] Output: The terminal sends the entered information to the server.

[0403] Step 2:

[0404] The terminal transmits the entered information to the server through the cloud storage application.

[0405] The server receives this information and stores it in a database.

[0406] Input: Education-related information sent from the device.

[0407] Output: The server stores the received information in a database.

[0408] Step 3:

[0409] When a user wants to obtain information, they enter a prompt sentence into the cloud storage application.

[0410] For example, a user types, "When is the assignment due next week?"

[0411] Input: The user enters the prompt text into the cloud storage application.

[0412] Output: The terminal sends the prompt text entered to the server.

[0413] Step 4:

[0414] The terminal sends the prompt text entered to the server.

[0415] The server receives the prompt and passes it to the generative AI model.

[0416] Input: The prompt text sent from the terminal.

[0417] Output: The server passes the prompt to the generative AI model.

[0418] Step 5:

[0419] A generative AI model parses the prompt and extracts relevant information from a database.

[0420] For example, in response to the prompt "When is next week's assignment due?", the information extracted is "October 15, 2023."

[0421] Input: Prompt text passed by the server and information stored in the database.

[0422] Output: The generative AI model extracts the relevant information and returns it to the server.

[0423] Step 6:

[0424] The server receives the information obtained from the generative AI model and transmits it to the terminal.

[0425] The server generates a response saying, "Next week's math assignment is due on October 15, 2023," and sends it to the device.

[0426] Input: Information extracted from a generative AI model.

[0427] Output: The server sends the generated response to the terminal.

[0428] Step 7:

[0429] The terminal receives the information sent from the server and displays it to the user through the cloud storage application.

[0430] The user sees the information, "Next week's math assignment is due on October 15, 2023."

[0431] Input: The response sent by the server.

[0432] Output: The terminal displays the response to the user.

[0433] (Application example 1)

[0434] 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".

[0435] In modern factory operations, work schedule management and preventive maintenance management of machinery and equipment are extremely important. However, when these management tasks are performed manually, there is a problem that human error is likely to occur, hindering efficient operation. In addition, in the current system, information such as each work schedule and memos is stored separately, making it difficult to manage them centrally. Furthermore, reminder and schedule management functions are not sufficiently integrated, making it difficult to notify important information in a timely manner. As a result, work efficiency is reduced and preventive maintenance is delayed, increasing risks in factory operations.

[0436] 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.

[0437] In this invention, the server includes a means for centrally storing at least one of information on a user's work, project, and memo, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one reminder of a work deadline, an inspection date, and an important memo, and a means for providing work schedule management and preventive maintenance reminders within the factory. This enables centralized management of work schedules within the factory and efficient reminder notifications, reduces human errors, prevents delays in preventive maintenance, and significantly improves the efficiency and safety of factory operations.

[0438] A "cloud storage app" is an application that stores data on a server on the Internet and can be accessed from multiple devices.

[0439] "User" refers to any individual or entity that uses the cloud storage app.

[0440] "Work" refers to the work or tasks performed in a factory or office.

[0441] "Project" refers to a set of activities planned and carried out to achieve a specific purpose.

[0442] A "memo" is a simple piece of writing or a note that contains important information or records.

[0443] "Centralized storage" refers to the integrated management and storage of multiple data in one place.

[0444] An "interactive machine learning model" refers to an AI technology that uses natural language processing and other techniques to provide information through dialogue with users.

[0445] "Date and time information" refers to information relating to a specific date and time, including work deadlines and inspection dates.

[0446] "Reminders" is a feature that notifies you in advance of important events and tasks.

[0447] "Work schedule management" refers to centralized management of work plans and progress.

[0448] "Preventive maintenance reminder" is a function that notifies users of the need to perform maintenance work on machinery and equipment at the appropriate time.

[0449] A "server" is a computer system that stores data and executes programs.

[0450] The embodiment of the present invention provides a system that manages information on a user's work, projects, and notes in an integrated manner and realizes efficient reminder notifications and schedule management. The following describes how to specifically implement the present invention.

[0451] First, the server uses a cloud storage app to centrally store at least one of the user's work, project, and memo information. The cloud storage app stores data on a server on the Internet and is accessible from multiple devices. By using this application, the user can access and update the data from anywhere.

[0452] Then, an interactive machine learning model (generative AI model) is integrated into the server to extract information about dates and times from the stored database. This model applies natural language processing technology to set at least one reminder for work deadlines, inspection dates, and important notes based on the user's requests. When generating a specific reminder, the interactive machine learning model processes the prompts and generates an appropriate reminder.

[0453] In addition, the server has the function of managing work schedules within the factory and providing preventive maintenance reminders. This function allows users to centrally manage work schedules and receive suggestions to improve the productivity of each worker. The preventive maintenance reminder function notifies users of the need for timely maintenance work on machinery and equipment, preventing breakdowns before they occur.

[0454] As specific examples, the following operations are performed. For example, the server uses AWS S3 and AWS RDS to store and manage data. The generative AI model uses the OpenAI ChatGPT API for natural language processing. The user interface is built using ROS (Robot Operating System) within the factory, and React Native is used for smartphones and tablets. The system is operated via a browser or mobile app.

[0455] An example of a prompt sentence would be generated as follows:

[0456] Example prompt: "Generate a maintenance reminder for equipment ID: equipment_456"

[0457] Expected result: "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly."

[0458] In this way, the server can comprehensively manage users' work and schedule information and utilize the generative AI model to provide reminders and schedule management, thereby supporting efficient factory operations.

[0459] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0460] Step 1:

[0461] A user uses a device to access a cloud storage app. The user inputs and saves task, project, and note information into the app. The input can be in the form of text or files, and the data is stored in AWS S3 on the server. The output is a confirmation message indicating that the data was saved successfully.

[0462] Step 2:

[0463] The server stores the saved data in an AWS RDS database, a relational database that allows information to be organized and efficiently searched. The input is the data sent from the cloud storage app, and the output is the reflected entries in the database.

[0464] Step 3:

[0465] A user sends a reminder setting request containing certain information to the server via a terminal: the input is a natural language request such as "Please set a maintenance reminder", and the output is a confirmation message indicating that the request has been accepted.

[0466] Step 4:

[0467] When the server receives a request, it performs natural language processing using an interactive machine learning model. The input is the request from the user, which is analyzed as text. To process the data, natural language processing technology is used to perform natural language analysis to extract the request content. The output is the analyzed request content.

[0468] Step 5:

[0469] The server extracts relevant date and time information from the stored database based on the parsed request content. For example, it extracts the maintenance date of a specific machine. In this case, the input is the parsed request content, and the output is the relevant date and time information.

[0470] Step 6:

[0471] The server sends a prompt to the generative AI model (OpenAI ChatGPT) to generate an appropriate reminder message. The input is a prompt such as "Generate a maintenance reminder for equipment ID: equipment_456", and the output is the generated result such as "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly".

[0472] Step 7:

[0473] The server sends the generated reminder message to the user's terminal. The input is the generated reminder message, and the output is the notification displayed on the user's terminal.

[0474] Step 8:

[0475] The user checks the reminders on the device and adjusts their work schedule or maintenance plan as necessary, where the input is the reminder message displayed on the device and the output is the adjustment to the user's plan or schedule.

[0476] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0477] An embodiment for implementing the present invention includes the following elements.

[0478] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[0479] 2. Database: Where student assignment, project, and / or notebook information is stored.

[0480] 3. Generative AI function as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0481] 4. Emotion engine: Technology for recognizing and analyzing the user's emotions. It detects changes in tone of voice and facial expressions to understand the user's emotional state.

[0482] 5. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[0483] 6. Server: The central processing unit where the cloud storage app, database, generative AI functions, and emotion engine run.

[0484] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, extraction of information, recognition of emotions, and appropriate responses.

[0485] As a concrete example, a user uses a terminal to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Furthermore, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function customizes the generated response while taking into account the user's emotional state (step 6). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (step 7). In addition to displaying the response on the terminal, the response may be output as voice.

[0486] In this way, by combining a cloud storage app, a database, generative AI functions, an emotion engine, a terminal, and a server based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, information extraction and support, and even emotion recognition and appropriate responses.

[0487] The process flow will be explained below.

[0488] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[0489] Step 2: The user sends a request to the server via the terminal.

[0490] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[0491] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[0492] Step 5: The emotion engine recognizes the user's tone of voice and changes in facial expressions to understand the user's emotional state.

[0493] Step 6: The server leverages its generative AI capabilities to generate a customized response based on the extracted information and the user's emotional state.

[0494] Step 7: The server sends the generated response to the terminal.

[0495] Step 8: The terminal receives the response from the server and displays it to the user.

[0496] As a concrete example, a user uses a terminal to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). At the same time, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function generates a customized response based on the extracted information and the user's emotional state, such as "Tomorrow's math homework is due at 5 p.m., are you okay? Please be careful when you work on it" (step 6). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 7 and 8). In addition to displaying the response on the terminal, the response may be output as voice.

[0497] In this way, a user sends a request to the server through a terminal, the server analyzes the request, extracts information from a database to generate a response, and the emotion engine grasps the user's emotional state and provides a customized response, allowing the user to obtain the information he or she needs and receive an appropriate response.

[0498] Example 2

[0499] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0500] Modern students have difficulty efficiently managing assignments, projects, and note information in various educational activities and quickly retrieving the necessary information. In addition, stress and emotional fluctuations can reduce learning efficiency, so a system to solve these problems is required. Current technologies require the use of multiple applications and systems, and often lack centralized management and emotion recognition functions.

[0501] 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.

[0502] In this invention, the server includes a means for centrally storing at least one of the information of educational activities in a cloud storage app, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting reminders for important matters, and an emotion engine means for recognizing and analyzing the emotional state of a user to generate an appropriate response. This allows students to centrally manage information, quickly obtain the information they need, and receive support according to their emotional state, thereby improving the efficiency of their learning.

[0503] A "cloud storage app" is an application for centrally storing and managing information about educational activities.

[0504] "Educational activity information" refers to digital data related to learning, such as student assignments, projects, and notes.

[0505] An "interactive machine learning model" is a machine learning model that enables natural language dialogue with the user and has the ability to extract and present relevant information from a stored database.

[0506] "Date and time information" refers to data about assignment deadlines, exam dates, and dates of other important events.

[0507] "Reminder" refers to a function that notifies or warns the user to prevent them from forgetting important dates and times.

[0508] An "emotion engine" refers to technology that detects changes in the user's tone of voice and facial expressions and recognizes and analyzes their emotional state.

[0509] "Server" refers to a central high-performance computer that hosts and processes the cloud storage app, the interactive machine learning models, and the emotion engine.

[0510] "Terminal" refers to a device (such as a smartphone or PC) that a user uses to access and operate a cloud storage app.

[0511] "User request" refers to a request made by a user to confirm information such as assignment deadlines, exam dates, etc.

[0512] "Natural language processing technology" refers to technology that analyzes a user's voice or text input, understands the meaning, and extracts appropriate responses or information.

[0513] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0514] The embodiment of the present invention is composed of multiple elements: a cloud storage application, an interactive machine learning model, an emotion engine, a database, a terminal, and a server.

[0515] Cloud Storage Apps

[0516] A server hosts a cloud storage application, which users access from their devices (smartphones and PCs). As a concrete example of an application, we will use a general cloud storage service. Users use this app to upload and manage their assignments, projects, and notes in digital format.

[0517] Database

[0518] The database exists on the server and is used to centrally manage the information on educational activities saved by users. Specifically, a database management system such as MySQL or PostgreSQL is used. The database stores information such as deadlines for assignments, exam dates, and important notes.

[0519] Interactive Machine Learning Models

[0520] An interactive machine learning model (e.g., a generative AI model) installed on the server is used to analyze requests from users in natural language and extract and present appropriate information. The models used here include high-performance natural language processing models such as ChatGPT. For example, it generates an appropriate answer to a question such as, "What time is the deadline for my math homework tomorrow?"

[0521] Emotion Engine

[0522] The emotion engine runs on the server and detects changes in the user's tone of voice and facial expressions to recognize and analyze the user's emotional state. As a specific technology, for example, the emotion recognition API of Microsoft Azure Cognitive Services is used. This makes it possible to determine whether the user is feeling stressed.

[0523] Terminal

[0524] A device that allows a user to use a cloud storage app. Specifically, it can be a smartphone or a PC. The device provides an interface for the user to send requests to the server and receive and display responses from the server.

[0525] server

[0526] The server is a central high-performance computer that hosts the cloud storage app, the interactive machine learning models, the emotion engine, and the database. The server also receives user requests and performs the appropriate processing to generate a response.

[0527] Examples

[0528] For example, a user uses a smartphone to access a cloud storage app and saves his / her math homework in a database. After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?". The server receives the request, analyzes it using natural language processing technology, and extracts information about the deadline. In addition, an emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state. The generative AI model customizes the generated response while taking into account the user's emotional state. The generated response is sent from the server to the terminal, and the user can check the response on the terminal.

[0529] Through this system, users can centrally manage information about their educational activities and efficiently obtain the information they need. Furthermore, the emotion engine function allows users to receive appropriate support according to their emotional state.

[0530] Example prompt:

[0531] "Describe a scenario where a user uses their smartphone to access a cloud storage app to check deadline information and then receives a stress-based message of encouragement."

[0532] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0533] Step 1:

[0534] The user uses the device to access the cloud storage app and uploads information about educational activities to the database.

[0535] Specifically, a user uploads a file such as a math homework file called "math_homework.docx" using a smartphone or computer. The uploaded file is sent to a server via a cloud storage app, and the server receives the file and stores it in a database.

[0536] Input: File data uploaded by the user

[0537] Output: File data stored in database

[0538] Step 2:

[0539] The user sends a request from the terminal.

[0540] Specifically, the user uses the voice assistant function to ask, "What time is my math homework due tomorrow?" The device converts this voice data into text and sends it to the server via a cloud storage app.

[0541] Input: User's voice request

[0542] Output: Request data in text format

[0543] Step 3:

[0544] The server receives the request and analyzes the request using an interactive machine learning model.

[0545] Specifically, the server analyzes the text "What time is tomorrow's math homework due?" to identify the required information (the due date of the assignment). Here, a generative AI model is used to perform semantic analysis.

[0546] Input: Request data in text format

[0547] Output: Parsed request content

[0548] Step 4:

[0549] The server extracts the required information from the database.

[0550] Specifically, the database is searched for the deadline for "Math Homework" and the data "2023-10-15 17:00" is extracted. In this process, related entries are retrieved from the database based on the analysis results.

[0551] Input: Parsed request content

[0552] Output: Deadline information

[0553] Step 5:

[0554] The server uses an emotion engine to recognize the user's emotional state.

[0555] Specifically, the server analyzes the user's voice data and facial expression images to determine whether the user is feeling stressed. Here, the emotion recognition API is used.

[0556] Input: User's voice data and facial expression images

[0557] Output: Perceived emotional state

[0558] Step 6:

[0559] A generative AI model uses the analyzed data and emotional information to generate a response.

[0560] Specifically, the server uses the generated AI model to generate an appropriate response, "The deadline for your math homework is tomorrow at 5:00 p.m. Good luck!", based on the extracted deadline date and time information and the results of sentiment analysis.

[0561] Input: Deadline information and emotional state information

[0562] Output: The response message to be presented to the user

[0563] Step 7:

[0564] The server sends the generated response to the user's terminal.

[0565] Specifically, the server sends the generated response message to the user's device as a text message via the cloud storage app.

[0566] Input: The generated response message

[0567] Output: The response message displayed on the user's terminal.

[0568] Step 8:

[0569] The user checks the response and sends the request again if necessary.

[0570] Specifically, the user checks the response on their smartphone, and if additional information is needed, they send a new request to the server again using the cloud storage app.

[0571] Input: The response message received from the server.

[0572] Output: A new request by the user (if necessary).

[0573] (Application example 2)

[0574] 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".

[0575] Conventional cloud storage systems allow for centralized management of students' learning content and the setting of reminders, but in order to maximize learning effectiveness, it is necessary to recommend appropriate content according to the user's emotional state and learning situation. However, conventional systems lack the functionality to recognize the user's emotions and recommend learning materials, making it difficult to improve learning efficiency. Therefore, the present invention aims to provide a system that improves learning efficiency by recognizing the user's emotions and recommending appropriate learning materials.

[0576] 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.

[0577] In this invention, the server includes a means for centrally storing at least one of the pieces of information in the cloud storage app, a means for integrating the functions of an interactive machine learning model, extracting information on date and time from the stored database, and setting a reminder, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for recommending learning materials and generating reminders using generative AI. This makes it possible to provide optimal learning materials and generate reminders while taking into account the user's emotional state.

[0578] (definition statement)

[0579] A "cloud storage app" is an application that stores and manages data on the Internet and can be accessed from various devices.

[0580] An "interactive machine learning model" is a machine learning model that interacts with the user in a dialogue format and analyzes and generates information using natural language processing technology.

[0581] An "emotion engine" is a technology that recognizes and judges a user's emotional state by analyzing data such as their voice tone and facial expressions.

[0582] "Generative AI" is an AI technology that generates natural-looking sentences and answers in response to user requests.

[0583] "Centralized information storage" refers to the means of managing data such as assignments, projects, and notes in one place on the cloud.

[0584] "Setting a reminder" is a means for notifying the user at an appropriate time based on date and time information extracted from the database.

[0585] "Recommend learning materials" is a function that takes into account the user's learning situation and emotional state and provides the most appropriate learning videos and materials.

[0586] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[0587] The system that realizes this invention is composed of a cloud storage app, an interactive machine learning model, an emotion engine, and a generative AI. Users access it via their terminals (smartphones or PCs) and manage and recommend learning materials.

[0588] Program processing explanation

[0589] Cloud Storage:

[0590] The server runs a cloud storage app and centrally stores the data of assignments, projects, and notes uploaded by users. An SDK for cloud storage (e.g. Google Cloud Storage SDK) is used.

[0591] Interactive Machine Learning Models:

[0592] The server integrates an interactive machine learning model to analyze user requests using natural language processing techniques. The model uses generative AI (e.g. ChatGPT) to generate appropriate responses to user requests.

[0593] Emotion Engine:

[0594] The server uses an emotion engine to analyze the user's emotional state from their voice tone and facial expression data. An SDK for emotion analysis (e.g. Microsoft Azure Emotion API) is used.

[0595] Generative AI:

[0596] The server uses generative AI to recommend appropriate learning materials and generate reminders based on the user's learning status and emotional state. In this process, it generates prompt sentences and inputs them into the AI ​​model.

[0597] Examples

[0598] For example, a user can use a device to access a cloud storage app, upload a biology video lecture, and then request, "Tell me about a video that will help me prepare for the exam." The server can then use generative AI to respond with, "Here's a video that will help me prepare for the exam." The emotion engine can also detect tension in the user's tone of voice and generate a response to relax the user. Reminders can also be set for upcoming exams and assignment deadlines.

[0599] Examples of prompt statements

[0600] "Can you tell me which video would be helpful for my next biology exam?"

[0601] In this way, the system of the present invention can provide users with an optimal learning experience by combining centralized data management, sentiment analysis, and natural language processing.

[0602] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0603] Program processing flow

[0604] Step 1:

[0605] A user uses a device to access a cloud storage app and uploads learning materials (e.g., video lectures and notes).

[0606] Input: Study materials (videos, notes, projects)

[0607] Output: Data stored in cloud storage

[0608] Specific operation: The user drags and drops the learning materials saved on the device to the cloud storage app and clicks the upload button. The server stores the received data in the cloud storage.

[0609] Step 2:

[0610] A user uses the device to input requests for study content and reminders (e.g., "Tell me which videos would be helpful for my next exam").

[0611] Input: User request (natural language question or instruction)

[0612] Output: The request data sent to the server.

[0613] Specific behavior: The user makes a request by voice or keyboard input, and the device sends this input to the server.

[0614] Step 3:

[0615] The server analyzes the received user request using natural language processing technology to understand the intent of the request.

[0616] Input: User request data

[0617] Output: Parsed request (intent and required information)

[0618] How it works: The server uses a natural language processing model (e.g. ChatGPT) to analyze the user's request and understand its intent, extracting keywords and important information from the request.

[0619] Step 4:

[0620] The server uses an emotion engine to analyze the user's emotional state from their tone of voice and facial expressions.

[0621] Input: User voice and facial expression data

[0622] Output: The user's emotional state.

[0623] Specific operation: The server uses an SDK for voice and facial expression analysis (e.g., Microsoft Azure Emotion API) to input the user's voice tone and facial expression data into the emotion engine for analysis. The analysis result is the user's emotional state (e.g., tension, relaxation).

[0624] Step 5:

[0625] The server uses generative AI to recommend optimal learning materials based on the analysis results (request content and emotional state).

[0626] Input: Parsed desire and emotional state

[0627] Output: Recommended learning materials

[0628] Specific operation: The server generates and inputs a prompt to the generative AI (e.g. ChatGPT). Example: "Please recommend a relaxing learning video for the next exam." The AI ​​model generates optimal learning materials based on this prompt and returns them to the server.

[0629] Step 6:

[0630] The server generates a response and sends it to the user, who can review the response via their device and access recommended learning materials and reminders.

[0631] Input: Recommended learning material information

[0632] Output: Information displayed on the user's terminal.

[0633] Specific operation: The server sends the recommended learning materials obtained from the generative AI to the user's device. The device displays this information and can read it out loud if necessary. The user checks the displayed recommended materials and uses them.

[0634] In this way, by linking cloud storage, natural language processing, sentiment analysis, and generative AI at each step, we create a system that provides users with optimal learning support.

[0635] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0636] 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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0637] 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 smart glasses 214.

[0638] [Third embodiment]

[0639] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0640] 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.

[0641] 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 wide area network (WAN) and / or a local area network (LAN).

[0642] 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.

[0643] 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 the voice according to instructions from the processor 46.

[0644] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0645] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0646] Fig. 6 shows an example of 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.

[0647] 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.

[0648] 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.

[0649] In the headset type terminal 314, 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.

[0650] 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".

[0651] An embodiment for implementing the present invention includes the following elements.

[0652] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[0653] 2. Database: Where student assignment, project, and / or notebook information is stored.

[0654] 3. Generative AI function as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0655] 4. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[0656] 5. Server: The central processing unit where the cloud storage app, database, and generative AI functions run.

[0657] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, as well as information extraction and support.

[0658] As a concrete example, a user uses a device to access a cloud storage app and saves assignments, projects, and notes in a database. The user then sends a request to a server via the device, and the server extracts relevant information from the saved database and responds to the user's request using generative AI functions. The user receives the response from the server via the device and can obtain the information he or she needs.

[0659] In this way, by combining a cloud storage app, database, generative AI functions, terminals, and servers based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, and to extract and support information.

[0660] The process flow will be explained below.

[0661] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[0662] Step 2: The user sends a request to the server via the terminal.

[0663] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[0664] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[0665] Step 5: The server uses the generative AI capabilities to generate a response that meets the user's request based on the extracted information.

[0666] Step 6: The server sends the generated response to the terminal.

[0667] Step 7: The terminal receives the response from the server and displays it to the user.

[0668] As a specific example, a user uses a terminal to access a cloud storage app and saves math homework in a database (step 1). After that, the user sends a request to a server via the terminal, asking "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Next, the server uses the functions of generative AI to generate a response saying "Tomorrow's math homework is due at 5 p.m." (step 5). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 6 and 7). Note that the response may be output as voice instead of being displayed on the terminal.

[0669] In this way, a user sends a request to a server through a terminal, the server analyzes the request, extracts information from a database, generates a response, and sends the response to the terminal, allowing the user to obtain the information he or she needs.

[0670] Example 1

[0671] 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".

[0672] Conventional education-related information management systems have the problem that information on assignments, projects, and notes is stored in a scattered manner, making efficient management difficult. In addition, the function to remind users of important information such as deadlines and exam dates was insufficient, so users had to take a lot of time and effort to check the information. Furthermore, there was a lack of means to quickly extract the specific information that users were looking for, which resulted in low user convenience.

[0673] 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.

[0674] In this invention, the server includes a means for centrally storing at least one piece of education-related information as an example of pre-registered information in a cloud storage application, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one notification of a deadline, an event date, and an important note as an example of a reminder, and a means for utilizing a generative AI model for searching and extracting related information in response to a user request. This makes it possible to provide an environment in which education-related information can be managed efficiently in a centralized manner and users can check important information such as deadlines and exam dates in a timely manner.

[0675] A "cloud storage application" is an application that centrally stores education-related information on the Internet and allows users to access, manage, and edit information from any device.

[0676] "Education-related information" refers to information including student assignments, projects, notes, and associated time and date information.

[0677] An "interactive machine learning model" is a machine learning model used to extract, analyze, and present information through natural language interactions with a user.

[0678] "Date and time information" refers to date and time information related to assignment deadlines, exam dates, and important notes.

[0679] A "notification" is a means of communication to inform a user of important information (e.g. deadlines or event dates).

[0680] A "generative AI model" is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[0681] "Server" refers to a central processing unit such as a cloud storage application, database, or generative AI model, which processes user requests and provides the necessary information.

[0682] "Database" means a collection of education-related information collected through the Cloud Storage Application that is structured to store, search and retrieve information efficiently.

[0683] A "prompt sentence" refers to a search request or instruction sentence that a user inputs into a cloud storage application using natural language.

[0684] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0685] The present invention is a system that is constructed by elements such as a cloud storage application, education-related information, an interactive machine learning model, information on date and time, notifications, a generative AI model, a server, a database, and prompt sentences, which allows users to efficiently manage education-related information and quickly obtain the information they need.

[0686] 1. System Configuration

[0687] 1.1 Cloud storage applications:

[0688] A cloud storage application is an application that allows users to centrally store educational information on the Internet and access, manage, and edit it from any device. Educational information includes student assignments, projects, notes, and associated time and date information.

[0689] 1.2 Database:

[0690] A database is a structured collection of education-related information collected through cloud storage applications that is stored and made available for efficient search and retrieval.

[0691] 1.3 Interactive Machine Learning Models:

[0692] An interactive machine learning model is a machine learning model used to extract, analyze, and present information through natural language dialogue with a user.

[0693] 1.4 Generative AI Models:

[0694] A generative AI model is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[0695] 1.5 Server:

[0696] A server refers to a central processing unit such as a cloud storage application, database, or generative AI model, and is responsible for processing user requests and providing the necessary information.

[0697] 1.6 Terminal:

[0698] The terminal is a device such as a smartphone or a personal computer that allows a user to operate a cloud storage application. The terminal transmits input information to the server and displays the response from the server to the user.

[0699] 2. How to operate the system

[0700] 2.1 Entering and saving information:

[0701] A user uses a device to access a cloud storage application and inputs education-related information. The input information is sent through the device to a server, which stores the information in a database. Specifically, if a user inputs "Next week's math assignment: Calculus homework, due October 15, 2023," the information is stored in the database.

[0702] 2.2 Requesting and Extracting Information:

[0703] To obtain the desired information, a user inputs a prompt sentence into a cloud storage application. The device sends the input prompt sentence to the server, which uses the generative AI model to analyze and process the prompt sentence. The generative AI model extracts relevant information from the database, and the server sends the results to the device. In concrete terms, if a user inputs "When is next week's assignment due?", the generative AI model extracts information such as "The deadline for next week's math assignment is October 15, 2023," and displays it on the device.

[0704] In this way, the system of the present invention is designed to enable users to efficiently manage education-related information and quickly obtain the information they need. In addition, by utilizing an interactive machine learning model and a generative AI model, it is possible to extract and notify information according to the user's request.

[0705] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0706] Step 1:

[0707] A user inputs education-related information, such as assignments, projects, and notes, into a cloud storage application via the device.

[0708] Specifically, a user enters "Math assignment for next week: Calculus homework, due October 15, 2023." This input includes the name of the assignment, details, and the due date.

[0709] Input: A user inputs education-related information into a cloud storage application.

[0710] Output: The terminal sends the entered information to the server.

[0711] Step 2:

[0712] The terminal transmits the entered information to the server through the cloud storage application.

[0713] The server receives this information and stores it in a database.

[0714] Input: Education-related information sent from the device.

[0715] Output: The server stores the received information in a database.

[0716] Step 3:

[0717] When a user wants to obtain information, they enter a prompt sentence into the cloud storage application.

[0718] For example, a user types, "When is the assignment due next week?"

[0719] Input: The user enters the prompt text into the cloud storage application.

[0720] Output: The terminal sends the prompt text entered to the server.

[0721] Step 4:

[0722] The terminal sends the prompt text entered to the server.

[0723] The server receives the prompt and passes it to the generative AI model.

[0724] Input: The prompt text sent from the terminal.

[0725] Output: The server passes the prompt to the generative AI model.

[0726] Step 5:

[0727] A generative AI model parses the prompt and extracts relevant information from a database.

[0728] For example, in response to the prompt "When is next week's assignment due?", the information extracted is "October 15, 2023."

[0729] Input: Prompt text passed by the server and information stored in the database.

[0730] Output: The generative AI model extracts the relevant information and returns it to the server.

[0731] Step 6:

[0732] The server receives the information obtained from the generative AI model and transmits it to the terminal.

[0733] The server generates a response saying, "Next week's math assignment is due on October 15, 2023," and sends it to the device.

[0734] Input: Information extracted from a generative AI model.

[0735] Output: The server sends the generated response to the terminal.

[0736] Step 7:

[0737] The terminal receives the information sent from the server and displays it to the user through the cloud storage application.

[0738] The user sees the information, "Next week's math assignment is due on October 15, 2023."

[0739] Input: The response sent by the server.

[0740] Output: The terminal displays the response to the user.

[0741] (Application example 1)

[0742] 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."

[0743] In modern factory operations, work schedule management and preventive maintenance management of machinery and equipment are extremely important. However, when these management tasks are performed manually, there is a problem that human error is likely to occur, hindering efficient operation. In addition, in the current system, information such as each work schedule and memos is stored separately, making it difficult to manage them centrally. Furthermore, reminder and schedule management functions are not sufficiently integrated, making it difficult to notify important information in a timely manner. As a result, work efficiency is reduced and preventive maintenance is delayed, increasing risks in factory operations.

[0744] 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.

[0745] In this invention, the server includes a means for centrally storing at least one of information on a user's work, project, and memo, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one reminder of a work deadline, an inspection date, and an important memo, and a means for providing work schedule management and preventive maintenance reminders within the factory. This enables centralized management of work schedules within the factory and efficient reminder notifications, reduces human errors, prevents delays in preventive maintenance, and significantly improves the efficiency and safety of factory operations.

[0746] A "cloud storage app" is an application that stores data on a server on the Internet and can be accessed from multiple devices.

[0747] "User" refers to any individual or entity that uses the cloud storage app.

[0748] "Work" refers to the work or tasks performed in a factory or office.

[0749] "Project" refers to a set of activities planned and carried out to achieve a specific purpose.

[0750] A "memo" is a simple piece of writing or a note that contains important information or records.

[0751] "Centralized storage" refers to the integrated management and storage of multiple data in one place.

[0752] An "interactive machine learning model" refers to an AI technology that uses natural language processing and other techniques to provide information through dialogue with users.

[0753] "Date and time information" refers to information relating to a specific date and time, including work deadlines and inspection dates.

[0754] "Reminders" is a feature that notifies you in advance of important events and tasks.

[0755] "Work schedule management" refers to centralized management of work plans and progress.

[0756] "Preventive maintenance reminder" is a function that notifies users of the need to perform maintenance work on machinery and equipment at the appropriate time.

[0757] A "server" is a computer system that stores data and executes programs.

[0758] The embodiment of the present invention provides a system that manages information on a user's work, projects, and notes in an integrated manner and realizes efficient reminder notifications and schedule management. The following describes how to specifically implement the present invention.

[0759] First, the server uses a cloud storage app to centrally store at least one of the user's work, project, and memo information. The cloud storage app stores data on a server on the Internet and is accessible from multiple devices. By using this application, the user can access and update the data from anywhere.

[0760] Then, an interactive machine learning model (generative AI model) is integrated into the server to extract information about dates and times from the stored database. This model applies natural language processing technology to set at least one reminder for work deadlines, inspection dates, and important notes based on the user's requests. When generating a specific reminder, the interactive machine learning model processes the prompts and generates an appropriate reminder.

[0761] In addition, the server has the function of managing work schedules within the factory and providing preventive maintenance reminders. This function allows users to centrally manage work schedules and receive suggestions to improve the productivity of each worker. The preventive maintenance reminder function notifies users of the need for timely maintenance work on machinery and equipment, preventing breakdowns before they occur.

[0762] As specific examples, the following operations are performed. For example, the server uses AWS S3 and AWS RDS to store and manage data. The generative AI model uses the OpenAI ChatGPT API for natural language processing. The user interface is built using ROS (Robot Operating System) within the factory, and React Native is used for smartphones and tablets. The system is operated via a browser or mobile app.

[0763] An example of a prompt sentence would be generated as follows:

[0764] Example prompt: "Generate a maintenance reminder for equipment ID: equipment_456"

[0765] Expected result: "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly."

[0766] In this way, the server can comprehensively manage users' work and schedule information and utilize the generative AI model to provide reminders and schedule management, thereby supporting efficient factory operations.

[0767] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0768] Step 1:

[0769] A user uses a device to access a cloud storage app. The user inputs and saves task, project, and note information into the app. The input can be in the form of text or files, and the data is stored in AWS S3 on the server. The output is a confirmation message indicating that the data was saved successfully.

[0770] Step 2:

[0771] The server stores the saved data in an AWS RDS database, a relational database that allows information to be organized and efficiently searched. The input is the data sent from the cloud storage app, and the output is the reflected entries in the database.

[0772] Step 3:

[0773] A user sends a reminder setting request containing certain information to the server via a terminal: the input is a natural language request such as "Please set a maintenance reminder", and the output is a confirmation message indicating that the request has been accepted.

[0774] Step 4:

[0775] When the server receives a request, it performs natural language processing using an interactive machine learning model. The input is the request from the user, which is analyzed as text. To process the data, natural language processing technology is used to perform natural language analysis to extract the request content. The output is the analyzed request content.

[0776] Step 5:

[0777] The server extracts relevant date and time information from the stored database based on the parsed request content. For example, it extracts the maintenance date of a specific machine. In this case, the input is the parsed request content, and the output is the relevant date and time information.

[0778] Step 6:

[0779] The server sends a prompt to the generative AI model (OpenAI ChatGPT) to generate an appropriate reminder message. The input is a prompt such as "Generate a maintenance reminder for equipment ID: equipment_456", and the output is the generated result such as "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly".

[0780] Step 7:

[0781] The server sends the generated reminder message to the user's terminal. The input is the generated reminder message, and the output is the notification displayed on the user's terminal.

[0782] Step 8:

[0783] The user checks the reminders on the device and adjusts their work schedule or maintenance plan as necessary, where the input is the reminder message displayed on the device and the output is the adjustment to the user's plan or schedule.

[0784] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0785] An embodiment for implementing the present invention includes the following elements.

[0786] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[0787] 2. Database: Where student assignment, project, and / or notebook information is stored.

[0788] 3. Generative AI function as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0789] 4. Emotion engine: Technology for recognizing and analyzing the user's emotions. It detects changes in tone of voice and facial expressions to understand the user's emotional state.

[0790] 5. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[0791] 6. Server: The central processing unit where the cloud storage app, database, generative AI functions, and emotion engine run.

[0792] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, extraction of information, recognition of emotions, and appropriate responses.

[0793] As a concrete example, a user uses a terminal to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Furthermore, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function customizes the generated response while taking into account the user's emotional state (step 6). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (step 7). In addition to displaying the response on the terminal, the response may be output as voice.

[0794] In this way, by combining a cloud storage app, a database, generative AI functions, an emotion engine, a terminal, and a server based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, information extraction and support, and even emotion recognition and appropriate responses.

[0795] The process flow will be explained below.

[0796] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[0797] Step 2: The user sends a request to the server via the terminal.

[0798] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[0799] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[0800] Step 5: The emotion engine recognizes the user's tone of voice and changes in facial expressions to understand the user's emotional state.

[0801] Step 6: The server leverages its generative AI capabilities to generate a customized response based on the extracted information and the user's emotional state.

[0802] Step 7: The server sends the generated response to the terminal.

[0803] Step 8: The terminal receives the response from the server and displays it to the user.

[0804] As a concrete example, a user uses a terminal to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). At the same time, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function generates a customized response based on the extracted information and the user's emotional state, such as "Tomorrow's math homework is due at 5 p.m., are you okay? Please be careful when you work on it" (step 6). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 7 and 8). In addition to displaying the response on the terminal, the response may be output as voice.

[0805] In this way, a user sends a request to the server through a terminal, the server analyzes the request, extracts information from a database to generate a response, and the emotion engine grasps the user's emotional state and provides a customized response, allowing the user to obtain the information he or she needs and receive an appropriate response.

[0806] Example 2

[0807] 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".

[0808] Modern students have difficulty efficiently managing assignments, projects, and note information in various educational activities and quickly retrieving the necessary information. In addition, stress and emotional fluctuations can reduce learning efficiency, so a system to solve these problems is required. Current technologies require the use of multiple applications and systems, and often lack centralized management and emotion recognition functions.

[0809] 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.

[0810] In this invention, the server includes a means for centrally storing at least one of the information of educational activities in a cloud storage app, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting reminders for important matters, and an emotion engine means for recognizing and analyzing the emotional state of a user to generate an appropriate response. This allows students to centrally manage information, quickly obtain the information they need, and receive support according to their emotional state, thereby improving the efficiency of their learning.

[0811] A "cloud storage app" is an application for centrally storing and managing information about educational activities.

[0812] "Educational activity information" refers to digital data related to learning, such as student assignments, projects, and notes.

[0813] An "interactive machine learning model" is a machine learning model that enables natural language dialogue with the user and has the ability to extract and present relevant information from a stored database.

[0814] "Date and time information" refers to data about assignment deadlines, exam dates, and dates of other important events.

[0815] "Reminder" refers to a function that notifies or warns the user to prevent them from forgetting important dates and times.

[0816] An "emotion engine" refers to technology that detects changes in the user's tone of voice and facial expressions and recognizes and analyzes their emotional state.

[0817] "Server" refers to a central high-performance computer that hosts and processes the cloud storage app, the interactive machine learning models, and the emotion engine.

[0818] "Terminal" refers to a device (such as a smartphone or PC) that a user uses to access and operate a cloud storage app.

[0819] "User request" refers to a request made by a user to confirm information such as assignment deadlines, exam dates, etc.

[0820] "Natural language processing technology" refers to technology that analyzes a user's voice or text input, understands the meaning, and extracts appropriate responses or information.

[0821] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0822] The embodiment of the present invention is composed of multiple elements: a cloud storage application, an interactive machine learning model, an emotion engine, a database, a terminal, and a server.

[0823] Cloud Storage Apps

[0824] A server hosts a cloud storage application, which users access from their devices (smartphones and PCs). As a concrete example of an application, we will use a general cloud storage service. Users use this app to upload and manage their assignments, projects, and notes in digital format.

[0825] Database

[0826] The database exists on the server and is used to centrally manage the information on educational activities saved by users. Specifically, a database management system such as MySQL or PostgreSQL is used. The database stores information such as deadlines for assignments, exam dates, and important notes.

[0827] Interactive Machine Learning Models

[0828] An interactive machine learning model (e.g., a generative AI model) installed on the server is used to analyze requests from users in natural language and extract and present appropriate information. The models used here include high-performance natural language processing models such as ChatGPT. For example, it generates an appropriate answer to a question such as, "What time is the deadline for my math homework tomorrow?"

[0829] Emotion Engine

[0830] The emotion engine runs on the server and detects changes in the user's tone of voice and facial expressions to recognize and analyze the user's emotional state. As a specific technology, for example, the emotion recognition API of Microsoft Azure Cognitive Services is used. This makes it possible to determine whether the user is feeling stressed.

[0831] Terminal

[0832] A device that allows a user to use a cloud storage app. Specifically, it can be a smartphone or a PC. The device provides an interface for the user to send requests to the server and receive and display responses from the server.

[0833] server

[0834] The server is a central high-performance computer that hosts the cloud storage app, the interactive machine learning models, the emotion engine, and the database. The server also receives user requests and performs the appropriate processing to generate a response.

[0835] Examples

[0836] For example, a user uses a smartphone to access a cloud storage app and saves his / her math homework in a database. After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?". The server receives the request, analyzes it using natural language processing technology, and extracts information about the deadline. In addition, an emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state. The generative AI model customizes the generated response while taking into account the user's emotional state. The generated response is sent from the server to the terminal, and the user can check the response on the terminal.

[0837] Through this system, users can centrally manage information about their educational activities and efficiently obtain the information they need. Furthermore, the emotion engine function allows users to receive appropriate support according to their emotional state.

[0838] Example prompt:

[0839] "Describe a scenario where a user uses their smartphone to access a cloud storage app to check deadline information and then receives a stress-based message of encouragement."

[0840] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0841] Step 1:

[0842] The user uses the device to access the cloud storage app and uploads information about educational activities to the database.

[0843] Specifically, a user uploads a file such as a math homework file called "math_homework.docx" using a smartphone or computer. The uploaded file is sent to a server via a cloud storage app, and the server receives the file and stores it in a database.

[0844] Input: File data uploaded by the user

[0845] Output: File data stored in database

[0846] Step 2:

[0847] The user sends a request from the terminal.

[0848] Specifically, the user uses the voice assistant function to ask, "What time is my math homework due tomorrow?" The device converts this voice data into text and sends it to the server via a cloud storage app.

[0849] Input: User's voice request

[0850] Output: Request data in text format

[0851] Step 3:

[0852] The server receives the request and analyzes the request using an interactive machine learning model.

[0853] Specifically, the server analyzes the text "What time is tomorrow's math homework due?" to identify the required information (the due date of the assignment). Here, a generative AI model is used to perform semantic analysis.

[0854] Input: Request data in text format

[0855] Output: Parsed request content

[0856] Step 4:

[0857] The server extracts the required information from the database.

[0858] Specifically, the database is searched for the deadline for "Math Homework" and the data "2023-10-15 17:00" is extracted. In this process, related entries are retrieved from the database based on the analysis results.

[0859] Input: Parsed request content

[0860] Output: Deadline information

[0861] Step 5:

[0862] The server uses an emotion engine to recognize the user's emotional state.

[0863] Specifically, the server analyzes the user's voice data and facial expression images to determine whether the user is feeling stressed. Here, the emotion recognition API is used.

[0864] Input: User's voice data and facial expression images

[0865] Output: Perceived emotional state

[0866] Step 6:

[0867] A generative AI model uses the analyzed data and emotional information to generate a response.

[0868] Specifically, the server uses the generated AI model to generate an appropriate response, "The deadline for your math homework is tomorrow at 5:00 p.m. Good luck!", based on the extracted deadline date and time information and the results of sentiment analysis.

[0869] Input: Deadline information and emotional state information

[0870] Output: The response message to be presented to the user

[0871] Step 7:

[0872] The server sends the generated response to the user's terminal.

[0873] Specifically, the server sends the generated response message to the user's device as a text message via the cloud storage app.

[0874] Input: The generated response message

[0875] Output: The response message displayed on the user's terminal.

[0876] Step 8:

[0877] The user checks the response and sends the request again if necessary.

[0878] Specifically, the user checks the response on their smartphone, and if additional information is needed, they send a new request to the server again using the cloud storage app.

[0879] Input: The response message received from the server.

[0880] Output: A new request by the user (if necessary).

[0881] (Application example 2)

[0882] 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".

[0883] Conventional cloud storage systems allow for centralized management of students' learning content and the setting of reminders, but in order to maximize learning effectiveness, it is necessary to recommend appropriate content according to the user's emotional state and learning situation. However, conventional systems lack the functionality to recognize the user's emotions and recommend learning materials, making it difficult to improve learning efficiency. Therefore, the present invention aims to provide a system that improves learning efficiency by recognizing the user's emotions and recommending appropriate learning materials.

[0884] 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.

[0885] In this invention, the server includes a means for centrally storing at least one of the pieces of information in the cloud storage app, a means for integrating the functions of an interactive machine learning model, extracting information on date and time from the stored database, and setting a reminder, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for recommending learning materials and generating reminders using generative AI. This makes it possible to provide optimal learning materials and generate reminders while taking into account the user's emotional state.

[0886] (definition statement)

[0887] A "cloud storage app" is an application that stores and manages data on the Internet and can be accessed from various devices.

[0888] An "interactive machine learning model" is a machine learning model that interacts with the user in a dialogue format and analyzes and generates information using natural language processing technology.

[0889] An "emotion engine" is a technology that recognizes and judges a user's emotional state by analyzing data such as their voice tone and facial expressions.

[0890] "Generative AI" is an AI technology that generates natural-looking sentences and answers in response to user requests.

[0891] "Centralized information storage" refers to the means of managing data such as assignments, projects, and notes in one place on the cloud.

[0892] "Setting a reminder" is a means for notifying the user at an appropriate time based on date and time information extracted from the database.

[0893] "Recommend learning materials" is a function that takes into account the user's learning situation and emotional state and provides the most appropriate learning videos and materials.

[0894] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[0895] The system that realizes this invention is composed of a cloud storage app, an interactive machine learning model, an emotion engine, and a generative AI. Users access it via their terminals (smartphones or PCs) and manage and recommend learning materials.

[0896] Program processing explanation

[0897] Cloud Storage:

[0898] The server runs a cloud storage app and centrally stores the data of assignments, projects, and notes uploaded by users. An SDK for cloud storage (e.g. Google Cloud Storage SDK) is used.

[0899] Interactive Machine Learning Models:

[0900] The server integrates an interactive machine learning model to analyze user requests using natural language processing techniques. The model uses generative AI (e.g. ChatGPT) to generate appropriate responses to user requests.

[0901] Emotion Engine:

[0902] The server uses an emotion engine to analyze the user's emotional state from their voice tone and facial expression data. An SDK for emotion analysis (e.g. Microsoft Azure Emotion API) is used.

[0903] Generative AI:

[0904] The server uses generative AI to recommend appropriate learning materials and generate reminders based on the user's learning status and emotional state. In this process, it generates prompt sentences and inputs them into the AI ​​model.

[0905] Examples

[0906] For example, a user can use a device to access a cloud storage app, upload a biology video lecture, and then request, "Tell me about a video that will help me prepare for the exam." The server can then use generative AI to respond with, "Here's a video that will help me prepare for the exam." The emotion engine can also detect tension in the user's tone of voice and generate a response to relax the user. Reminders can also be set for upcoming exams and assignment deadlines.

[0907] Examples of prompt statements

[0908] "Can you tell me which video would be helpful for my next biology exam?"

[0909] In this way, the system of the present invention can provide users with an optimal learning experience by combining centralized data management, sentiment analysis, and natural language processing.

[0910] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0911] Program processing flow

[0912] Step 1:

[0913] A user uses a device to access a cloud storage app and uploads learning materials (e.g., video lectures and notes).

[0914] Input: Study materials (videos, notes, projects)

[0915] Output: Data stored in cloud storage

[0916] Specific operation: The user drags and drops the learning materials saved on the device to the cloud storage app and clicks the upload button. The server stores the received data in the cloud storage.

[0917] Step 2:

[0918] A user uses the device to input requests for study content and reminders (e.g., "Tell me which videos would be helpful for my next exam").

[0919] Input: User request (natural language question or instruction)

[0920] Output: The request data sent to the server.

[0921] Specific behavior: The user makes a request by voice or keyboard input, and the device sends this input to the server.

[0922] Step 3:

[0923] The server analyzes the received user request using natural language processing technology to understand the intent of the request.

[0924] Input: User request data

[0925] Output: Parsed request (intent and required information)

[0926] How it works: The server uses a natural language processing model (e.g. ChatGPT) to analyze the user's request and understand its intent, extracting keywords and important information from the request.

[0927] Step 4:

[0928] The server uses an emotion engine to analyze the user's emotional state from their tone of voice and facial expressions.

[0929] Input: User voice and facial expression data

[0930] Output: The user's emotional state.

[0931] Specific operation: The server uses an SDK for voice and facial expression analysis (e.g., Microsoft Azure Emotion API) to input the user's voice tone and facial expression data into the emotion engine for analysis. The analysis result is the user's emotional state (e.g., tension, relaxation).

[0932] Step 5:

[0933] The server uses generative AI to recommend optimal learning materials based on the analysis results (request content and emotional state).

[0934] Input: Parsed desire and emotional state

[0935] Output: Recommended learning materials

[0936] Specific operation: The server generates and inputs a prompt to the generative AI (e.g. ChatGPT). Example: "Please recommend a relaxing learning video for the next exam." The AI ​​model generates optimal learning materials based on this prompt and returns them to the server.

[0937] Step 6:

[0938] The server generates a response and sends it to the user, who can review the response via their device and access recommended learning materials and reminders.

[0939] Input: Recommended learning material information

[0940] Output: Information displayed on the user's terminal.

[0941] Specific operation: The server sends the recommended learning materials obtained from the generative AI to the user's device. The device displays this information and can read it out loud if necessary. The user checks the displayed recommended materials and uses them.

[0942] In this way, by linking cloud storage, natural language processing, sentiment analysis, and generative AI at each step, we create a system that provides users with optimal learning support.

[0943] 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 voice indicating a user input for 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.

[0944] 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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0945] 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.

[0946] [Fourth embodiment]

[0947] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0948] 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.

[0949] 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 wide area network (WAN) and / or a local area network (LAN).

[0950] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0951] 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 the voice according to instructions from the processor 46.

[0952] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0953] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0954] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[0955] Fig. 8 shows an example of 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.

[0956] 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.

[0957] 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.

[0958] In the robot 414, 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.

[0959] Next, a description will be given of the specific processing 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".

[0960] An embodiment for implementing the present invention includes the following elements.

[0961] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[0962] 2. Database: Where student assignment, project, and / or notebook information is stored.

[0963] 3. Generative AI function as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology and provides support according to user requests, such as extracting information about dates and times from a stored database and setting at least one reminder for assignment deadlines, exam dates, and important notes.

[0964] 4. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[0965] 5. Server: The central processing unit where the cloud storage app, database, and generative AI functions run.

[0966] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, as well as information extraction and support.

[0967] As a concrete example, a user uses a device to access a cloud storage app and saves assignments, projects, and notes in a database. The user then sends a request to a server via the device, and the server extracts relevant information from the saved database and responds to the user's request using generative AI functions. The user receives the response from the server via the device and can obtain the information he or she needs.

[0968] In this way, by combining a cloud storage app, database, generative AI functions, terminals, and servers based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, and to extract and support information.

[0969] The process flow will be explained below.

[0970] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[0971] Step 2: The user sends a request to the server via the terminal.

[0972] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[0973] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[0974] Step 5: The server uses the generative AI capabilities to generate a response that meets the user's request based on the extracted information.

[0975] Step 6: The server sends the generated response to the terminal.

[0976] Step 7: The terminal receives the response from the server and displays it to the user.

[0977] As a specific example, a user uses a terminal to access a cloud storage app and saves math homework in a database (step 1). After that, the user sends a request to a server via the terminal, asking "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Next, the server uses the functions of generative AI to generate a response saying "Tomorrow's math homework is due at 5 p.m." (step 5). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 6 and 7). Note that the response may be output as voice instead of being displayed on the terminal.

[0978] In this way, a user sends a request to a server through a terminal, the server analyzes the request, extracts information from a database, generates a response, and sends the response to the terminal, allowing the user to obtain the information he or she needs.

[0979] Example 1

[0980] Next, a description will be given of Example 1. In the following description, the data processing device 12 is referred to as a "server" and the robot 414 is referred to as a "terminal."

[0981] Conventional education-related information management systems have the problem that information on assignments, projects, and notes is stored in a scattered manner, making efficient management difficult. In addition, the function to remind users of important information such as deadlines and exam dates was insufficient, so users had to take a lot of time and effort to check the information. Furthermore, there was a lack of means to quickly extract the specific information that users were looking for, which resulted in low user convenience.

[0982] 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.

[0983] In this invention, the server includes a means for centrally storing at least one piece of education-related information as an example of pre-registered information in a cloud storage application, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one notification of a deadline, an event date, and an important note as an example of a reminder, and a means for utilizing a generative AI model for searching and extracting related information in response to a user request. This makes it possible to provide an environment in which education-related information can be managed efficiently in a centralized manner and users can check important information such as deadlines and exam dates in a timely manner.

[0984] A "cloud storage application" is an application that centrally stores education-related information on the Internet and allows users to access, manage, and edit information from any device.

[0985] "Education-related information" refers to information including student assignments, projects, notes, and associated time and date information.

[0986] An "interactive machine learning model" is a machine learning model used to extract, analyze, and present information through natural language interactions with a user.

[0987] "Date and time information" refers to date and time information related to assignment deadlines, exam dates, and important notes.

[0988] A "notification" is a means of communication to inform a user of important information (e.g. deadlines or event dates).

[0989] A "generative AI model" is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[0990] "Server" refers to a central processing unit such as a cloud storage application, database, or generative AI model, which processes user requests and provides the necessary information.

[0991] "Database" means a collection of education-related information collected through the Cloud Storage Application that is structured to store, search and retrieve information efficiently.

[0992] A "prompt sentence" refers to a search request or instruction sentence that a user inputs into a cloud storage application using natural language.

[0993] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0994] The present invention is a system that is constructed by elements such as a cloud storage application, education-related information, an interactive machine learning model, information on date and time, notifications, a generative AI model, a server, a database, and prompt sentences, which allows users to efficiently manage education-related information and quickly obtain the information they need.

[0995] 1. System Configuration

[0996] 1.1 Cloud storage applications:

[0997] A cloud storage application is an application that allows users to centrally store educational information on the Internet and access, manage, and edit it from any device. Educational information includes student assignments, projects, notes, and associated time and date information.

[0998] 1.2 Database:

[0999] A database is a structured collection of education-related information collected through cloud storage applications that is stored and made available for efficient search and retrieval.

[1000] 1.3 Interactive Machine Learning Models:

[1001] An interactive machine learning model is a machine learning model used to extract, analyze, and present information through natural language dialogue with a user.

[1002] 1.4 Generative AI Models:

[1003] A generative AI model is an artificial intelligence model that automatically extracts and provides information from a stored database in response to a user's request.

[1004] 1.5 Server:

[1005] A server refers to a central processing unit such as a cloud storage application, database, or generative AI model, and is responsible for processing user requests and providing the necessary information.

[1006] 1.6 Terminal:

[1007] The terminal is a device such as a smartphone or a personal computer that allows a user to operate a cloud storage application. The terminal transmits input information to the server and displays the response from the server to the user.

[1008] 2. How to operate the system

[1009] 2.1 Entering and saving information:

[1010] A user uses a device to access a cloud storage application and inputs education-related information. The input information is sent through the device to a server, which stores the information in a database. Specifically, if a user inputs "Next week's math assignment: Calculus homework, due October 15, 2023," the information is stored in the database.

[1011] 2.2 Requesting and Extracting Information:

[1012] To obtain the desired information, a user inputs a prompt sentence into a cloud storage application. The device sends the input prompt sentence to the server, which uses the generative AI model to analyze and process the prompt sentence. The generative AI model extracts relevant information from the database, and the server sends the results to the device. In concrete terms, if a user inputs "When is next week's assignment due?", the generative AI model extracts information such as "The deadline for next week's math assignment is October 15, 2023," and displays it on the device.

[1013] In this way, the system of the present invention is designed to enable users to efficiently manage education-related information and quickly obtain the information they need. In addition, by utilizing an interactive machine learning model and a generative AI model, it is possible to extract and notify information according to the user's request.

[1014] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1015] Step 1:

[1016] A user inputs education-related information, such as assignments, projects, and notes, into a cloud storage application via the device.

[1017] Specifically, a user enters "Math assignment for next week: Calculus homework, due October 15, 2023." This input includes the name of the assignment, details, and the due date.

[1018] Input: A user inputs education-related information into a cloud storage application.

[1019] Output: The terminal sends the entered information to the server.

[1020] Step 2:

[1021] The terminal transmits the entered information to the server through the cloud storage application.

[1022] The server receives this information and stores it in a database.

[1023] Input: Education-related information sent from the device.

[1024] Output: The server stores the received information in a database.

[1025] Step 3:

[1026] When a user wants to obtain information, they enter a prompt sentence into the cloud storage application.

[1027] For example, a user types, "When is the assignment due next week?"

[1028] Input: The user enters the prompt text into the cloud storage application.

[1029] Output: The terminal sends the prompt text entered to the server.

[1030] Step 4:

[1031] The terminal sends the prompt text entered to the server.

[1032] The server receives the prompt and passes it to the generative AI model.

[1033] Input: The prompt text sent from the terminal.

[1034] Output: The server passes the prompt to the generative AI model.

[1035] Step 5:

[1036] A generative AI model parses the prompt and extracts relevant information from a database.

[1037] For example, in response to the prompt "When is next week's assignment due?", the information extracted is "October 15, 2023."

[1038] Input: Prompt text passed by the server and information stored in the database.

[1039] Output: The generative AI model extracts the relevant information and returns it to the server.

[1040] Step 6:

[1041] The server receives the information obtained from the generative AI model and transmits it to the terminal.

[1042] The server generates a response saying, "Next week's math assignment is due on October 15, 2023," and sends it to the device.

[1043] Input: Information extracted from a generative AI model.

[1044] Output: The server sends the generated response to the terminal.

[1045] Step 7:

[1046] The terminal receives the information sent from the server and displays it to the user through the cloud storage application.

[1047] The user sees the information, "Next week's math assignment is due on October 15, 2023."

[1048] Input: The response sent by the server.

[1049] Output: The terminal displays the response to the user.

[1050] (Application example 1)

[1051] 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."

[1052] In modern factory operations, work schedule management and preventive maintenance management of machinery and equipment are extremely important. However, when these management tasks are performed manually, there is a problem that human error is likely to occur, hindering efficient operation. In addition, in the current system, information such as each work schedule and memos is stored separately, making it difficult to manage them centrally. Furthermore, reminder and schedule management functions are not sufficiently integrated, making it difficult to notify important information in a timely manner. As a result, work efficiency is reduced and preventive maintenance is delayed, increasing risks in factory operations.

[1053] 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.

[1054] In this invention, the server includes a means for centrally storing at least one of information on a user's work, project, and memo, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting at least one reminder of a work deadline, an inspection date, and an important memo, and a means for providing work schedule management and preventive maintenance reminders within the factory. This enables centralized management of work schedules within the factory and efficient reminder notifications, reduces human errors, prevents delays in preventive maintenance, and significantly improves the efficiency and safety of factory operations.

[1055] A "cloud storage app" is an application that stores data on a server on the Internet and can be accessed from multiple devices.

[1056] "User" refers to any individual or entity that uses the cloud storage app.

[1057] "Work" refers to the work or tasks performed in a factory or office.

[1058] "Project" refers to a set of activities planned and carried out to achieve a specific purpose.

[1059] A "memo" is a simple piece of writing or a note that contains important information or records.

[1060] "Centralized storage" refers to the integrated management and storage of multiple data in one place.

[1061] An "interactive machine learning model" refers to an AI technology that uses natural language processing and other techniques to provide information through dialogue with users.

[1062] "Date and time information" refers to information relating to a specific date and time, including work deadlines and inspection dates.

[1063] "Reminders" is a feature that notifies you in advance of important events and tasks.

[1064] "Work schedule management" refers to centralized management of work plans and progress.

[1065] "Preventive maintenance reminder" is a function that notifies users of the need to perform maintenance work on machinery and equipment at the appropriate time.

[1066] A "server" is a computer system that stores data and executes programs.

[1067] The embodiment of the present invention provides a system that manages information on a user's work, projects, and notes in an integrated manner and realizes efficient reminder notifications and schedule management. The following describes how to specifically implement the present invention.

[1068] First, the server uses a cloud storage app to centrally store at least one of the user's work, project, and memo information. The cloud storage app stores data on a server on the Internet and is accessible from multiple devices. By using this application, the user can access and update the data from anywhere.

[1069] Then, an interactive machine learning model (generative AI model) is integrated into the server to extract information about dates and times from the stored database. This model applies natural language processing technology to set at least one reminder for work deadlines, inspection dates, and important notes based on the user's requests. When generating a specific reminder, the interactive machine learning model processes the prompts and generates an appropriate reminder.

[1070] In addition, the server has the function of managing work schedules within the factory and providing preventive maintenance reminders. This function allows users to centrally manage work schedules and receive suggestions to improve the productivity of each worker. The preventive maintenance reminder function notifies users of the need for timely maintenance work on machinery and equipment, preventing breakdowns before they occur.

[1071] As specific examples, the following operations are performed. For example, the server uses AWS S3 and AWS RDS to store and manage data. The generative AI model uses the OpenAI ChatGPT API for natural language processing. The user interface is built using ROS (Robot Operating System) within the factory, and React Native is used for smartphones and tablets. The system is operated via a browser or mobile app.

[1072] An example of a prompt sentence would be generated as follows:

[1073] Example prompt: "Generate a maintenance reminder for equipment ID: equipment_456"

[1074] Expected result: "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly."

[1075] In this way, the server can comprehensively manage users' work and schedule information and utilize the generative AI model to provide reminders and schedule management, thereby supporting efficient factory operations.

[1076] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1077] Step 1:

[1078] A user uses a device to access a cloud storage app. The user inputs and saves task, project, and note information into the app. The input can be in the form of text or files, and the data is stored in AWS S3 on the server. The output is a confirmation message indicating that the data was saved successfully.

[1079] Step 2:

[1080] The server stores the saved data in an AWS RDS database, a relational database that allows information to be organized and efficiently searched. The input is the data sent from the cloud storage app, and the output is the reflected entries in the database.

[1081] Step 3:

[1082] A user sends a reminder setting request containing certain information to the server via a terminal: the input is a natural language request such as "Please set a maintenance reminder", and the output is a confirmation message indicating that the request has been accepted.

[1083] Step 4:

[1084] When the server receives a request, it performs natural language processing using an interactive machine learning model. The input is the request from the user, which is analyzed as text. To process the data, natural language processing technology is used to perform natural language analysis to extract the request content. The output is the analyzed request content.

[1085] Step 5:

[1086] The server extracts relevant date and time information from the stored database based on the parsed request content. For example, it extracts the maintenance date of a specific machine. In this case, the input is the parsed request content, and the output is the relevant date and time information.

[1087] Step 6:

[1088] The server sends a prompt to the generative AI model (OpenAI ChatGPT) to generate an appropriate reminder message. The input is a prompt such as "Generate a maintenance reminder for equipment ID: equipment_456", and the output is the generated result such as "Equipment ID: equipment_456 will require routine maintenance within the next 30 days. Please schedule maintenance activities accordingly".

[1089] Step 7:

[1090] The server sends the generated reminder message to the user's terminal. The input is the generated reminder message, and the output is the notification displayed on the user's terminal.

[1091] Step 8:

[1092] The user checks the reminders on the device and adjusts their work schedule or maintenance plan as necessary, where the input is the reminder message displayed on the device and the output is the adjustment to the user's plan or schedule.

[1093] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[1094] An embodiment for implementing the present invention includes the following elements.

[1095] 1. Cloud Storage App: An application for centrally storing student assignment, project, and / or note information.

[1096] 2. Database: Where student assignment, project, and / or notebook information is stored.

[1097] 3. Generative AI functionality as an example of a conversational machine learning model: A conversational AI model that applies natural language processing technology to extract information about dates and times from a stored database and provide support according to user requests, such as setting at least one reminder for assignment deadlines, exam dates, and important notes.

[1098] 4. Emotion engine: Technology for recognizing and analyzing the user's emotions. It detects changes in tone of voice and facial expressions to understand the user's emotional state.

[1099] 5. Terminal: The device (smartphone, computer, etc.) that a user uses to operate the cloud storage app.

[1100] 6. Server: The central processing unit where the cloud storage app, database, generative AI functions, and emotion engine run.

[1101] The above is an embodiment of the present invention. By constructing and operating a system in accordance with this embodiment, it is possible to realize unified management of students' assignments, projects, and notes, extraction of information, recognition of emotions, and appropriate responses.

[1102] As a concrete example, a user uses a device to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the device, asking "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes it using natural language processing technology, and extracts information about the deadline (steps 3 and 4). Furthermore, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function customizes the generated response while taking into account the user's emotional state (step 6). The generated response is sent from the server to the device, and the user can check the response on the device (step 7).

[1103] In this way, by combining a cloud storage app, a database, generative AI functions, an emotion engine, a terminal, and a server based on the form for implementing the present invention, it is possible to realize management of students' assignments, projects, and notes, information extraction and support, and even emotion recognition and appropriate responses.

[1104] The process flow will be explained below.

[1105] Step 1: A user uses a device to access a cloud storage app and saves an assignment, project, or note to a database.

[1106] Step 2: The user sends a request to the server via the terminal.

[1107] Step 3: The server receives the user's request and parses the request using natural language processing techniques.

[1108] Step 4: Based on the analysis results, the server extracts relevant information from the stored database.

[1109] Step 5: The emotion engine recognizes the user's tone of voice and changes in facial expressions to understand the user's emotional state.

[1110] Step 6: The server leverages its generative AI capabilities to generate a customized response based on the extracted information and the user's emotional state.

[1111] Step 7: The server sends the generated response to the terminal.

[1112] Step 8: The terminal receives the response from the server and displays it to the user.

[1113] As a concrete example, a user uses a terminal to access a cloud storage app and saves his / her math homework in a database (step 1). After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?" (step 2). The server receives the request, analyzes the request using natural language processing technology, and extracts information about the deadline (steps 3 and 4). At the same time, the emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state (step 5). The generative AI function generates a customized response based on the extracted information and the user's emotional state, such as "Tomorrow's math homework is due at 5 p.m., are you okay? Please be careful when you work on it" (step 6). The generated response is sent from the server to the terminal, and the user can check the response on the terminal (steps 7 and 8). In addition to displaying the response on the terminal, the response may be output as voice.

[1114] In this way, a user sends a request to the server through a terminal, the server analyzes the request, extracts information from a database to generate a response, and the emotion engine grasps the user's emotional state and provides a customized response, allowing the user to obtain the information he or she needs and receive an appropriate response.

[1115] Example 2

[1116] Next, a description will be given of Example 2. In the following description, the data processing device 12 is referred to as a "server" and the robot 414 is referred to as a "terminal."

[1117] Modern students have difficulty efficiently managing assignments, projects, and note information in various educational activities and quickly retrieving the necessary information. In addition, stress and emotional fluctuations can reduce learning efficiency, so a system to solve these problems is required. Current technologies require the use of multiple applications and systems, and often lack centralized management and emotion recognition functions.

[1118] 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.

[1119] In this invention, the server includes a means for centrally storing at least one of the information of educational activities in a cloud storage app, a means for integrating the function of an interactive machine learning model, extracting information on date and time from the stored database, and setting reminders for important matters, and an emotion engine means for recognizing and analyzing the emotional state of a user to generate an appropriate response. This allows students to centrally manage information, quickly obtain the information they need, and receive support according to their emotional state, thereby improving the efficiency of their learning.

[1120] A "cloud storage app" is an application for centrally storing and managing information about educational activities.

[1121] "Educational activity information" refers to digital data related to learning, such as student assignments, projects, and notes.

[1122] An "interactive machine learning model" is a machine learning model that enables natural language dialogue with the user and has the ability to extract and present relevant information from a stored database.

[1123] "Date and time information" refers to data about assignment deadlines, exam dates, and dates of other important events.

[1124] "Reminder" refers to a function that notifies or warns the user to prevent them from forgetting important dates and times.

[1125] An "emotion engine" refers to technology that detects changes in the user's tone of voice and facial expressions and recognizes and analyzes their emotional state.

[1126] "Server" refers to a central high-performance computer that hosts and processes the cloud storage app, the interactive machine learning models, and the emotion engine.

[1127] "Terminal" refers to a device (such as a smartphone or PC) that a user uses to access and operate a cloud storage app.

[1128] "User request" refers to a request made by a user to confirm information such as assignment deadlines, exam dates, etc.

[1129] "Natural language processing technology" refers to technology that analyzes a user's voice or text input, understands the meaning, and extracts appropriate responses or information.

[1130] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1131] The embodiment of the present invention is composed of multiple elements: a cloud storage application, an interactive machine learning model, an emotion engine, a database, a terminal, and a server.

[1132] Cloud Storage Apps

[1133] A server hosts a cloud storage application, which users access from their devices (smartphones and PCs). As a concrete example of an application, we will use a general cloud storage service. Users use this app to upload and manage their assignments, projects, and notes in digital format.

[1134] Database

[1135] The database exists on the server and is used to centrally manage the information on educational activities saved by users. Specifically, a database management system such as MySQL or PostgreSQL is used. The database stores information such as deadlines for assignments, exam dates, and important notes.

[1136] Interactive Machine Learning Models

[1137] An interactive machine learning model (e.g., a generative AI model) installed on the server is used to analyze requests from users in natural language and extract and present appropriate information. The models used here include high-performance natural language processing models such as ChatGPT. For example, it generates an appropriate answer to a question such as, "What time is the deadline for my math homework tomorrow?"

[1138] Emotion Engine

[1139] The emotion engine runs on the server and detects changes in the user's tone of voice and facial expressions to recognize and analyze the user's emotional state. As a specific technology, for example, the emotion recognition API of Microsoft Azure Cognitive Services is used. This makes it possible to determine whether the user is feeling stressed.

[1140] Terminal

[1141] A device that allows a user to use a cloud storage app. Specifically, it can be a smartphone or a PC. The device provides an interface for the user to send requests to the server and receive and display responses from the server.

[1142] server

[1143] The server is a central high-performance computer that hosts the cloud storage app, the interactive machine learning models, the emotion engine, and the database. The server also receives user requests and performs the appropriate processing to generate a response.

[1144] Examples

[1145] For example, a user uses a smartphone to access a cloud storage app and saves his / her math homework in a database. After that, the user sends a request to the server via the terminal, such as "What time is the deadline for tomorrow's math homework?". The server receives the request, analyzes it using natural language processing technology, and extracts information about the deadline. In addition, an emotion engine recognizes the user's tone of voice and changes in facial expression to grasp the user's emotional state. The generative AI model customizes the generated response while taking into account the user's emotional state. The generated response is sent from the server to the terminal, and the user can check the response on the terminal.

[1146] Through this system, users can centrally manage information about their educational activities and efficiently obtain the information they need. Furthermore, the emotion engine function allows users to receive appropriate support according to their emotional state.

[1147] Example prompt:

[1148] "Describe a scenario where a user uses their smartphone to access a cloud storage app to check deadline information and then receives a stress-based message of encouragement."

[1149] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1150] Step 1:

[1151] The user uses the device to access the cloud storage app and uploads information about educational activities to the database.

[1152] Specifically, a user uploads a file such as a math homework file called "math_homework.docx" using a smartphone or computer. The uploaded file is sent to a server via a cloud storage app, and the server receives the file and stores it in a database.

[1153] Input: File data uploaded by the user

[1154] Output: File data stored in database

[1155] Step 2:

[1156] The user sends a request from the terminal.

[1157] Specifically, the user uses the voice assistant function to ask, "What time is my math homework due tomorrow?" The device converts this voice data into text and sends it to the server via a cloud storage app.

[1158] Input: User's voice request

[1159] Output: Request data in text format

[1160] Step 3:

[1161] The server receives the request and analyzes the request using an interactive machine learning model.

[1162] Specifically, the server analyzes the text "What time is tomorrow's math homework due?" to identify the required information (the due date of the assignment). Here, a generative AI model is used to perform semantic analysis.

[1163] Input: Request data in text format

[1164] Output: Parsed request content

[1165] Step 4:

[1166] The server extracts the required information from the database.

[1167] Specifically, the database is searched for the deadline for "Math Homework" and the data "2023-10-15 17:00" is extracted. In this process, related entries are retrieved from the database based on the analysis results.

[1168] Input: Parsed request content

[1169] Output: Deadline information

[1170] Step 5:

[1171] The server uses an emotion engine to recognize the user's emotional state.

[1172] Specifically, the server analyzes the user's voice data and facial expression images to determine whether the user is feeling stressed. Here, the emotion recognition API is used.

[1173] Input: User's voice data and facial expression images

[1174] Output: Perceived emotional state

[1175] Step 6:

[1176] A generative AI model uses the analyzed data and emotional information to generate a response.

[1177] Specifically, the server uses the generated AI model to generate an appropriate response, "The deadline for your math homework is tomorrow at 5:00 p.m. Good luck!", based on the extracted deadline date and time information and the results of sentiment analysis.

[1178] Input: Deadline information and emotional state information

[1179] Output: The response message to be presented to the user

[1180] Step 7:

[1181] The server sends the generated response to the user's terminal.

[1182] Specifically, the server sends the generated response message to the user's device as a text message via the cloud storage app.

[1183] Input: The generated response message

[1184] Output: The response message displayed on the user's terminal.

[1185] Step 8:

[1186] The user checks the response and sends the request again if necessary.

[1187] Specifically, the user checks the response on their smartphone, and if additional information is needed, they send a new request to the server again using the cloud storage app.

[1188] Input: The response message received from the server.

[1189] Output: A new request by the user (if necessary).

[1190] (Application example 2)

[1191] 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".

[1192] Conventional cloud storage systems allow for centralized management of students' learning content and the setting of reminders, but in order to maximize learning effectiveness, it is necessary to recommend appropriate content according to the user's emotional state and learning situation. However, conventional systems lack the functionality to recognize the user's emotions and recommend learning materials, making it difficult to improve learning efficiency. Therefore, the present invention aims to provide a system that improves learning efficiency by recognizing the user's emotions and recommending appropriate learning materials.

[1193] 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.

[1194] In this invention, the server includes a means for centrally storing at least one of the pieces of information in the cloud storage app, a means for integrating the functions of an interactive machine learning model, extracting information on date and time from the stored database, and setting a reminder, a means for recognizing and analyzing the user's emotions using an emotion engine, and a means for recommending learning materials and generating reminders using generative AI. This makes it possible to provide optimal learning materials and generate reminders while taking into account the user's emotional state.

[1195] (definition statement)

[1196] A "cloud storage app" is an application that stores and manages data on the Internet and can be accessed from various devices.

[1197] An "interactive machine learning model" is a machine learning model that interacts with the user in a dialogue format and analyzes and generates information using natural language processing technology.

[1198] An "emotion engine" is a technology that recognizes and judges a user's emotional state by analyzing data such as their voice tone and facial expressions.

[1199] "Generative AI" is an AI technology that generates natural-looking sentences and answers in response to user requests.

[1200] "Centralized information storage" refers to the means of managing data such as assignments, projects, and notes in one place on the cloud.

[1201] "Setting a reminder" is a means for notifying the user at an appropriate time based on date and time information extracted from the database.

[1202] "Recommend learning materials" is a function that takes into account the user's learning situation and emotional state and provides the most appropriate learning videos and materials.

[1203] "Natural language processing technology" is a technology that enables computers to understand, generate, and analyze human language.

[1204] The system that realizes this invention is composed of a cloud storage app, an interactive machine learning model, an emotion engine, and a generative AI. Users access it via their terminals (smartphones or PCs) and manage and recommend learning materials.

[1205] Program processing explanation

[1206] Cloud Storage:

[1207] The server runs a cloud storage app and centrally stores the data of assignments, projects, and notes uploaded by users. An SDK for cloud storage (e.g. Google Cloud Storage SDK) is used.

[1208] Interactive Machine Learning Models:

[1209] The server integrates an interactive machine learning model to analyze user requests using natural language processing techniques. The model uses generative AI (e.g. ChatGPT) to generate appropriate responses to user requests.

[1210] Emotion Engine:

[1211] The server uses an emotion engine to analyze the user's emotional state from their voice tone and facial expression data. An SDK for emotion analysis (e.g. Microsoft Azure Emotion API) is used.

[1212] Generative AI:

[1213] The server uses generative AI to recommend appropriate learning materials and generate reminders based on the user's learning status and emotional state. In this process, it generates prompt sentences and inputs them into the AI ​​model.

[1214] Examples

[1215] For example, a user can use a device to access a cloud storage app, upload a biology video lecture, and then request, "Tell me about a video that will help me prepare for the exam." The server can then use generative AI to respond with, "Here's a video that will help me prepare for the exam." The emotion engine can also detect tension in the user's tone of voice and generate a response to relax the user. Reminders can also be set for upcoming exams and assignment deadlines.

[1216] Examples of prompt statements

[1217] "Can you tell me which video would be helpful for my next biology exam?"

[1218] In this way, the system of the present invention can provide users with an optimal learning experience by combining centralized data management, sentiment analysis, and natural language processing.

[1219] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1220] Program processing flow

[1221] Step 1:

[1222] A user uses a device to access a cloud storage app and uploads learning materials (e.g., video lectures and notes).

[1223] Input: Study materials (videos, notes, projects)

[1224] Output: Data stored in cloud storage

[1225] Specific operation: The user drags and drops the learning materials saved on the device to the cloud storage app and clicks the upload button. The server stores the received data in the cloud storage.

[1226] Step 2:

[1227] A user uses the device to input requests for study content and reminders (e.g., "Tell me which videos would be helpful for my next exam").

[1228] Input: User request (natural language question or instruction)

[1229] Output: The request data sent to the server.

[1230] Specific behavior: The user makes a request by voice or keyboard input, and the device sends this input to the server.

[1231] Step 3:

[1232] The server analyzes the received user request using natural language processing technology to understand the intent of the request.

[1233] Input: User request data

[1234] Output: Parsed request (intent and required information)

[1235] How it works: The server uses a natural language processing model (e.g. ChatGPT) to analyze the user's request and understand its intent, extracting keywords and important information from the request.

[1236] Step 4:

[1237] The server uses an emotion engine to analyze the user's emotional state from their tone of voice and facial expressions.

[1238] Input: User voice and facial expression data

[1239] Output: The user's emotional state.

[1240] Specific operation: The server uses an SDK for voice and facial expression analysis (e.g., Microsoft Azure Emotion API) to input the user's voice tone and facial expression data into the emotion engine for analysis. The analysis result is the user's emotional state (e.g., tension, relaxation).

[1241] Step 5:

[1242] The server uses generative AI to recommend optimal learning materials based on the analysis results (request content and emotional state).

[1243] Input: Parsed desire and emotional state

[1244] Output: Recommended learning materials

[1245] Specific operation: The server generates and inputs a prompt to the generative AI (e.g. ChatGPT). Example: "Please recommend a relaxing learning video for the next exam." The AI ​​model generates optimal learning materials based on this prompt and returns them to the server.

[1246] Step 6:

[1247] The server generates a response and sends it to the user, who can review the response via their device and access recommended learning materials and reminders.

[1248] Input: Recommended learning material information

[1249] Output: Information displayed on the user's terminal.

[1250] Specific operation: The server sends the recommended learning materials obtained from the generative AI to the user's device. The device displays this information and can read it out loud if necessary. The user checks the displayed recommended materials and uses them.

[1251] In this way, by linking cloud storage, natural language processing, sentiment analysis, and generative AI at each step, we create a system that provides users with optimal learning support.

[1252] 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 a voice indicating a user input for 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.

[1253] 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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1254] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the robot 414.

[1255] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[1256] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1257] These emotions are distributed in the three o'clock direction of emotion map 400 and usually 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.

[1258] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1259] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[1260] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[1261] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[1262] Although the system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, the system according to the present disclosure is not necessarily implemented in 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 that runs on a personal computer, or an application that runs on a smartphone or the like. The method according to the present disclosure may be provided to a user in the form of SaaS (Software as a Service).

[1263] In the above embodiment, an example is 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 the external device may generate data according to input data.

[1264] 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 Universal Serial Bus (USB) 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.

[1265] In addition, 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 upon request from the data processing device 12.

[1266] 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.

[1267] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing the specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[1268] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[1269] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[1270] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[1271] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 description and illustrations, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above description and illustrations omit explanations of technical common sense that do not require explanation in order to enable the implementation of the technology of the present disclosure.

[1272] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or standard was specifically and individually indicated to be incorporated by reference.

[1273] The following supplementary notes are further disclosed regarding the above embodiment.

[1274] (Appendix 1) means for centrally storing at least one of the student's assignment, project, and note information in a cloud storage app; means for integrating functionality of an interactive machine learning model to extract information about time and date from the stored database and set reminders for at least one of assignment deadlines, exam dates, and important notes; A system including:

[1275] (Appendix 2) 2. The system of claim 1, further comprising means for searching and retrieving relevant content from the stored database in response to a user request.

[1276] (Appendix 3) 3. The system of claim 1 or 2, further comprising means for analyzing the request using natural language processing technology when the user sends a request to the server via the terminal, and extracting or searching for appropriate information.

[1277] (Appendix 4) 4. The system according to any one of claims 1 to 3, further comprising an emotion engine for recognizing an emotion of a user.

[1278] (Appendix 5) 5. The system of claim 4, further comprising means for analyzing emotions in response to user requests and responses and providing an appropriate response.

[1279] (Appendix 6) 6. The system of claim 4 or claim 5, further comprising means for the emotion engine to recognize the user's tone of voice, facial expression changes, etc., and customize responses based thereon.

[1280] "Example 1" (Claim 1) means for centrally storing at least one of the education-related information in a cloud storage application; means for integrating functionality of an interactive machine learning model to extract information about time and date from the stored database and set notifications for at least one of deadlines, event dates, and important notes; By using generative AI models to search and extract relevant information based on user requests; means for processing user requests by the server and providing results to the terminal; A system including:

[1281] (Claim 2) 2. The system of claim 1, further comprising means for the generative AI model to extract relevant information from the database using a prompt sentence input in natural language by a user.

[1282] (Claim 3) 10. The system of claim 1, further comprising means for a user to input information into the cloud storage application via the terminal and for the server to store the information in a database.

[1283] "Application example 1" (Claim 1) A means for centrally storing at least one of a user's work, project, and memo information in a cloud storage app; A means for integrating functionality of an interactive machine learning model to extract information about time and date from the stored database and set at least one reminder for a work deadline, an inspection date, and an important note; A means of providing work schedule management and preventive maintenance reminders within the factory; A system including:

[1284] (Claim 2) 10. The system of claim 1, further comprising means for searching and retrieving relevant content from the stored database in response to a user request.

[1285] (Claim 3) 2. The system according to claim 1, further comprising: means for analyzing a request by using a natural language processing technique when the user sends a request to the server via the terminal, and extracting or searching for appropriate information.

[1286] "Example 2 of combining emotion engines" (Claim 1) means for centrally storing at least one of the information of the educational activity in a cloud storage app; A means to integrate the functionality of an interactive machine learning model to extract date and time information from the stored database and set reminders for important matters; an emotion engine means for recognizing and analyzing an emotional state of a user and generating an appropriate response; A system including:

[1287] (Claim 2) 10. The system of claim 1, further comprising means for searching and retrieving relevant content from the stored database in response to a user request.

[1288] (Claim 3) 2. The system according to claim 1, further comprising: means for analyzing a request by using a natural language processing technique when the user sends a request to the server via the terminal, and extracting or searching for appropriate information.

[1289] "Application example 2 when combining emotion engines" (Claim 1) means for centrally storing at least one of the information in a cloud storage application; A means of integrating the functionality of an interactive machine learning model to extract date and time information from the stored database and set reminders; means for recognizing and analyzing user emotions using an emotion engine; A means to use generative AI to recommend learning materials and generate reminders; A system including:

[1290] (Claim 2) 10. The system of claim 1, further comprising means for searching and retrieving relevant content from the stored database in response to a user request.

[1291] (Claim 3) 2. The system according to claim 1, further comprising: means for analyzing a request by using a natural language processing technique when the user sends a request to the server via the terminal, and extracting or searching for appropriate information. [Explanation of symbols]

[1292] 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 for storing registration information previously registered by a user; A means for integrating a function of an interactive machine learning model to extract information regarding date and time from the stored registration information and set a reminder; Means for providing the reminders relevant to a user request using a generative AI model; A system including:

2. The system of claim 1 , further comprising means for the generative AI model to extract relevant reminders using a prompt sentence entered by a user in natural language.

3. The system of claim 1 , further comprising a means for a user to input information into the cloud storage application via a terminal, and for the server to store the input information in a database.

Images