system

Abstract

We provide the system. [Solution] A means of aggregating user schedule information and task information, A means to optimize the user's schedule and tasks using a generative AI model based on aggregated information, A means of notifying the user terminal of optimized schedules and tasks, A means of collecting user feedback and incorporating it into the generated AI model, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including: receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the modern business environment, tasks and schedules for individuals have increased, and efficient task management and schedule adjustment have become essential. Conventional methods require manual schedule setting and task management, which have the problem of taking a lot of time and labor. Therefore, there is a need for a system that reduces the burden on users and realizes a balanced life both privately and publicly.

Means for Solving the Problems

[0005] This invention provides a system that aggregates user schedule and task information and proposes an optimal schedule and task allocation using a generative AI model. Specifically, it integrates information obtained from the user into a database, and the generative AI model analyzes this data to create an optimized plan that takes into account the user's priorities and goals. Furthermore, it notifies the user terminal of the optimized schedule and tasks, collects user feedback, and incorporates it into the generative AI model to continuously improve the proposals. This enables efficient task management and schedule adjustment.

[0006] A "user" is an individual or group of people who use the system to manage their schedules and optimize their tasks.

[0007] "Schedule information" refers to information about the time and appointments that users plan, and is provided as data in the form of a calendar or timetable.

[0008] "Task information" refers to information about the activities or tasks that a user needs to complete, including detailed items such as priority and deadline.

[0009] A "generative AI model" is a module that uses machine learning algorithms based on collected data to propose the optimal schedule and task allocation.

[0010] "Optimization" is the process of streamlining schedules and tasks based on the user's goals and priorities.

[0011] A "terminal" is a device used to provide information to a user and receive feedback, and includes devices such as smartphones and computers.

[0012] "Feedback" refers to information such as opinions and requests for modifications that users provide regarding system suggestions.

[0013] A "database" is a structured collection of data used to centrally store collected information and analyze generative AI models. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[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 labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

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

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

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

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

[0032] The storage 32 stores the data generation model 58 and the 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 the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0035] The system of this invention is designed to efficiently manage user schedules and optimize tasks. In this system, a server plays a central role, handling user information and suggesting optimizations.

[0036] Server Embodiment

[0037] The server first collects schedule and task information from the user's device. The collected information is integrated and managed in a database. Next, the server inputs the aggregated information into a generating AI model to optimize the schedule and tasks. This AI model uses machine learning algorithms to generate optimal suggestions while considering the user's goals and priorities.

[0038] Terminal embodiment

[0039] The device notifies the user of optimized schedules and tasks sent from the server. Notifications are provided via push notifications and email for quick user review. The device also receives user feedback and sends it back to the server. The device provides user-friendly interfaces, including voice and text input.

[0040] User Embodiment

[0041] Users interact with the system through their terminals. They review proposed schedules and task information and provide correction requests and feedback as needed. This feedback is used to achieve personalized optimization tailored to the user's lifestyle and work requirements.

[0042] Specific example: If a user typically has many meetings on Mondays, the server takes this into account and optimizes scheduling other important tasks for Tuesday or later. The terminal notifies the user of tasks to be handled in the next few days and their priorities, and the user can provide voice feedback, such as "I'd like to add a task for this evening."

[0043] Thus, the system of the present invention, through the cooperation of a server and a terminal, enables users to manage their tasks quickly and efficiently, supporting a lifestyle that balances work and personal life.

[0044] The following describes the processing flow.

[0045] Step 1:

[0046] The server receives schedule and task information from the user's device. This includes retrieving data from calendar applications and task management tools via APIs.

[0047] Step 2:

[0048] The server stores the received information in a database and creates a unified schedule and task dataset for each user. This data is used as the basis for analysis by generative AI models.

[0049] Step 3:

[0050] The server inputs the integrated data into the generated AI model and performs optimization calculations that take into account the user's goals and priorities. The AI ​​model generates an efficient task allocation and schedule for the user.

[0051] Step 4:

[0052] The server prepares optimized scheduling information derived from the AI ​​model and sends it to the device. This can be in the form of push notifications, email, or in-app notifications, depending on the user's preference.

[0053] Step 5:

[0054] The terminal displays information received from the server on the user interface and notifies the user. The user can review this information and provide feedback on schedules and tasks as needed.

[0055] Step 6:

[0056] Users provide feedback on the proposed schedule using voice or text input. This feedback includes adding, deleting, modifying, and reprioritizing tasks.

[0057] Step 7:

[0058] The device sends the user feedback back to the server. The server updates its database based on the received feedback and incorporates it into the next optimization calculation.

[0059] Step 8:

[0060] The server uses the collected feedback to adaptively train the generated AI model, enabling it to make more accurate optimization suggestions in the future. This continuously improves the system's user experience.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In today's busy lifestyle, effectively managing users' schedules and work information and proposing optimal schedules based on priorities and individual goals is difficult. Furthermore, conventional systems lack sufficient interfaces to reflect direct user feedback, making it difficult to optimize them to accurately reflect user needs.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for aggregating user schedule information and work information, means for integrating the aggregated information into an information storage device, and means for optimizing the user's schedule and work using a generated AI model based on the information in the information storage device, and means for notifying the user device of the optimized schedule and work. This enables flexible and efficient schedule proposals tailored to the user's priorities and goals.

[0066] "User schedule information" refers to information about activities and events that the user plans to participate in in the future, including details such as the date, time, location, and participants.

[0067] "Work information" refers to information about specific tasks or projects that a user needs to perform, including deadlines, priorities, and required resources.

[0068] "Means of aggregation" refers to methods or devices for gathering and organizing dispersed information in one place, and includes the process of data integration.

[0069] An "information storage device" is hardware or software that stores large amounts of information in a specific format and allows for efficient retrieval as needed.

[0070] A "generative AI model" is an artificial intelligence model designed based on machine learning algorithms, which performs predictions and optimizations based on the input data.

[0071] "Optimization" refers to the efficient adjustment of plans and resource allocations to best meet a particular objective or condition.

[0072] "User device" refers to a device that enables interaction between the user and the system, and includes smartphones, tablets, computers, and the like.

[0073] "Feedback" refers to information about opinions and reactions received from users, which is used to adjust and improve the system.

[0074] The embodiments for carrying out the present invention are shown below.

[0075] First, the server collects schedule and task information from the user's device. This information is obtained from the user's calendar app or task management app, and the data extracted by the device is sent to the server. The types of information include the date and time of events, priority, and deadline. When aggregating the information, it is recommended to use data encryption technology to ensure security. The data is also stored in an information storage device such as an SQL database, enabling efficient data access.

[0076] Next, the server inputs this aggregated information into a generating AI model. This AI model is built using machine learning frameworks (e.g., TENSORFLOW® or PyTorch) and optimizes schedules and tasks, taking into account the user's priorities and goals. Specifically, it analyzes historical data and suggests the most efficient way to manage time. In this process, generated prompts can be used to guide the model on how to process the data. An example of a prompt might be, "Consider the user's current schedule and optimize tasks based on next week's priorities."

[0077] The server then sends the optimized schedule and tasks to the terminal. The terminal receives this and notifies the user of the suggestions via push notifications or email. The terminal has interfaces such as voice input and touch input, through which the user can provide feedback. For example, if the user gives voice feedback such as "I would like to add a meeting this Friday," the terminal will send this information back to the server and update the database.

[0078] This system aims to adapt to the user's lifestyle and enable efficient time management. Feedback such as schedule changes and task additions are smoothly reflected, creating an environment where users can manage their time efficiently.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects schedule and task information from the user's device. At this stage, the device receives data from calendar and task management apps as input and sends it to the server. Specifically, the device retrieves event dates and task deadlines from each app via API and securely sends the data to the server using encryption technology. The output is the raw schedule data stored on the server.

[0082] Step 2:

[0083] The server stores the received schedule and work information in its information storage device and integrates it into the database. At this time, it stores the multiple input datasets as structured data. Specifically, it adds schedule and task entries to the SQL database and generates the necessary indexes to enable efficient access. The output of this step is an integrated dataset in an accessible format.

[0084] Step 3:

[0085] The server inputs integrated information into a generating AI model to optimize schedules and tasks. The input is a dataset containing user priorities and historical behavior data. Specifically, it uses a machine learning framework to analyze the provided data and execute predictive algorithms. Following prompts, the AI ​​is given instructions such as, "Optimize tasks for next week." The output of this step is an optimized schedule and task list.

[0086] Step 4:

[0087] The server sends an optimized schedule and task details to the terminal. At this stage, the server outputs optimized data, which the terminal receives as input. Specifically, it generates data in JSON format and sends it to the terminal via an HTTP request. The output is a schedule that is visually displayed on the terminal.

[0088] Step 5:

[0089] The device notifies the user of an optimized schedule and collects any changes or feedback. The input is user feedback information. Specifically, it presents information to the user using notification bars and pop-up messages, and accepts feedback via voice recognition or touch input. The output of this step is the information returned to the server as feedback data.

[0090] Step 6:

[0091] The server updates the database based on user feedback and performs further optimization using the AI ​​model as needed. Inputs include user feedback and existing schedule information. Specifically, it analyzes the feedback, updates the database information, and performs new optimizations. The output of this step is the updated schedule and tasks.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] In modern society, managing individual activity plans and tasks can increase the time burden and significantly reduce the quality of life. To address this problem, effective activity planning methods tailored to individual users are needed. Furthermore, technologies with support functions for daily life are required.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes means for integrating user activity plan information and work information, means for optimizing the user's activity plan and work using a generated AI model based on the integrated information, and means for notifying the user's device of the optimized activity plan and work. This enables more efficient task management in the user's living environment. Furthermore, by equipping it with home support functions and providing daily support through voice support functions, the user can improve their quality of life.

[0097] "Activity plan information" refers to data on plans and schedules related to the user's daily life and work.

[0098] "Work information" refers to data related to the tasks and work content that the user is supposed to perform.

[0099] "Means of integration" refers to a function that centrally manages activity plan information and work information obtained from users and aggregates them in a database or similar system.

[0100] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to create activity plans and task suggestions optimized for the user.

[0101] "Optimization means" refers to a function that uses a generative AI model to calculate the most efficient schedule based on the user's activity plan information and work information.

[0102] "User devices" refer to devices that users can directly operate, such as smartphones and personal computers.

[0103] "Notification methods" refer to ways to inform users of optimized activity plans and tasks, including features such as push notifications and voice alerts.

[0104] "Home-use support functions" refer to features incorporated into robots and digital assistant devices intended for home use that support the user's daily life.

[0105] "Voice support function" refers to a function that allows the user to interact with the system through voice input, and utilizes speech recognition technology.

[0106] The system for realizing this invention efficiently manages user activity plan information and work information to improve quality of life. A server collects activity plan information and work information from the user's device and integrates this information into a data storage device. The integrated information is analyzed using a generative AI model to optimize the user's activity plan and work for maximum efficiency. This optimized information is then communicated to the user's device.

[0107] User devices, such as smartphones and computers, have the function of notifying the user of optimized activity plans and tasks visually and audibly. Devices with home assistance functions interface with the user using voice assistance functions to support the user's daily life. These voice assistance functions can notify the user of daily tasks by voice and accept voice input from the user.

[0108] For example, the server might analyze a user's activity on Monday, when many appointments are concentrated, and suggest tasks that can be moved to Tuesday or later to provide a more efficient plan. The user can then provide feedback via voice input, such as "I want to do this appointment earlier."

[0109] An example of a prompt for a generating AI model could be: "Optimize user ID 123's schedule for this week and create suggestions to prioritize high-priority tasks." This would significantly improve the user's task management and quality of life.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server receives activity plan information and work information as input from user devices. This data includes each user's schedule and task information. The server aggregates this information and stores it in a data storage device.

[0113] Step 2:

[0114] The server retrieves aggregated information from data storage and inputs it into the generating AI model. By generating prompt statements and giving instructions to the AI ​​model, it performs data analysis to optimize the user's activity plan and tasks. This results in an optimized schedule that takes into account the user's priorities and efficiency.

[0115] Step 3:

[0116] The server sends optimized schedule and task information to the user's device. The device notifies the user of this information in audio or visual format. Specifically, it can notify the user via push notifications or voice alerts.

[0117] Step 4:

[0118] Users provide feedback on the schedules and tasks they receive. They can input requests to add or modify new tasks via voice or text through their device.

[0119] Step 5:

[0120] The device then sends the user feedback back to the server. The server records this feedback in its data storage and incorporates it into the generated AI model. This ensures that user feedback is taken into consideration for future optimizations.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] The system of this invention aims to optimize schedule management and tasks while taking user emotions into consideration. This will help users lead more comfortable and efficient daily lives.

[0123] Server Embodiment

[0124] The server retrieves data from the user's device to aggregate the user's schedule and task information. This data is stored in a database and used for subsequent analysis. Furthermore, the server utilizes an emotion engine to recognize emotions based on the voice and text data received from the user. This emotion information is input into a generative AI model and reflected in the optimization suggestions for schedules and tasks.

[0125] Terminal embodiment

[0126] The device notifies the user of optimized schedules and tasks sent from the server, as well as personalized suggestions based on sentiment information. These notifications are delivered via push notifications, allowing users to access them quickly. The device also provides an interface for the sentiment engine to analyze the user's speech and writing through voice and text input.

[0127] User Embodiment

[0128] Users interact with the system using their devices. They evaluate the provided schedule and task suggestions and provide feedback as needed. This includes emotional feedback based on the user's stress and satisfaction levels. This feedback is used to improve subsequent optimization processes.

[0129] Specific example: If a user tells the server via their device one morning, "I'm feeling a bit down today," the emotion engine analyzes this data, and the generative AI model reconfigures the schedule to slightly reduce the day's tasks. The optimized schedule is then immediately notified to the user's device, allowing the user to review and adjust it.

[0130] Thus, the system of the present invention, by combining an emotion engine, achieves flexible schedule management that responds to the user's psychological state. Furthermore, it aims to improve the user's quality of life in the long term through a continuous feedback loop.

[0131] The following describes the processing flow.

[0132] Step 1:

[0133] The server receives schedule and task information from the user's device. This includes aggregating information through APIs of calendar and task management applications.

[0134] Step 2:

[0135] The server uses an emotion engine to recognize the user's emotional state based on the voice and text data acquired through the terminal. It determines the user's emotions by analyzing the tone of voice and the content of the text.

[0136] Step 3:

[0137] The server integrates the received schedule and task information, along with the recognized emotion information, into a database. Based on this integrated data, it runs a generative AI model to calculate the optimal schedule and task allocation.

[0138] Step 4:

[0139] The server creates and sends emotionally sensitive suggestions to the terminal based on the optimization results from the generated AI model. These suggestions include adjusting task priorities and reducing tasks as needed.

[0140] Step 5:

[0141] The terminal displays suggestions received from the server to the user as notifications. The user can review the suggested schedule and tasks and make changes or adjustments.

[0142] Step 6:

[0143] Users can provide feedback on suggestions via voice or text input. This feedback may include additional information regarding their feelings.

[0144] Step 7:

[0145] The device sends user feedback to the server. The server stores the received feedback in a database and uses it to optimize future generational AI models.

[0146] Step 8:

[0147] The server adjusts the parameters of the generated AI model based on feedback, improving the accuracy of the emotion engine. This ensures that future optimization suggestions are more tailored to the user.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] Modern individuals and organizations face diverse activities and responsibilities, demanding efficient and stress-free time management and work optimization. However, current scheduling systems often fail to adequately consider users' emotional states and psychological burdens, resulting in a lack of long-term quality of life improvement. To address this challenge, there is a need for the development of time management systems that take user emotions into account.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes means for aggregating user timetable information and work information, means for optimizing the user's timetable and work using a generative AI model based on the aggregated information and emotional information, and means for identifying the user's emotional state using an emotional analysis engine and utilizing that emotional state as input information for the generative AI model. This enables flexible and efficient schedule management that takes the user's emotions into consideration, thereby improving the long-term quality of life.

[0153] "Timetable information" refers to information related to a user's schedule or planned activities, and includes data such as date, time, location, and activity details.

[0154] "Work information" refers to data that includes information about tasks and work content that a user should perform, including their priority and deadlines.

[0155] "Emotional information" refers to information that indicates the user's psychological state, and includes data on emotional tendencies obtained through the analysis of voice and text.

[0156] An "information terminal" is a device that a user can directly operate, and includes smartphones and computers.

[0157] "Evaluation information" refers to information based on user feedback and is used as an indicator for improving and optimizing the system.

[0158] An "emotion analysis engine" is software or a function that analyzes a user's voice and text data to identify their emotional state.

[0159] An "information storage device" is a mechanism for storing digital data, and databases and cloud storage fall into this category.

[0160] The system of this invention aims to optimize timetable management and work processes while taking user emotions into consideration. To this end, the system interacts with each other through the server, terminal, and user interface to improve the user's quality of life.

[0161] Server Embodiment

[0162] The server is responsible for acquiring and aggregating user timetable and work information from terminals. This information is stored in a database and used for subsequent analysis. The server utilizes an emotion analysis engine to analyze emotional information based on voice and text data received from users. The analysis results are input into a generative AI model, which then provides optimization suggestions for timetables and work. Specifically, the server uses speech recognition software to convert voice data into text and quantifies emotions using natural language processing. This quantified emotional information is provided to the generative AI model as a prompt, generating optimal suggestions tailored to the user's needs.

[0163] Terminal embodiment

[0164] The terminal pushes optimized timetables and tasks sent from the server to the user. By receiving these notifications, the user can quickly check their schedule and make necessary adjustments. The terminal also provides an interface for analyzing the user's emotions through voice and text input. This uses speech recognition technology and a text analysis engine. The terminal uses a smartphone or computer that the user can directly operate as the implementation device.

[0165] User Embodiment

[0166] Users interact with the system through their terminals and evaluate the provided timetables and work suggestions. They provide feedback as needed, and this feedback contributes to improving the system's optimization process. For example, a user might input something like "I'm feeling a bit down today" into their terminal, and this emotional information is analyzed and reflected by the system, which then reconfigures the schedule. The optimized schedule is immediately notified, allowing the user to review it and make further adjustments.

[0167] Specific example: For instance, if a user enters "I want to relax today" into their device, the server analyzes that emotion, and a generative AI model suggests increasing leisure time in their schedule. This allows the user to spend more relaxing time.

[0168] An example of a prompt message is, "Generate a schedule that reflects the user's emotions." This allows for flexible schedule management that takes the user's psychological state into consideration.

[0169] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0170] Step 1:

[0171] The server retrieves timetable and work information from the user's terminal. It receives data about the user's schedule and work content as input, aggregates this data, and stores it in a database. Specifically, this process involves receiving information using the HTTP protocol in response to data requests and storing the information through a database management system. The output is the user's schedule and work information, integrated on the server side.

[0172] Step 2:

[0173] The terminal acquires voice or text data entered by the user. The input data consists of text related to the user's statements and emotions, obtained through speech recognition or text input interfaces on the terminal. The terminal sends this data to a server, which uses it as input for sentiment analysis. Specific operations include speech-to-text conversion using a speech recognition API and direct input using a text box. The output is formatted text data for sentiment analysis.

[0174] Step 3:

[0175] The server analyzes text data received from the terminal using an emotion analysis engine. It uses natural language processing techniques to identify the emotional state of the acquired text data. This analysis quantifies the degree of positive or negative emotion. The specific operation involves inputting data into the emotion analysis algorithm and quantifying the results. The output is data quantified as emotional information.

[0176] Step 4:

[0177] The server inputs analyzed emotional information into a generative AI model to generate an optimized schedule and work suggestions. The input data consists of the user's emotional state and existing schedule information, which are used to generate prompt messages. The generative AI model uses these prompts to construct the most suitable suggestions for the user. Specifically, the process involves calling the generative AI model and performing calculations for suggestion generation. The output is an optimized schedule and work suggestions.

[0178] Step 5:

[0179] The device pushes optimized schedules and suggestions received from the server to the user. The input is suggestion data received from the server, and the device's notification system displays it. Specific actions include sending and displaying notifications in real time. The output is an optimization suggestion notification that the user can view on their device.

[0180] Step 6:

[0181] Users review optimization suggestions via their terminals and provide feedback as needed. They receive the presented schedule and work proposals as input, and evaluate and modify them based on their own judgment. This information is then sent back to the server to aid in the continuous optimization of the system. Specific actions include filling out feedback forms and submitting proposed revisions. The output consists of evaluation information and proposed changes sent back to the server as feedback.

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] Traditional schedule management systems managed schedules and tasks uniformly without considering the user's emotional state, thus failing to adequately reduce user psychological burden and improve their quality of life. Furthermore, they lacked the flexibility to adjust schedules to meet individual user needs.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for aggregating user schedule information and work information, means for optimizing the user's schedule and work using a generative AI model based on the aggregated information, and means for analyzing the user's emotional state and reflecting it in the schedule optimization. This enables detailed and flexible schedule management that takes the user's emotional state into consideration.

[0187] "User schedule information" refers to the details of the timetable and activities that the user plans to carry out.

[0188] "Work information" refers to the details of tasks and duties that a user needs to perform.

[0189] "Methods of aggregation" refer to the process of collecting data from multiple sources and combining them into a single, integrated dataset.

[0190] A "generative AI model" refers to a computational model designed using artificial intelligence technology for data analysis and decision-making.

[0191] "Means for analyzing emotional states" refers to processes designed to identify and evaluate a user's emotions and psychological state.

[0192] "Methods for reflecting schedule optimization" refers to the process of creating the most effective schedule for the user based on the analyzed data.

[0193] A "user terminal" refers to a computing device that a user can directly operate.

[0194] An "information storage device" refers to a device that stores data and retrieves and processes it as needed.

[0195] In embodiments of the present invention, a server aggregates user schedule information and work information from user terminals. The aggregated data is stored in an information aggregation device and used for analysis. The server uses sentiment analysis software (e.g., IBM Watson® Tone Analyzer) to analyze voice and text data obtained from speech recognition software (e.g., Google® Speech-to-Text) to determine the user's emotional state. This emotional information is used as data input to optimize the user's schedule and work using a generative AI model, such as OpenAI® GPT.

[0196] The optimized schedule and tasks are sent to the user's device as push notifications. The user's device is equipped with a user interface where the user can review the proposed schedule and make adjustments as needed. There is also a mechanism for users to provide feedback, which allows the server to incorporate that feedback into the generated AI model and continuously improve the optimization algorithm.

[0197] For example, if a user says to the device, "I'm not in the mood today," the system analyzes that emotion and uses a generative AI model to restructure the day's schedule in a less demanding way. In this way, flexible schedule management that responds to emotions is achieved. An example of a prompt would be, "If a user says, 'I'm feeling down today,' how would you optimize their schedule for the day based on that?"

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The server collects schedule and work information from user terminals. This input data is stored in an information aggregation device. Schedule information includes the date, time, and planned content, while work information includes deadlines and priorities. This data is stored in an integrated format for later analysis.

[0201] Step 2:

[0202] The server receives voice or text data from the user's terminal. Voice recognition software converts the voice into text. This converted text is then input into sentiment analysis software to analyze the user's emotional state. For example, if the user says "I'm not in the mood today," the sentiment analysis software will determine that the emotion is negative.

[0203] Step 3:

[0204] The server inputs the analyzed emotional information into a generative AI model. The generative AI model comprehensively considers the user's schedule and work information, as well as their emotional state, to generate an optimal schedule proposal. As a result of the data calculations, for example, the schedule may be streamlined or high-priority tasks may be reallocated.

[0205] Step 4:

[0206] The server pushes the generated optimization schedule to the user's device. The notification includes specific schedule changes and reasons, designed to be easily understood by the user. Based on this push notification information, the user can review and adjust the schedule as needed.

[0207] Step 5:

[0208] Users provide feedback on the provided schedule. This feedback includes satisfaction with the proposed content and suggestions for improvement. This feedback information is sent to the server and used to improve the algorithm of the generated AI model. This promotes continuous improvement in the accuracy of schedule optimization.

[0209] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0210] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of 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">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0211] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0212] [Second Embodiment]

[0213] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0214] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0215] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0216] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0217] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0218] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0219] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0220] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0221] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0222] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0223] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0224] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0225] The system of this invention is designed to efficiently manage user schedules and optimize tasks. In this system, a server plays a central role, handling user information and suggesting optimizations.

[0226] Server Embodiment

[0227] The server first collects schedule and task information from the user's device. The collected information is integrated and managed in a database. Next, the server inputs the aggregated information into a generating AI model to optimize the schedule and tasks. This AI model uses machine learning algorithms to generate optimal suggestions while considering the user's goals and priorities.

[0228] Terminal embodiment

[0229] The device notifies the user of optimized schedules and tasks sent from the server. Notifications are provided via push notifications and email for quick user review. The device also receives user feedback and sends it back to the server. The device provides user-friendly interfaces, including voice and text input.

[0230] User Embodiment

[0231] Users interact with the system through their terminals. They review proposed schedules and task information and provide correction requests and feedback as needed. This feedback is used to achieve personalized optimization tailored to the user's lifestyle and work requirements.

[0232] Specific example: If a user typically has many meetings on Mondays, the server takes this into account and optimizes scheduling other important tasks for Tuesday or later. The terminal notifies the user of tasks to be handled in the next few days and their priorities, and the user can provide voice feedback, such as "I'd like to add a task for this evening."

[0233] Thus, the system of the present invention, through the cooperation of a server and a terminal, enables users to manage their tasks quickly and efficiently, supporting a lifestyle that balances work and personal life.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The server receives schedule and task information from the user's device. This includes retrieving data from calendar applications and task management tools via APIs.

[0237] Step 2:

[0238] The server stores the received information in a database and creates a unified schedule and task dataset for each user. This data is used as the basis for analysis by generative AI models.

[0239] Step 3:

[0240] The server inputs the integrated data into the generated AI model and performs optimization calculations that take into account the user's goals and priorities. The AI ​​model generates an efficient task allocation and schedule for the user.

[0241] Step 4:

[0242] The server prepares optimized scheduling information derived from the AI ​​model and sends it to the device. This can be in the form of push notifications, email, or in-app notifications, depending on the user's preference.

[0243] Step 5:

[0244] The terminal displays information received from the server on the user interface and notifies the user. The user can review this information and provide feedback on schedules and tasks as needed.

[0245] Step 6:

[0246] Users provide feedback on the proposed schedule using voice or text input. This feedback includes adding, deleting, modifying, and reprioritizing tasks.

[0247] Step 7:

[0248] The device sends the user feedback back to the server. The server updates its database based on the received feedback and incorporates it into the next optimization calculation.

[0249] Step 8:

[0250] The server uses the collected feedback to adaptively train the generated AI model, enabling it to make more accurate optimization suggestions in the future. This continuously improves the system's user experience.

[0251] (Example 1)

[0252] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0253] In today's busy lifestyle, effectively managing users' schedules and work information and proposing optimal schedules based on priorities and individual goals is difficult. Furthermore, conventional systems lack sufficient interfaces to reflect direct user feedback, making it difficult to optimize them to accurately reflect user needs.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes means for aggregating user schedule information and work information, means for integrating the aggregated information into an information storage device, and means for optimizing the user's schedule and work using a generated AI model based on the information in the information storage device, and means for notifying the user device of the optimized schedule and work. This enables flexible and efficient schedule proposals tailored to the user's priorities and goals.

[0256] "User schedule information" refers to information about activities and events that the user plans to participate in in the future, including details such as the date, time, location, and participants.

[0257] "Work information" refers to information about specific tasks or projects that a user needs to perform, including deadlines, priorities, and required resources.

[0258] "Means of aggregation" refers to methods or devices for gathering and organizing dispersed information in one place, and includes the process of data integration.

[0259] An "information storage device" is hardware or software that stores large amounts of information in a specific format and allows for efficient retrieval as needed.

[0260] A "generative AI model" is an artificial intelligence model designed based on machine learning algorithms, which performs predictions and optimizations based on the input data.

[0261] "Optimization" refers to the efficient adjustment of plans and resource allocations to best meet a particular objective or condition.

[0262] "User device" refers to a device that enables interaction between the user and the system, and includes smartphones, tablets, computers, and the like.

[0263] "Feedback" refers to information about opinions and reactions received from users, which is used to adjust and improve the system.

[0264] The embodiments for carrying out the present invention are shown below.

[0265] First, the server collects schedule and task information from the user's device. This information is obtained from the user's calendar app or task management app, and the data extracted by the device is sent to the server. The types of information include the date and time of events, priority, and deadline. When aggregating the information, it is recommended to use data encryption technology to ensure security. The data is also stored in an information storage device such as an SQL database, enabling efficient data access.

[0266] Next, the server inputs this aggregated information into a generating AI model. This AI model is built using a machine learning framework (e.g., TensorFlow or PyTorch) and optimizes schedules and tasks, taking into account the user's priorities and goals. Specifically, it analyzes historical data and suggests the most efficient way to manage time. In this process, generated prompts can be used to guide the model on how to process the data. An example of a prompt might be, "Consider the user's current schedule and optimize tasks based on next week's priorities."

[0267] The server then sends the optimized schedule and tasks to the terminal. The terminal receives this and notifies the user of the suggestions via push notifications or email. The terminal has interfaces such as voice input and touch input, through which the user can provide feedback. For example, if the user gives voice feedback such as "I would like to add a meeting this Friday," the terminal will send this information back to the server and update the database.

[0268] This system aims to adapt to the user's lifestyle and enable efficient time management. Feedback such as schedule changes and task additions are smoothly reflected, creating an environment where users can manage their time efficiently.

[0269] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0270] Step 1:

[0271] The server collects schedule and task information from the user's device. At this stage, the device receives data from calendar and task management apps as input and sends it to the server. Specifically, the device retrieves event dates and task deadlines from each app via API and securely sends the data to the server using encryption technology. The output is the raw schedule data stored on the server.

[0272] Step 2:

[0273] The server stores the received schedule and work information in its information storage device and integrates it into the database. At this time, it stores the multiple input datasets as structured data. Specifically, it adds schedule and task entries to the SQL database and generates the necessary indexes to enable efficient access. The output of this step is an integrated dataset in an accessible format.

[0274] Step 3:

[0275] The server inputs integrated information into a generating AI model to optimize schedules and tasks. The input is a dataset containing user priorities and historical behavior data. Specifically, it uses a machine learning framework to analyze the provided data and execute predictive algorithms. Following prompts, the AI ​​is given instructions such as, "Optimize tasks for next week." The output of this step is an optimized schedule and task list.

[0276] Step 4:

[0277] The server sends an optimized schedule and task details to the terminal. At this stage, the server outputs optimized data, which the terminal receives as input. Specifically, it generates data in JSON format and sends it to the terminal via an HTTP request. The output is a schedule that is visually displayed on the terminal.

[0278] Step 5:

[0279] The device notifies the user of an optimized schedule and collects any changes or feedback. The input is user feedback information. Specifically, it presents information to the user using notification bars and pop-up messages, and accepts feedback via voice recognition or touch input. The output of this step is the information returned to the server as feedback data.

[0280] Step 6:

[0281] The server updates the database based on user feedback and performs further optimization using the AI ​​model as needed. Inputs include user feedback and existing schedule information. Specifically, it analyzes the feedback, updates the database information, and performs new optimizations. The output of this step is the updated schedule and tasks.

[0282] (Application Example 1)

[0283] Next, Application Example 1 will be described. 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".

[0284] In modern society, the management of personal activity plans and tasks can increase the time burden and significantly reduce the quality of life. To solve this problem, an effective activity plan management method suitable for individual users is required. In addition, technologies with daily support functions are required.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0286] In this invention, the server includes means for integrating the user's activity plan information and work information, means for optimizing the user's activity plan and work using a generated AI model based on the integrated information, and means for notifying the user device of the optimized activity plan and work. Thereby, it becomes possible to improve the efficiency of task management in the user's living environment. In addition, by equipping with a home support function and providing daily support through a voice support function, the user can improve the quality of life.

[0287] The "activity plan information" refers to data on schedules and plans related to the user's daily life and work.

[0288] The "work information" refers to data related to tasks and work contents that the user should perform.

[0289] The "means for integrating" refers to a function for centrally managing the activity plan information and work information acquired from the user and aggregating them in a database or the like.

[0290] The "generated AI model" is an artificial intelligence model using machine learning technology and is used to create proposals for activity plans and work optimized for the user.

[0291] "Optimization means" refers to a function that uses a generative AI model to calculate the most efficient schedule based on the user's activity plan information and work information.

[0292] "User devices" refer to devices that users can directly operate, such as smartphones and personal computers.

[0293] "Notification methods" refer to ways to inform users of optimized activity plans and tasks, including features such as push notifications and voice alerts.

[0294] "Home-use support functions" refer to features incorporated into robots and digital assistant devices intended for home use that support the user's daily life.

[0295] "Voice support function" refers to a function that allows the user to interact with the system through voice input, and utilizes speech recognition technology.

[0296] The system for realizing this invention efficiently manages user activity plan information and work information to improve quality of life. A server collects activity plan information and work information from the user's device and integrates this information into a data storage device. The integrated information is analyzed using a generative AI model to optimize the user's activity plan and work for maximum efficiency. This optimized information is then communicated to the user's device.

[0297] User devices, such as smartphones and computers, have the function of notifying the user of optimized activity plans and tasks visually and audibly. Devices with home assistance functions interface with the user using voice assistance functions to support the user's daily life. These voice assistance functions can notify the user of daily tasks by voice and accept voice input from the user.

[0298] For example, the server might analyze a user's activity on Monday, when many appointments are concentrated, and suggest tasks that can be moved to Tuesday or later to provide a more efficient plan. The user can then provide feedback via voice input, such as "I want to do this appointment earlier."

[0299] An example of a prompt for a generating AI model could be: "Optimize user ID 123's schedule for this week and create suggestions to prioritize high-priority tasks." This would significantly improve the user's task management and quality of life.

[0300] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0301] Step 1:

[0302] The server receives activity plan information and work information as input from user devices. This data includes each user's schedule and task information. The server aggregates this information and stores it in a data storage device.

[0303] Step 2:

[0304] The server retrieves aggregated information from data storage and inputs it into the generating AI model. By generating prompt statements and giving instructions to the AI ​​model, it performs data analysis to optimize the user's activity plan and tasks. This results in an optimized schedule that takes into account the user's priorities and efficiency.

[0305] Step 3:

[0306] The server sends optimized schedule and task information to the user's device. The device notifies the user of this information in audio or visual format. Specifically, it can notify the user via push notifications or voice alerts.

[0307] Step 4:

[0308] The user provides feedback on the received schedule and tasks. Through the terminal, requests for adding or changing new tasks can be input in the form of voice or text.

[0309] Step 5:

[0310] The terminal resends the user's feedback to the server. The server records this feedback in the data storage device and reflects it in the generated AI model. In this way, the user's feedback will be taken into account in the next optimization.

[0311] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0312] The system of the present invention aims to perform schedule management and task optimization considering the user's emotion, thereby assisting the user to lead a more comfortable and efficient daily life.

[0313] Embodiment of the server

[0314] The server acquires data from the user's terminal in order to aggregate the user's schedule information and task information. This data is stored in the database and used for subsequent analysis. Furthermore, the server utilizes the emotion engine to recognize the emotion based on the voice and text data received from the user. This emotion information is input into the generated AI model and reflected in the optimization proposal of the schedule and tasks.

[0315] Embodiment of the terminal

[0316] The device notifies the user of optimized schedules and tasks sent from the server, as well as personalized suggestions based on sentiment information. These notifications are delivered via push notifications, allowing users to access them quickly. The device also provides an interface for the sentiment engine to analyze the user's speech and writing through voice and text input.

[0317] User Embodiment

[0318] Users interact with the system using their devices. They evaluate the provided schedule and task suggestions and provide feedback as needed. This includes emotional feedback based on the user's stress and satisfaction levels. This feedback is used to improve subsequent optimization processes.

[0319] Specific example: If a user tells the server via their device one morning, "I'm feeling a bit down today," the emotion engine analyzes this data, and the generative AI model reconfigures the schedule to slightly reduce the day's tasks. The optimized schedule is then immediately notified to the user's device, allowing the user to review and adjust it.

[0320] Thus, the system of the present invention, by combining an emotion engine, achieves flexible schedule management that responds to the user's psychological state. Furthermore, it aims to improve the user's quality of life in the long term through a continuous feedback loop.

[0321] The following describes the processing flow.

[0322] Step 1:

[0323] The server receives schedule and task information from the user's device. This includes aggregating information through APIs of calendar and task management applications.

[0324] Step 2:

[0325] The server uses an emotion engine to recognize the user's emotional state based on the voice and text data acquired through the terminal. It determines the user's emotions by analyzing the tone of voice and the content of the text.

[0326] Step 3:

[0327] The server integrates the received schedule and task information, along with the recognized emotion information, into a database. Based on this integrated data, it runs a generative AI model to calculate the optimal schedule and task allocation.

[0328] Step 4:

[0329] The server creates and sends emotionally sensitive suggestions to the terminal based on the optimization results from the generated AI model. These suggestions include adjusting task priorities and reducing tasks as needed.

[0330] Step 5:

[0331] The terminal displays suggestions received from the server to the user as notifications. The user can review the suggested schedule and tasks and make changes or adjustments.

[0332] Step 6:

[0333] Users can provide feedback on suggestions via voice or text input. This feedback may include additional information regarding their feelings.

[0334] Step 7:

[0335] The device sends user feedback to the server. The server stores the received feedback in a database and uses it to optimize future generational AI models.

[0336] Step 8:

[0337] The server adjusts the parameters of the generated AI model based on feedback, improving the accuracy of the emotion engine. This ensures that future optimization suggestions are more tailored to the user.

[0338] (Example 2)

[0339] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0340] Modern individuals and organizations face diverse activities and responsibilities, demanding efficient and stress-free time management and work optimization. However, current scheduling systems often fail to adequately consider users' emotional states and psychological burdens, resulting in a lack of long-term quality of life improvement. To address this challenge, there is a need for the development of time management systems that take user emotions into account.

[0341] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0342] In this invention, the server includes means for aggregating user timetable information and work information, means for optimizing the user's timetable and work using a generative AI model based on the aggregated information and emotional information, and means for identifying the user's emotional state using an emotional analysis engine and utilizing that emotional state as input information for the generative AI model. This enables flexible and efficient schedule management that takes the user's emotions into consideration, thereby improving the long-term quality of life.

[0343] "Timetable information" refers to information related to a user's schedule or planned activities, and includes data such as date, time, location, and activity details.

[0344] "Work information" refers to data that includes information about tasks and work content that a user should perform, including their priority and deadlines.

[0345] "Emotional information" refers to information that indicates the user's psychological state, and includes data on emotional tendencies obtained through the analysis of voice and text.

[0346] An "information terminal" is a device that a user can directly operate, and includes smartphones and computers.

[0347] "Evaluation information" refers to information based on user feedback and is used as an indicator for improving and optimizing the system.

[0348] An "emotion analysis engine" is software or a function that analyzes a user's voice and text data to identify their emotional state.

[0349] An "information storage device" is a mechanism for storing digital data, and databases and cloud storage fall into this category.

[0350] The system of this invention aims to optimize timetable management and work processes while taking user emotions into consideration. To this end, the system interacts with each other through the server, terminal, and user interface to improve the user's quality of life.

[0351] Server Embodiment

[0352] The server is responsible for acquiring and aggregating user timetable and work information from terminals. This information is stored in a database and used for subsequent analysis. The server utilizes an emotion analysis engine to analyze emotional information based on voice and text data received from users. The analysis results are input into a generative AI model, which then provides optimization suggestions for timetables and work. Specifically, the server uses speech recognition software to convert voice data into text and quantifies emotions using natural language processing. This quantified emotional information is provided to the generative AI model as a prompt, generating optimal suggestions tailored to the user's needs.

[0353] Terminal embodiment

[0354] The terminal pushes optimized timetables and tasks sent from the server to the user. By receiving these notifications, the user can quickly check their schedule and make necessary adjustments. The terminal also provides an interface for analyzing the user's emotions through voice and text input. This uses speech recognition technology and a text analysis engine. The terminal uses a smartphone or computer that the user can directly operate as the implementation device.

[0355] User Embodiment

[0356] Users interact with the system through their terminals and evaluate the provided timetables and work suggestions. They provide feedback as needed, and this feedback contributes to improving the system's optimization process. For example, a user might input something like "I'm feeling a bit down today" into their terminal, and this emotional information is analyzed and reflected by the system, which then reconfigures the schedule. The optimized schedule is immediately notified, allowing the user to review it and make further adjustments.

[0357] Specific example: For instance, if a user enters "I want to relax today" into their device, the server analyzes that emotion, and a generative AI model suggests increasing leisure time in their schedule. This allows the user to spend more relaxing time.

[0358] An example of a prompt message is, "Generate a schedule that reflects the user's emotions." This allows for flexible schedule management that takes the user's psychological state into consideration.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The server retrieves timetable and work information from the user's terminal. It receives data about the user's schedule and work content as input, aggregates this data, and stores it in a database. Specifically, this process involves receiving information using the HTTP protocol in response to data requests and storing the information through a database management system. The output is the user's schedule and work information, integrated on the server side.

[0362] Step 2:

[0363] The terminal acquires voice or text data entered by the user. The input data consists of text related to the user's statements and emotions, obtained through speech recognition or text input interfaces on the terminal. The terminal sends this data to a server, which uses it as input for sentiment analysis. Specific operations include speech-to-text conversion using a speech recognition API and direct input using a text box. The output is formatted text data for sentiment analysis.

[0364] Step 3:

[0365] The server analyzes text data received from the terminal using an emotion analysis engine. It uses natural language processing techniques to identify the emotional state of the acquired text data. This analysis quantifies the degree of positive or negative emotion. The specific operation involves inputting data into the emotion analysis algorithm and quantifying the results. The output is data quantified as emotional information.

[0366] Step 4:

[0367] The server inputs analyzed emotional information into a generative AI model to generate an optimized schedule and work suggestions. The input data consists of the user's emotional state and existing schedule information, which are used to generate prompt messages. The generative AI model uses these prompts to construct the most suitable suggestions for the user. Specifically, the process involves calling the generative AI model and performing calculations for suggestion generation. The output is an optimized schedule and work suggestions.

[0368] Step 5:

[0369] The device pushes optimized schedules and suggestions received from the server to the user. The input is suggestion data received from the server, and the device's notification system displays it. Specific actions include sending and displaying notifications in real time. The output is an optimization suggestion notification that the user can view on their device.

[0370] Step 6:

[0371] Users review optimization suggestions via their terminals and provide feedback as needed. They receive the presented schedule and work proposals as input, and evaluate and modify them based on their own judgment. This information is then sent back to the server to aid in the continuous optimization of the system. Specific actions include filling out feedback forms and submitting proposed revisions. The output consists of evaluation information and proposed changes sent back to the server as feedback.

[0372] (Application Example 2)

[0373] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0374] Traditional schedule management systems managed schedules and tasks uniformly without considering the user's emotional state, thus failing to adequately reduce user psychological burden and improve their quality of life. Furthermore, they lacked the flexibility to adjust schedules to meet individual user needs.

[0375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0376] In this invention, the server includes means for aggregating user schedule information and work information, means for optimizing the user's schedule and work using a generative AI model based on the aggregated information, and means for analyzing the user's emotional state and reflecting it in the schedule optimization. This enables detailed and flexible schedule management that takes the user's emotional state into consideration.

[0377] "User schedule information" refers to the details of the timetable and activities that the user plans to carry out.

[0378] "Work information" refers to the details of tasks and duties that a user needs to perform.

[0379] "Methods of aggregation" refer to the process of collecting data from multiple sources and combining them into a single, integrated dataset.

[0380] A "generative AI model" refers to a computational model designed using artificial intelligence technology for data analysis and decision-making.

[0381] "Means for analyzing emotional states" refers to processes designed to identify and evaluate a user's emotions and psychological state.

[0382] "Methods for reflecting schedule optimization" refers to the process of creating the most effective schedule for the user based on the analyzed data.

[0383] A "user terminal" refers to a computing device that a user can directly operate.

[0384] An "information storage device" refers to a device that stores data and retrieves and processes it as needed.

[0385] In embodiments of the present invention, a server aggregates user schedule information and work information from user terminals. The aggregated data is stored in an information aggregation device and used for analysis. The server uses sentiment analysis software (e.g., IBM Watson Tone Analyzer) to analyze voice and text data obtained from speech recognition software (e.g., Google Speech-to-Text) to determine the user's emotional state. This sentiment information is used as data input to optimize the user's schedule and work using a generative AI model, such as OpenAI GPT.

[0386] The optimized schedule and tasks are sent to the user's device as push notifications. The user's device is equipped with a user interface where the user can review the proposed schedule and make adjustments as needed. There is also a mechanism for users to provide feedback, which allows the server to incorporate that feedback into the generated AI model and continuously improve the optimization algorithm.

[0387] For example, if a user says to the device, "I'm not in the mood today," the system analyzes that emotion and uses a generative AI model to restructure the day's schedule in a less demanding way. In this way, flexible schedule management that responds to emotions is achieved. An example of a prompt would be, "If a user says, 'I'm feeling down today,' how would you optimize their schedule for the day based on that?"

[0388] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0389] Step 1:

[0390] The server collects schedule and work information from user terminals. This input data is stored in an information aggregation device. Schedule information includes the date, time, and planned content, while work information includes deadlines and priorities. This data is stored in an integrated format for later analysis.

[0391] Step 2:

[0392] The server receives voice or text data from the user's terminal. Voice recognition software converts the voice into text. This converted text is then input into sentiment analysis software to analyze the user's emotional state. For example, if the user says "I'm not in the mood today," the sentiment analysis software will determine that the emotion is negative.

[0393] Step 3:

[0394] The server inputs the analyzed emotional information into a generative AI model. The generative AI model comprehensively considers the user's schedule and work information, as well as their emotional state, to generate an optimal schedule proposal. As a result of the data calculations, for example, the schedule may be streamlined or high-priority tasks may be reallocated.

[0395] Step 4:

[0396] The server pushes the generated optimization schedule to the user's device. The notification includes specific schedule changes and reasons, designed to be easily understood by the user. Based on this push notification information, the user can review and adjust the schedule as needed.

[0397] Step 5:

[0398] Users provide feedback on the provided schedule. This feedback includes satisfaction with the proposed content and suggestions for improvement. This feedback information is sent to the server and used to improve the algorithm of the generated AI model. This promotes continuous improvement in the accuracy of schedule optimization.

[0399] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0400] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0401] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0402] [Third Embodiment]

[0403] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0404] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0405] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0406] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0407] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0408] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0409] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0410] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0411] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0412] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0413] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0414] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0415] The system of this invention is designed to efficiently manage user schedules and optimize tasks. In this system, a server plays a central role, handling user information and suggesting optimizations.

[0416] Server Embodiment

[0417] The server first collects schedule and task information from the user's device. The collected information is integrated and managed in a database. Next, the server inputs the aggregated information into a generating AI model to optimize the schedule and tasks. This AI model uses machine learning algorithms to generate optimal suggestions while considering the user's goals and priorities.

[0418] Terminal embodiment

[0419] The device notifies the user of optimized schedules and tasks sent from the server. Notifications are provided via push notifications and email for quick user review. The device also receives user feedback and sends it back to the server. The device provides user-friendly interfaces, including voice and text input.

[0420] User Embodiment

[0421] Users interact with the system through their terminals. They review proposed schedules and task information and provide correction requests and feedback as needed. This feedback is used to achieve personalized optimization tailored to the user's lifestyle and work requirements.

[0422] Specific example: If a user typically has many meetings on Mondays, the server takes this into account and optimizes scheduling other important tasks for Tuesday or later. The terminal notifies the user of tasks to be handled in the next few days and their priorities, and the user can provide voice feedback, such as "I'd like to add a task for this evening."

[0423] Thus, the system of the present invention, through the cooperation of a server and a terminal, enables users to manage their tasks quickly and efficiently, supporting a lifestyle that balances work and personal life.

[0424] The following describes the processing flow.

[0425] Step 1:

[0426] The server receives schedule and task information from the user's device. This includes retrieving data from calendar applications and task management tools via APIs.

[0427] Step 2:

[0428] The server stores the received information in a database and creates a unified schedule and task dataset for each user. This data is used as the basis for analysis by generative AI models.

[0429] Step 3:

[0430] The server inputs the integrated data into the generated AI model and performs optimization calculations that take into account the user's goals and priorities. The AI ​​model generates an efficient task allocation and schedule for the user.

[0431] Step 4:

[0432] The server prepares optimized scheduling information derived from the AI ​​model and sends it to the device. This can be in the form of push notifications, email, or in-app notifications, depending on the user's preference.

[0433] Step 5:

[0434] The terminal displays information received from the server on the user interface and notifies the user. The user can review this information and provide feedback on schedules and tasks as needed.

[0435] Step 6:

[0436] Users provide feedback on the proposed schedule using voice or text input. This feedback includes adding, deleting, modifying, and reprioritizing tasks.

[0437] Step 7:

[0438] The device sends the user feedback back to the server. The server updates its database based on the received feedback and incorporates it into the next optimization calculation.

[0439] Step 8:

[0440] The server uses the collected feedback to adaptively train the generated AI model, enabling it to make more accurate optimization suggestions in the future. This continuously improves the system's user experience.

[0441] (Example 1)

[0442] Next, we will describe Example 1. 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."

[0443] In today's busy lifestyle, effectively managing users' schedules and work information and proposing optimal schedules based on priorities and individual goals is difficult. Furthermore, conventional systems lack sufficient interfaces to reflect direct user feedback, making it difficult to optimize them to accurately reflect user needs.

[0444] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0445] In this invention, the server includes means for aggregating user schedule information and work information, means for integrating the aggregated information into an information storage device, and means for optimizing the user's schedule and work using a generated AI model based on the information in the information storage device, and means for notifying the user device of the optimized schedule and work. This enables flexible and efficient schedule proposals tailored to the user's priorities and goals.

[0446] "User schedule information" refers to information about activities and events that the user plans to participate in in the future, including details such as the date, time, location, and participants.

[0447] "Work information" refers to information about specific tasks or projects that a user needs to perform, including deadlines, priorities, and required resources.

[0448] "Means of aggregation" refers to methods or devices for gathering and organizing dispersed information in one place, and includes the process of data integration.

[0449] An "information storage device" is hardware or software that stores large amounts of information in a specific format and allows for efficient retrieval as needed.

[0450] A "generative AI model" is an artificial intelligence model designed based on machine learning algorithms, which performs predictions and optimizations based on the input data.

[0451] "Optimization" refers to the efficient adjustment of plans and resource allocations to best meet a particular objective or condition.

[0452] "User device" refers to a device that enables interaction between the user and the system, and includes smartphones, tablets, computers, and other similar devices.

[0453] "Feedback" refers to information about opinions and reactions received from users, which is used to adjust and improve the system.

[0454] The embodiments for carrying out the present invention are shown below.

[0455] First, the server collects schedule and task information from the user's device. This information is obtained from the user's calendar app or task management app, and the data extracted by the device is sent to the server. The types of information include the date and time of events, priority, and deadline. When aggregating the information, it is recommended to use data encryption technology to ensure security. The data is also stored in an information storage device such as an SQL database, enabling efficient data access.

[0456] Next, the server inputs this aggregated information into a generating AI model. This AI model is built using a machine learning framework (e.g., TensorFlow or PyTorch) and optimizes schedules and tasks, taking into account the user's priorities and goals. Specifically, it analyzes historical data and suggests the most efficient way to manage time. In this process, generated prompts can be used to guide the model on how to process the data. An example of a prompt might be, "Consider the user's current schedule and optimize tasks based on next week's priorities."

[0457] The server then sends the optimized schedule and tasks to the terminal. The terminal receives this and notifies the user of the suggestions via push notifications or email. The terminal has interfaces such as voice input and touch input, through which the user can provide feedback. For example, if the user gives voice feedback such as "I would like to add a meeting this Friday," the terminal will send this information back to the server and update the database.

[0458] This system aims to adapt to the user's lifestyle and enable efficient time management. Feedback such as schedule changes and task additions are smoothly reflected, creating an environment where users can manage their time efficiently.

[0459] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0460] Step 1:

[0461] The server collects schedule and task information from the user's device. At this stage, the device receives data from calendar and task management apps as input and sends it to the server. Specifically, the device retrieves event dates and task deadlines from each app via API and securely sends the data to the server using encryption technology. The output is the raw schedule data stored on the server.

[0462] Step 2:

[0463] The server stores the received schedule and work information in its information storage device and integrates it into the database. At this time, it stores the multiple input datasets as structured data. Specifically, it adds schedule and task entries to the SQL database and generates the necessary indexes to enable efficient access. The output of this step is an integrated dataset in an accessible format.

[0464] Step 3:

[0465] The server inputs integrated information into a generating AI model to optimize schedules and tasks. The input is a dataset containing user priorities and historical behavior data. Specifically, it uses a machine learning framework to analyze the provided data and execute predictive algorithms. Following prompts, the AI ​​is given instructions such as, "Optimize tasks for next week." The output of this step is an optimized schedule and task list.

[0466] Step 4:

[0467] The server sends an optimized schedule and task details to the terminal. At this stage, the server outputs optimized data, which the terminal receives as input. Specifically, it generates data in JSON format and sends it to the terminal via an HTTP request. The output is a schedule that is visually displayed on the terminal.

[0468] Step 5:

[0469] The device notifies the user of an optimized schedule and collects any changes or feedback. The input is user feedback information. Specifically, it presents information to the user using notification bars and pop-up messages, and accepts feedback via voice recognition or touch input. The output of this step is the information returned to the server as feedback data.

[0470] Step 6:

[0471] The server updates the database based on user feedback and performs further optimization using the AI ​​model as needed. Inputs include user feedback and existing schedule information. Specifically, it analyzes the feedback, updates the database information, and performs new optimizations. The output of this step is the updated schedule and tasks.

[0472] (Application Example 1)

[0473] Next, we will explain Application Example 1. In the following explanation, 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."

[0474] In modern society, managing individual activity plans and tasks can increase the time burden and significantly reduce the quality of life. To address this problem, effective activity planning methods tailored to individual users are needed. Furthermore, technologies with support functions for daily life are required.

[0475] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0476] In this invention, the server includes means for integrating user activity plan information and work information, means for optimizing the user's activity plan and work using a generated AI model based on the integrated information, and means for notifying the user's device of the optimized activity plan and work. This enables more efficient task management in the user's living environment. Furthermore, by equipping it with home support functions and providing daily support through voice support functions, the user can improve their quality of life.

[0477] "Activity plan information" refers to data on plans and schedules related to the user's daily life and work.

[0478] "Work information" refers to data related to the tasks and work content that the user is supposed to perform.

[0479] "Means of integration" refers to a function that centrally manages activity plan information and work information obtained from users and aggregates them in a database or similar system.

[0480] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to create activity plans and task suggestions optimized for the user.

[0481] "Optimization means" refers to a function that uses a generative AI model to calculate the most efficient schedule based on the user's activity plan information and work information.

[0482] "User devices" refer to devices that users can directly operate, such as smartphones and personal computers.

[0483] "Notification methods" refer to ways to inform users of optimized activity plans and tasks, including features such as push notifications and voice alerts.

[0484] "Home-use support functions" refer to features incorporated into robots and digital assistant devices intended for home use that support the user's daily life.

[0485] "Voice support function" refers to a function that allows the user to interact with the system through voice input, and utilizes speech recognition technology.

[0486] The system for realizing this invention efficiently manages user activity plan information and work information to improve quality of life. A server collects activity plan information and work information from the user's device and integrates this information into a data storage device. The integrated information is analyzed using a generative AI model to optimize the user's activity plan and work for maximum efficiency. This optimized information is then communicated to the user's device.

[0487] User devices, such as smartphones and computers, have the function of notifying the user of optimized activity plans and tasks visually and audibly. Devices with home assistance functions interface with the user using voice assistance functions to support the user's daily life. These voice assistance functions can notify the user of daily tasks by voice and accept voice input from the user.

[0488] For example, the server might analyze a user's activity on Monday, when many appointments are concentrated, and suggest tasks that can be moved to Tuesday or later to provide a more efficient plan. The user can then provide feedback via voice input, such as "I want to do this appointment earlier."

[0489] An example of a prompt for a generating AI model could be: "Optimize user ID 123's schedule for this week and create suggestions to prioritize high-priority tasks." This would significantly improve the user's task management and quality of life.

[0490] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0491] Step 1:

[0492] The server receives activity plan information and work information as input from user devices. This data includes each user's schedule and task information. The server aggregates this information and stores it in a data storage device.

[0493] Step 2:

[0494] The server retrieves aggregated information from data storage and inputs it into the generating AI model. By generating prompt statements and giving instructions to the AI ​​model, it performs data analysis to optimize the user's activity plan and tasks. This results in an optimized schedule that takes into account the user's priorities and efficiency.

[0495] Step 3:

[0496] The server sends optimized schedule and task information to the user's device. The device notifies the user of this information in audio or visual format. Specifically, it can notify the user via push notifications or voice alerts.

[0497] Step 4:

[0498] Users provide feedback on the schedules and tasks they receive. They can input requests to add or modify new tasks via voice or text through their device.

[0499] Step 5:

[0500] The device then sends the user feedback back to the server. The server records this feedback in its data storage and incorporates it into the generated AI model. This ensures that user feedback is taken into consideration for future optimizations.

[0501] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0502] The system of this invention aims to optimize schedule management and tasks while taking user emotions into consideration. This will help users lead more comfortable and efficient daily lives.

[0503] Server Embodiment

[0504] The server retrieves data from the user's device to aggregate the user's schedule and task information. This data is stored in a database and used for subsequent analysis. Furthermore, the server utilizes an emotion engine to recognize emotions based on the voice and text data received from the user. This emotion information is input into a generative AI model and reflected in the optimization suggestions for schedules and tasks.

[0505] Terminal embodiment

[0506] The device notifies the user of optimized schedules and tasks sent from the server, as well as personalized suggestions based on sentiment information. These notifications are delivered via push notifications, allowing users to access them quickly. The device also provides an interface for the sentiment engine to analyze the user's speech and writing through voice and text input.

[0507] User Embodiment

[0508] Users interact with the system using their devices. They evaluate the provided schedule and task suggestions and provide feedback as needed. This includes emotional feedback based on the user's stress and satisfaction levels. This feedback is used to improve subsequent optimization processes.

[0509] Specific example: If a user tells the server via their device one morning, "I'm feeling a bit down today," the emotion engine analyzes this data, and the generative AI model reconfigures the schedule to slightly reduce the day's tasks. The optimized schedule is then immediately notified to the user's device, allowing the user to review and adjust it.

[0510] Thus, the system of the present invention, by combining an emotion engine, achieves flexible schedule management that responds to the user's psychological state. Furthermore, it aims to improve the user's quality of life in the long term through a continuous feedback loop.

[0511] The following describes the processing flow.

[0512] Step 1:

[0513] The server receives schedule and task information from the user's device. This includes aggregating information through APIs of calendar and task management applications.

[0514] Step 2:

[0515] The server uses an emotion engine to recognize the user's emotional state based on the voice and text data acquired through the terminal. It determines the user's emotions by analyzing the tone of voice and the content of the text.

[0516] Step 3:

[0517] The server integrates the received schedule and task information, along with the recognized emotion information, into a database. Based on this integrated data, it runs a generative AI model to calculate the optimal schedule and task allocation.

[0518] Step 4:

[0519] The server creates and sends emotionally sensitive suggestions to the terminal based on the optimization results from the generated AI model. These suggestions include adjusting task priorities and reducing tasks as needed.

[0520] Step 5:

[0521] The terminal displays suggestions received from the server to the user as notifications. The user can review the suggested schedule and tasks and make changes or adjustments.

[0522] Step 6:

[0523] Users can provide feedback on suggestions via voice or text input. This feedback may include additional information regarding their feelings.

[0524] Step 7:

[0525] The device sends user feedback to the server. The server stores the received feedback in a database and uses it to optimize future generational AI models.

[0526] Step 8:

[0527] The server adjusts the parameters of the generated AI model based on feedback, improving the accuracy of the emotion engine. This ensures that future optimization suggestions are more tailored to the user.

[0528] (Example 2)

[0529] Next, we will describe Example 2. 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."

[0530] Modern individuals and organizations face diverse activities and responsibilities, demanding efficient and stress-free time management and work optimization. However, current scheduling systems often fail to adequately consider users' emotional states and psychological burdens, resulting in a lack of long-term quality of life improvement. To address this challenge, there is a need for the development of time management systems that take user emotions into account.

[0531] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0532] In this invention, the server includes means for aggregating user timetable information and work information, means for optimizing the user's timetable and work using a generative AI model based on the aggregated information and emotional information, and means for identifying the user's emotional state using an emotional analysis engine and utilizing that emotional state as input information for the generative AI model. This enables flexible and efficient schedule management that takes the user's emotions into consideration, thereby improving the long-term quality of life.

[0533] "Timetable information" refers to information related to a user's schedule or planned activities, and includes data such as date, time, location, and activity details.

[0534] "Work information" refers to data that includes information about tasks and work content that a user should perform, including their priority and deadlines.

[0535] "Emotional information" refers to information that indicates the user's psychological state, and includes data on emotional tendencies obtained through the analysis of voice and text.

[0536] An "information terminal" is a device that a user can directly operate, and includes smartphones and computers.

[0537] "Evaluation information" refers to information based on user feedback and is used as an indicator for improving and optimizing the system.

[0538] An "emotion analysis engine" is software or a function that analyzes a user's voice and text data to identify their emotional state.

[0539] An "information storage device" is a mechanism for storing digital data, and databases and cloud storage fall into this category.

[0540] The system of this invention aims to optimize timetable management and work processes while taking user emotions into consideration. To this end, the system interacts with each other through the server, terminal, and user interface to improve the user's quality of life.

[0541] Server Embodiment

[0542] The server is responsible for acquiring and aggregating user timetable and work information from terminals. This information is stored in a database and used for subsequent analysis. The server utilizes an emotion analysis engine to analyze emotional information based on voice and text data received from users. The analysis results are input into a generative AI model, which then provides optimization suggestions for timetables and work. Specifically, the server uses speech recognition software to convert voice data into text and quantifies emotions using natural language processing. This quantified emotional information is provided to the generative AI model as a prompt, generating optimal suggestions tailored to the user's needs.

[0543] Terminal embodiment

[0544] The terminal pushes optimized timetables and tasks sent from the server to the user. By receiving these notifications, the user can quickly check their schedule and make necessary adjustments. The terminal also provides an interface for analyzing the user's emotions through voice and text input. This uses speech recognition technology and a text analysis engine. The terminal uses a smartphone or computer that the user can directly operate as the implementation device.

[0545] User Embodiment

[0546] Users interact with the system through their terminals and evaluate the provided timetables and work suggestions. They provide feedback as needed, and this feedback contributes to improving the system's optimization process. For example, a user might input something like "I'm feeling a bit down today" into their terminal, and this emotional information is analyzed and reflected by the system, which then reconfigures the schedule. The optimized schedule is immediately notified, allowing the user to review it and make further adjustments.

[0547] Specific example: For instance, if a user enters "I want to relax today" into their device, the server analyzes that emotion, and a generative AI model suggests increasing leisure time in their schedule. This allows the user to spend more relaxing time.

[0548] An example of a prompt message is, "Generate a schedule that reflects the user's emotions." This allows for flexible schedule management that takes the user's psychological state into consideration.

[0549] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0550] Step 1:

[0551] The server retrieves timetable and work information from the user's terminal. It receives data about the user's schedule and work content as input, aggregates this data, and stores it in a database. Specifically, this process involves receiving information using the HTTP protocol in response to data requests and storing the information through a database management system. The output is the user's schedule and work information, integrated on the server side.

[0552] Step 2:

[0553] The terminal acquires voice or text data entered by the user. The input data consists of text related to the user's statements and emotions, obtained through speech recognition or text input interfaces on the terminal. The terminal sends this data to a server, which uses it as input for sentiment analysis. Specific operations include speech-to-text conversion using a speech recognition API and direct input using a text box. The output is formatted text data for sentiment analysis.

[0554] Step 3:

[0555] The server analyzes text data received from the terminal using an emotion analysis engine. It uses natural language processing techniques to identify the emotional state of the acquired text data. This analysis quantifies the degree of positive or negative emotion. The specific operation involves inputting data into the emotion analysis algorithm and quantifying the results. The output is data quantified as emotional information.

[0556] Step 4:

[0557] The server inputs analyzed emotional information into a generative AI model to generate an optimized schedule and work suggestions. The input data consists of the user's emotional state and existing schedule information, which are used to generate prompt messages. The generative AI model uses these prompts to construct the most suitable suggestions for the user. Specifically, the process involves calling the generative AI model and performing calculations for suggestion generation. The output is an optimized schedule and work suggestions.

[0558] Step 5:

[0559] The device pushes optimized schedules and suggestions received from the server to the user. The input is suggestion data received from the server, and the device's notification system displays it. Specific actions include sending and displaying notifications in real time. The output is an optimization suggestion notification that the user can view on their device.

[0560] Step 6:

[0561] Users review optimization suggestions via their terminals and provide feedback as needed. They receive the presented schedule and work proposals as input, and evaluate and modify them based on their own judgment. This information is then sent back to the server to aid in the continuous optimization of the system. Specific actions include filling out feedback forms and submitting proposed revisions. The output consists of evaluation information and proposed changes sent back to the server as feedback.

[0562] (Application Example 2)

[0563] Next, we will explain application example 2. In the following explanation, 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."

[0564] Traditional schedule management systems managed schedules and tasks uniformly without considering the user's emotional state, thus failing to adequately reduce user psychological burden and improve their quality of life. Furthermore, they lacked the flexibility to adjust schedules to meet individual user needs.

[0565] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0566] In this invention, the server includes means for aggregating user schedule information and work information, means for optimizing the user's schedule and work using a generative AI model based on the aggregated information, and means for analyzing the user's emotional state and reflecting it in the schedule optimization. This enables detailed and flexible schedule management that takes the user's emotional state into consideration.

[0567] "User schedule information" refers to the details of the timetable and activities that the user plans to carry out.

[0568] "Work information" refers to the details of tasks and duties that a user needs to perform.

[0569] "Methods of aggregation" refer to the process of collecting data from multiple sources and combining them into a single, integrated dataset.

[0570] A "generative AI model" refers to a computational model designed using artificial intelligence technology for data analysis and decision-making.

[0571] "Means for analyzing emotional states" refers to processes designed to identify and evaluate a user's emotions and psychological state.

[0572] "Methods for reflecting schedule optimization" refers to the process of creating the most effective schedule for the user based on the analyzed data.

[0573] A "user terminal" refers to a computing device that a user can directly operate.

[0574] An "information storage device" refers to a device that stores data and retrieves and processes it as needed.

[0575] In embodiments of the present invention, a server aggregates user schedule information and work information from user terminals. The aggregated data is stored in an information aggregation device and used for analysis. The server uses sentiment analysis software (e.g., IBM Watson Tone Analyzer) to analyze voice and text data obtained from speech recognition software (e.g., Google Speech-to-Text) to determine the user's emotional state. This sentiment information is used as data input to optimize the user's schedule and work using a generative AI model, such as OpenAI GPT.

[0576] The optimized schedule and tasks are sent to the user's device as push notifications. The user's device is equipped with a user interface where the user can review the proposed schedule and make adjustments as needed. There is also a mechanism for users to provide feedback, which allows the server to incorporate that feedback into the generated AI model and continuously improve the optimization algorithm.

[0577] For example, if a user says to the device, "I'm not in the mood today," the system analyzes that emotion and uses a generative AI model to restructure the day's schedule in a less demanding way. In this way, flexible schedule management that responds to emotions is achieved. An example of a prompt would be, "If a user says, 'I'm feeling down today,' how would you optimize their schedule for the day based on that?"

[0578] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0579] Step 1:

[0580] The server collects schedule and work information from user terminals. This input data is stored in an information aggregation device. Schedule information includes the date, time, and planned content, while work information includes deadlines and priorities. This data is stored in an integrated format for later analysis.

[0581] Step 2:

[0582] The server receives voice or text data from the user's terminal. Voice recognition software converts the voice into text. This converted text is then input into sentiment analysis software to analyze the user's emotional state. For example, if the user says "I'm not in the mood today," the sentiment analysis software will determine that the emotion is negative.

[0583] Step 3:

[0584] The server inputs the analyzed emotional information into a generative AI model. The generative AI model comprehensively considers the user's schedule and work information, as well as their emotional state, to generate an optimal schedule proposal. As a result of the data calculations, for example, the schedule may be streamlined or high-priority tasks may be reallocated.

[0585] Step 4:

[0586] The server pushes the generated optimization schedule to the user's device. The notification includes specific schedule changes and reasons, designed to be easily understood by the user. Based on this push notification information, the user can review and adjust the schedule as needed.

[0587] Step 5:

[0588] Users provide feedback on the provided schedule. This feedback includes satisfaction with the proposed content and suggestions for improvement. This feedback information is sent to the server and used to improve the algorithm of the generated AI model. This promotes continuous improvement in the accuracy of schedule optimization.

[0589] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0590] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0591] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0592] [Fourth Embodiment]

[0593] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0594] As shown in Figure 7, the 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.

[0595] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0596] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0597] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0598] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0599] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0600] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0601] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0602] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0603] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0604] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0605] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0606] The system of this invention is designed to efficiently manage user schedules and optimize tasks. In this system, a server plays a central role, handling user information and suggesting optimizations.

[0607] Server Embodiment

[0608] The server first collects schedule and task information from the user's device. The collected information is integrated and managed in a database. Next, the server inputs the aggregated information into a generating AI model to optimize the schedule and tasks. This AI model uses machine learning algorithms to generate optimal suggestions while considering the user's goals and priorities.

[0609] Terminal embodiment

[0610] The device notifies the user of optimized schedules and tasks sent from the server. Notifications are provided via push notifications and email for quick user review. The device also receives user feedback and sends it back to the server. The device provides user-friendly interfaces, including voice and text input.

[0611] User Embodiment

[0612] Users interact with the system through their terminals. They review proposed schedules and task information and provide correction requests and feedback as needed. This feedback is used to achieve personalized optimization tailored to the user's lifestyle and work requirements.

[0613] Specific example: If a user typically has many meetings on Mondays, the server takes this into account and optimizes scheduling other important tasks for Tuesday or later. The terminal notifies the user of tasks to be handled in the next few days and their priorities, and the user can provide voice feedback, such as "I'd like to add a task for this evening."

[0614] Thus, the system of the present invention, through the cooperation of a server and a terminal, enables users to manage their tasks quickly and efficiently, supporting a lifestyle that balances work and personal life.

[0615] The following describes the processing flow.

[0616] Step 1:

[0617] The server receives schedule and task information from the user's device. This includes retrieving data from calendar applications and task management tools via APIs.

[0618] Step 2:

[0619] The server stores the received information in a database and creates a unified schedule and task dataset for each user. This data is used as the basis for analysis by generative AI models.

[0620] Step 3:

[0621] The server inputs the integrated data into the generated AI model and performs optimization calculations that take into account the user's goals and priorities. The AI ​​model generates an efficient task allocation and schedule for the user.

[0622] Step 4:

[0623] The server prepares optimized scheduling information derived from the AI ​​model and sends it to the device. This can be in the form of push notifications, email, or in-app notifications, depending on the user's preference.

[0624] Step 5:

[0625] The terminal displays information received from the server on the user interface and notifies the user. The user can review this information and provide feedback on schedules and tasks as needed.

[0626] Step 6:

[0627] Users provide feedback on the proposed schedule using voice or text input. This feedback includes adding, deleting, modifying, and reprioritizing tasks.

[0628] Step 7:

[0629] The device sends the user feedback back to the server. The server updates its database based on the received feedback and incorporates it into the next optimization calculation.

[0630] Step 8:

[0631] The server uses the collected feedback to adaptively train the generated AI model, enabling it to make more accurate optimization suggestions in the future. This continuously improves the system's user experience.

[0632] (Example 1)

[0633] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] In today's busy lifestyle, effectively managing users' schedules and work information and proposing optimal schedules based on priorities and individual goals is difficult. Furthermore, conventional systems lack sufficient interfaces to reflect direct user feedback, making it difficult to optimize them to accurately reflect user needs.

[0635] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0636] In this invention, the server includes means for aggregating user schedule information and work information, means for integrating the aggregated information into an information storage device, and means for optimizing the user's schedule and work using a generated AI model based on the information in the information storage device, and means for notifying the user device of the optimized schedule and work. This enables flexible and efficient schedule proposals tailored to the user's priorities and goals.

[0637] "User schedule information" refers to information about activities and events that the user plans to participate in in the future, including details such as the date, time, location, and participants.

[0638] "Work information" refers to information about specific tasks or projects that a user needs to perform, including deadlines, priorities, and required resources.

[0639] "Means of aggregation" refers to methods or devices for gathering and organizing dispersed information in one place, and includes the process of data integration.

[0640] An "information storage device" is hardware or software that stores large amounts of information in a specific format and allows for efficient retrieval as needed.

[0641] A "generative AI model" is an artificial intelligence model designed based on machine learning algorithms, which performs predictions and optimizations based on the input data.

[0642] "Optimization" refers to the efficient adjustment of plans and resource allocations to best meet a particular objective or condition.

[0643] "User device" refers to a device that enables interaction between the user and the system, and includes smartphones, tablets, computers, and the like.

[0644] "Feedback" refers to information about opinions and reactions received from users, which is used to adjust and improve the system.

[0645] The embodiments for carrying out the present invention are shown below.

[0646] First, the server collects schedule and task information from the user's device. This information is obtained from the user's calendar app or task management app, and the data extracted by the device is sent to the server. The types of information include the date and time of events, priority, and deadline. When aggregating the information, it is recommended to use data encryption technology to ensure security. The data is also stored in an information storage device such as an SQL database, enabling efficient data access.

[0647] Next, the server inputs this aggregated information into a generating AI model. This AI model is built using a machine learning framework (e.g., TensorFlow or PyTorch) and optimizes schedules and tasks, taking into account the user's priorities and goals. Specifically, it analyzes historical data and suggests the most efficient way to manage time. In this process, generated prompts can be used to guide the model on how to process the data. An example of a prompt might be, "Consider the user's current schedule and optimize tasks based on next week's priorities."

[0648] The server then sends the optimized schedule and tasks to the terminal. The terminal receives this and notifies the user of the suggestions via push notifications or email. The terminal has interfaces such as voice input and touch input, through which the user can provide feedback. For example, if the user gives voice feedback such as "I would like to add a meeting this Friday," the terminal will send this information back to the server and update the database.

[0649] This system aims to adapt to the user's lifestyle and enable efficient time management. Feedback such as schedule changes and task additions are smoothly reflected, creating an environment where users can manage their time efficiently.

[0650] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0651] Step 1:

[0652] The server collects schedule and task information from the user's device. At this stage, the device receives data from calendar and task management apps as input and sends it to the server. Specifically, the device retrieves event dates and task deadlines from each app via API and securely sends the data to the server using encryption technology. The output is the raw schedule data stored on the server.

[0653] Step 2:

[0654] The server stores the received schedule and work information in its information storage device and integrates it into the database. At this time, it stores the multiple input datasets as structured data. Specifically, it adds schedule and task entries to the SQL database and generates the necessary indexes to enable efficient access. The output of this step is an integrated dataset in an accessible format.

[0655] Step 3:

[0656] The server inputs integrated information into a generating AI model to optimize schedules and tasks. The input is a dataset containing user priorities and historical behavior data. Specifically, it uses a machine learning framework to analyze the provided data and execute predictive algorithms. Following prompts, the AI ​​is given instructions such as, "Optimize tasks for next week." The output of this step is an optimized schedule and task list.

[0657] Step 4:

[0658] The server sends an optimized schedule and task details to the terminal. At this stage, the server outputs optimized data, which the terminal receives as input. Specifically, it generates data in JSON format and sends it to the terminal via an HTTP request. The output is a schedule that is visually displayed on the terminal.

[0659] Step 5:

[0660] The device notifies the user of an optimized schedule and collects any changes or feedback. The input is user feedback information. Specifically, it presents information to the user using notification bars and pop-up messages, and accepts feedback via voice recognition or touch input. The output of this step is the information returned to the server as feedback data.

[0661] Step 6:

[0662] The server updates the database based on user feedback and performs further optimization using the AI ​​model as needed. Inputs include user feedback and existing schedule information. Specifically, it analyzes the feedback, updates the database information, and performs new optimizations. The output of this step is the updated schedule and tasks.

[0663] (Application Example 1)

[0664] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0665] In modern society, managing individual activity plans and tasks can increase the time burden and significantly reduce the quality of life. To address this problem, effective activity planning methods tailored to individual users are needed. Furthermore, technologies with support functions for daily life are required.

[0666] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0667] In this invention, the server includes means for integrating user activity plan information and work information, means for optimizing the user's activity plan and work using a generated AI model based on the integrated information, and means for notifying the user's device of the optimized activity plan and work. This enables more efficient task management in the user's living environment. Furthermore, by equipping it with home support functions and providing daily support through voice support functions, the user can improve their quality of life.

[0668] "Activity plan information" refers to data on plans and schedules related to the user's daily life and work.

[0669] "Work information" refers to data related to the tasks and work content that the user is supposed to perform.

[0670] "Means of integration" refers to a function that centrally manages activity plan information and work information obtained from users and aggregates them in a database or similar system.

[0671] A "generative AI model" is an artificial intelligence model that uses machine learning techniques to create activity plans and task suggestions optimized for the user.

[0672] "Optimization means" refers to a function that uses a generative AI model to calculate the most efficient schedule based on the user's activity plan information and work information.

[0673] "User devices" refer to devices that users can directly operate, such as smartphones and personal computers.

[0674] "Notification methods" refer to ways to inform users of optimized activity plans and tasks, including features such as push notifications and voice alerts.

[0675] "Home-use support functions" refer to features incorporated into robots and digital assistant devices intended for home use that support the user's daily life.

[0676] "Voice support function" refers to a function that allows the user to interact with the system through voice input, and utilizes speech recognition technology.

[0677] The system for realizing this invention efficiently manages user activity plan information and work information to improve quality of life. A server collects activity plan information and work information from the user's device and integrates this information into a data storage device. The integrated information is analyzed using a generative AI model to optimize the user's activity plan and work for maximum efficiency. This optimized information is then communicated to the user's device.

[0678] User devices, such as smartphones and computers, have the function of notifying the user of optimized activity plans and tasks visually and audibly. Devices with home assistance functions interface with the user using voice assistance functions to support the user's daily life. These voice assistance functions can notify the user of daily tasks by voice and accept voice input from the user.

[0679] For example, the server might analyze a user's activity on Monday, when many appointments are concentrated, and suggest tasks that can be moved to Tuesday or later to provide a more efficient plan. The user can then provide feedback via voice input, such as "I want to do this appointment earlier."

[0680] An example of a prompt for a generating AI model could be: "Optimize user ID 123's schedule for this week and create suggestions to prioritize high-priority tasks." This would significantly improve the user's task management and quality of life.

[0681] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0682] Step 1:

[0683] The server receives activity plan information and work information as input from user devices. This data includes each user's schedule and task information. The server aggregates this information and stores it in a data storage device.

[0684] Step 2:

[0685] The server retrieves aggregated information from data storage and inputs it into the generating AI model. By generating prompt statements and giving instructions to the AI ​​model, it performs data analysis to optimize the user's activity plan and tasks. This results in an optimized schedule that takes into account the user's priorities and efficiency.

[0686] Step 3:

[0687] The server sends optimized schedule and task information to the user's device. The device notifies the user of this information in audio or visual format. Specifically, it can notify the user via push notifications or voice alerts.

[0688] Step 4:

[0689] Users provide feedback on the schedules and tasks they receive. They can input requests to add or modify new tasks via voice or text through their device.

[0690] Step 5:

[0691] The device then sends the user feedback back to the server. The server records this feedback in its data storage and incorporates it into the generated AI model. This ensures that user feedback is taken into consideration for future optimizations.

[0692] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0693] The system of this invention aims to optimize schedule management and tasks while taking user emotions into consideration. This will help users lead more comfortable and efficient daily lives.

[0694] Server Embodiment

[0695] The server retrieves data from the user's device to aggregate the user's schedule and task information. This data is stored in a database and used for subsequent analysis. Furthermore, the server utilizes an emotion engine to recognize emotions based on the voice and text data received from the user. This emotion information is input into a generative AI model and reflected in the optimization suggestions for schedules and tasks.

[0696] Terminal embodiment

[0697] The device notifies the user of optimized schedules and tasks sent from the server, as well as personalized suggestions based on sentiment information. These notifications are delivered via push notifications, allowing users to access them quickly. The device also provides an interface for the sentiment engine to analyze the user's speech and writing through voice and text input.

[0698] User Embodiment

[0699] Users interact with the system using their devices. They evaluate the provided schedule and task suggestions and provide feedback as needed. This includes emotional feedback based on the user's stress and satisfaction levels. This feedback is used to improve subsequent optimization processes.

[0700] Specific example: If a user tells the server via their device one morning, "I'm feeling a bit down today," the emotion engine analyzes this data, and the generative AI model reconfigures the schedule to slightly reduce the day's tasks. The optimized schedule is then immediately notified to the user's device, allowing the user to review and adjust it.

[0701] Thus, the system of the present invention, by combining an emotion engine, achieves flexible schedule management that responds to the user's psychological state. Furthermore, it aims to improve the user's quality of life in the long term through a continuous feedback loop.

[0702] The following describes the processing flow.

[0703] Step 1:

[0704] The server receives schedule and task information from the user's device. This includes aggregating information through APIs of calendar and task management applications.

[0705] Step 2:

[0706] The server uses an emotion engine to recognize the user's emotional state based on the voice and text data acquired through the terminal. It determines the user's emotions by analyzing the tone of voice and the content of the text.

[0707] Step 3:

[0708] The server integrates the received schedule and task information, along with the recognized emotion information, into a database. Based on this integrated data, it runs a generative AI model to calculate the optimal schedule and task allocation.

[0709] Step 4:

[0710] The server creates and sends emotionally sensitive suggestions to the terminal based on the optimization results from the generated AI model. These suggestions include adjusting task priorities and reducing tasks as needed.

[0711] Step 5:

[0712] The terminal displays suggestions received from the server to the user as notifications. The user can review the suggested schedule and tasks and make changes or adjustments.

[0713] Step 6:

[0714] Users can provide feedback on suggestions via voice or text input. This feedback may include additional information regarding their feelings.

[0715] Step 7:

[0716] The device sends user feedback to the server. The server stores the received feedback in a database and uses it to optimize future generational AI models.

[0717] Step 8:

[0718] The server adjusts the parameters of the generated AI model based on feedback, improving the accuracy of the emotion engine. This ensures that future optimization suggestions are more tailored to the user.

[0719] (Example 2)

[0720] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] Modern individuals and organizations face diverse activities and responsibilities, demanding efficient and stress-free time management and work optimization. However, current scheduling systems often fail to adequately consider users' emotional states and psychological burdens, resulting in a lack of long-term quality of life improvement. To address this challenge, there is a need for the development of time management systems that take user emotions into account.

[0722] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0723] In this invention, the server includes means for aggregating user timetable information and work information, means for optimizing the user's timetable and work using a generative AI model based on the aggregated information and emotional information, and means for identifying the user's emotional state using an emotional analysis engine and utilizing that emotional state as input information for the generative AI model. This enables flexible and efficient schedule management that takes the user's emotions into consideration, thereby improving the long-term quality of life.

[0724] "Timetable information" refers to information related to a user's schedule or planned activities, and includes data such as date, time, location, and activity details.

[0725] "Work information" refers to data that includes information about tasks and work content that a user should perform, including their priority and deadlines.

[0726] "Emotional information" refers to information that indicates the user's psychological state, and includes data on emotional tendencies obtained through the analysis of voice and text.

[0727] An "information terminal" is a device that a user can directly operate, and includes smartphones and computers.

[0728] "Evaluation information" refers to information based on user feedback and is used as an indicator for improving and optimizing the system.

[0729] An "emotion analysis engine" is software or a function that analyzes a user's voice and text data to identify their emotional state.

[0730] An "information storage device" is a mechanism for storing digital data, and databases and cloud storage fall into this category.

[0731] The system of this invention aims to optimize timetable management and work processes while taking user emotions into consideration. To this end, the system interacts with each other through the server, terminal, and user interface to improve the user's quality of life.

[0732] Server Embodiment

[0733] The server is responsible for acquiring and aggregating user timetable and work information from terminals. This information is stored in a database and used for subsequent analysis. The server utilizes an emotion analysis engine to analyze emotional information based on voice and text data received from users. The analysis results are input into a generative AI model, which then provides optimization suggestions for timetables and work. Specifically, the server uses speech recognition software to convert voice data into text and quantifies emotions using natural language processing. This quantified emotional information is provided to the generative AI model as a prompt, generating optimal suggestions tailored to the user's needs.

[0734] Terminal embodiment

[0735] The terminal pushes optimized timetables and tasks sent from the server to the user. By receiving these notifications, the user can quickly check their schedule and make necessary adjustments. The terminal also provides an interface for analyzing the user's emotions through voice and text input. This uses speech recognition technology and a text analysis engine. The terminal uses a smartphone or computer that the user can directly operate as the implementation device.

[0736] User Embodiment

[0737] Users interact with the system through their terminals and evaluate the provided timetables and work suggestions. They provide feedback as needed, and this feedback contributes to improving the system's optimization process. For example, a user might input something like "I'm feeling a bit down today" into their terminal, and this emotional information is analyzed and reflected by the system, which then reconfigures the schedule. The optimized schedule is immediately notified, allowing the user to review it and make further adjustments.

[0738] Specific example: For instance, if a user enters "I want to relax today" into their device, the server analyzes that emotion, and a generative AI model suggests increasing leisure time in their schedule. This allows the user to spend more relaxing time.

[0739] An example of a prompt message is, "Generate a schedule that reflects the user's emotions." This allows for flexible schedule management that takes the user's psychological state into consideration.

[0740] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0741] Step 1:

[0742] The server retrieves timetable and work information from the user's terminal. It receives data about the user's schedule and work content as input, aggregates this data, and stores it in a database. Specifically, this process involves receiving information using the HTTP protocol in response to data requests and storing the information through a database management system. The output is the user's schedule and work information, integrated on the server side.

[0743] Step 2:

[0744] The terminal acquires voice or text data entered by the user. The input data consists of text related to the user's statements and emotions, obtained through speech recognition or text input interfaces on the terminal. The terminal sends this data to a server, which uses it as input for sentiment analysis. Specific operations include speech-to-text conversion using a speech recognition API and direct input using a text box. The output is formatted text data for sentiment analysis.

[0745] Step 3:

[0746] The server analyzes text data received from the terminal using an emotion analysis engine. It uses natural language processing techniques to identify the emotional state of the acquired text data. This analysis quantifies the degree of positive or negative emotion. The specific operation involves inputting data into the emotion analysis algorithm and quantifying the results. The output is data quantified as emotional information.

[0747] Step 4:

[0748] The server inputs analyzed emotional information into a generative AI model to generate an optimized schedule and work suggestions. The input data consists of the user's emotional state and existing schedule information, which are used to generate prompt messages. The generative AI model uses these prompts to construct the most suitable suggestions for the user. Specifically, the process involves calling the generative AI model and performing calculations for suggestion generation. The output is an optimized schedule and work suggestions.

[0749] Step 5:

[0750] The device pushes optimized schedules and suggestions received from the server to the user. The input is suggestion data received from the server, and the device's notification system displays it. Specific actions include sending and displaying notifications in real time. The output is an optimization suggestion notification that the user can view on their device.

[0751] Step 6:

[0752] Users review optimization suggestions via their terminals and provide feedback as needed. They receive the presented schedule and work proposals as input, and evaluate and modify them based on their own judgment. This information is then sent back to the server to aid in the continuous optimization of the system. Specific actions include filling out feedback forms and submitting proposed revisions. The output consists of evaluation information and proposed changes sent back to the server as feedback.

[0753] (Application Example 2)

[0754] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0755] Traditional schedule management systems managed schedules and tasks uniformly without considering the user's emotional state, thus failing to adequately reduce user psychological burden and improve their quality of life. Furthermore, they lacked the flexibility to adjust schedules to meet individual user needs.

[0756] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0757] In this invention, the server includes means for aggregating user schedule information and work information, means for optimizing the user's schedule and work using a generative AI model based on the aggregated information, and means for analyzing the user's emotional state and reflecting it in the schedule optimization. This enables detailed and flexible schedule management that takes the user's emotional state into consideration.

[0758] "User schedule information" refers to the details of the timetable and activities that the user plans to carry out.

[0759] "Work information" refers to the details of tasks and duties that a user needs to perform.

[0760] "Methods of aggregation" refer to the process of collecting data from multiple sources and combining them into a single, integrated dataset.

[0761] A "generative AI model" refers to a computational model designed using artificial intelligence technology for data analysis and decision-making.

[0762] "Means for analyzing emotional states" refers to processes designed to identify and evaluate a user's emotions and psychological state.

[0763] "Methods for reflecting schedule optimization" refers to the process of creating the most effective schedule for the user based on the analyzed data.

[0764] A "user terminal" refers to a computing device that a user can directly operate.

[0765] An "information storage device" refers to a device that stores data and retrieves and processes it as needed.

[0766] In embodiments of the present invention, a server aggregates user schedule information and work information from user terminals. The aggregated data is stored in an information aggregation device and used for analysis. The server uses sentiment analysis software (e.g., IBM Watson Tone Analyzer) to analyze voice and text data obtained from speech recognition software (e.g., Google Speech-to-Text) to determine the user's emotional state. This sentiment information is used as data input to optimize the user's schedule and work using a generative AI model, such as OpenAI GPT.

[0767] The optimized schedule and tasks are sent to the user's device as push notifications. The user's device is equipped with a user interface where the user can review the proposed schedule and make adjustments as needed. There is also a mechanism for users to provide feedback, which allows the server to incorporate that feedback into the generated AI model and continuously improve the optimization algorithm.

[0768] For example, if a user says to the device, "I'm not in the mood today," the system analyzes that emotion and uses a generative AI model to restructure the day's schedule in a less demanding way. In this way, flexible schedule management that responds to emotions is achieved. An example of a prompt would be, "If a user says, 'I'm feeling down today,' how would you optimize their schedule for the day based on that?"

[0769] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0770] Step 1:

[0771] The server collects schedule and work information from user terminals. This input data is stored in an information aggregation device. Schedule information includes the date, time, and planned content, while work information includes deadlines and priorities. This data is stored in an integrated format for later analysis.

[0772] Step 2:

[0773] The server receives voice or text data from the user's terminal. Voice recognition software converts the voice into text. This converted text is then input into sentiment analysis software to analyze the user's emotional state. For example, if the user says "I'm not in the mood today," the sentiment analysis software will determine that the emotion is negative.

[0774] Step 3:

[0775] The server inputs the analyzed emotional information into a generative AI model. The generative AI model comprehensively considers the user's schedule and work information, as well as their emotional state, to generate an optimal schedule proposal. As a result of the data calculations, for example, the schedule may be streamlined or high-priority tasks may be reallocated.

[0776] Step 4:

[0777] The server pushes the generated optimization schedule to the user's device. The notification includes specific schedule changes and reasons, designed to be easily understood by the user. Based on this push notification information, the user can review and adjust the schedule as needed.

[0778] Step 5:

[0779] Users provide feedback on the provided schedule. This feedback includes satisfaction with the proposed content and suggestions for improvement. This feedback information is sent to the server and used to improve the algorithm of the generated AI model. This promotes continuous improvement in the accuracy of schedule optimization.

[0780] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0781] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0782] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0783] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0784] Figure 9 shows an emotion map 400 in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0785] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0786] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0787] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0788] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0789] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0790] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0791] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a 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 the input data.

[0792] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0793] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0794] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0795] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0796] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0797] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0798] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0799] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0800] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0801] The following is further disclosed regarding the embodiments described above.

[0802] (Claim 1)

[0803] A means of aggregating user schedule information and task information,

[0804] A means to optimize the user's schedule and tasks using a generative AI model based on aggregated information,

[0805] A means of notifying the user terminal of optimized schedules and tasks,

[0806] A means of collecting user feedback and incorporating it into the generated AI model,

[0807] A system that includes this.

[0808] (Claim 2)

[0809] The system according to claim 1, which proposes schedule and task optimization taking into account the user's priorities and goal information.

[0810] (Claim 3)

[0811] The system according to claim 1, comprising integrating aggregated information into a database and analyzing a generated AI model based on the information in the database.

[0812] "Example 1"

[0813] (Claim 1)

[0814] A means of aggregating user schedule information and work information,

[0815] A means for integrating aggregated information into an information storage device and optimizing the user's schedule and work using an AI model generated based on the information in the information storage device,

[0816] Means for notifying the user device of optimized schedules and tasks,

[0817] A means of collecting user feedback and incorporating it into the generated AI model,

[0818] A system that includes this.

[0819] (Claim 2)

[0820] The system according to claim 1, which proposes optimization of schedules and tasks, taking into account the user's priorities and goal information.

[0821] (Claim 3)

[0822] The system according to claim 1, which receives voice or text provided by the user as an interface during work optimization, and sends feedback to the server for reflection.

[0823] "Application Example 1"

[0824] (Claim 1)

[0825] A means for integrating user activity plan information and work information,

[0826] A means to optimize user activity plans and tasks using a generative AI model based on integrated information,

[0827] Means for notifying the user device of optimized activity plans and tasks,

[0828] A means of collecting user response information and reflecting it in the generated AI model,

[0829] A means for equipping home support functions and providing voice support functions,

[0830] A system that includes this.

[0831] (Claim 2)

[0832] The system according to claim 1, which proposes an activity plan and work optimization taking into account the user's selection indicators and goal information.

[0833] (Claim 3)

[0834] The system according to claim 1, comprising integrating the combined information into a data storage device and analyzing the generated AI model based on the information in the data storage device.

[0835] "Example 2 of combining an emotion engine"

[0836] (Claim 1)

[0837] A means for aggregating user timetable information and work information,

[0838] A means of optimizing the user's timetable and tasks using a generative AI model based on aggregated information and emotional information,

[0839] A means of notifying information terminals of optimized timetables and tasks,

[0840] A means of collecting user evaluation information and reflecting it in the generated AI model,

[0841] A means of identifying a user's emotional state using an emotion analysis engine,

[0842] A means of utilizing emotional states as input information for generating AI models,

[0843] A system that includes this.

[0844] (Claim 2)

[0845] The system according to claim 1, which proposes timetable and work optimizations taking into account user priorities and objectives.

[0846] (Claim 3)

[0847] The system according to claim 1, comprising integrating aggregated information into an information storage device and analyzing a generated AI model based on the information in the information storage device.

[0848] "Application example 2 when combining with an emotional engine"

[0849] (Claim 1)

[0850] A means for aggregating user schedule information and work information,

[0851] A means to optimize the user's schedule and work using a generative AI model based on aggregated information,

[0852] A means of notifying the user terminal of an optimized schedule and tasks,

[0853] A means of analyzing the user's emotional state and reflecting it in schedule optimization,

[0854] A means of collecting user feedback and incorporating it into the generated AI model,

[0855] A system that includes this.

[0856] (Claim 2)

[0857] The system according to claim 1, which proposes schedule and work optimization taking into account the user's priorities and goal information.

[0858] (Claim 3)

[0859] The system according to claim 1, comprising integrating the collected information into an information accumulating device and analyzing the generated AI model based on the information from the information accumulating device. [Explanation of symbols]

[0860] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of aggregating user schedule information and task information, A means to optimize the user's schedule and tasks using a generative AI model based on aggregated information, A means of notifying the user terminal of optimized schedules and tasks, A means of collecting user feedback and incorporating it into the generated AI model, A system that includes this.

2. The system according to claim 1, which proposes the optimization of schedules and tasks, taking into account the user's priorities and goal information.

3. The system according to claim 1, comprising integrating the aggregated information into a database and analyzing the generated AI model based on the information in the database.

Images