system

Abstract

We provide the system. [Solution] A means for users to input schedules, A means by which the terminal sends user input data to the server, A means for analyzing the schedule data received by the server, A means for optimizing the analyzed schedule data, A means of sending an optimized schedule to the terminal, A system that includes means for users to review and modify their optimized schedules.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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 today's busy living environment, it is very difficult to efficiently manage schedules, process emails, manage tasks, and collect necessary information. As a result, an individual's productivity decreases, and it becomes difficult to achieve long-term goals for self-fulfillment. Also, these tasks are complex and time-consuming, imposing a great burden on users. The present invention aims to efficiently solve these problems by utilizing generative AI and support the improvement of individual productivity and self-fulfillment.

Means for Solving the Problems

[0005] This invention proposes a system in which a terminal sends a schedule entered by a user to a server, where AI analyzes and optimizes it. Specifically, the server analyzes the received schedule data, generates an optimal schedule that eliminates duplication and waste, and sends it to the terminal for the user to review and modify. In addition, for email processing, the system provides a system in which the terminal sends received email data to a server, where AI on the server side determines the importance and spam of the email and generates a summary and suggested replies. Furthermore, it provides a system in which the terminal sends tasks entered by a user to a server, where AI on the server side analyzes them, determines priorities and dependencies, generates an optimal task order and timeline, and sends it to the terminal. For information gathering, the system proposes a system in which the user enters an information gathering request, the terminal sends the request to the server, the AI ​​on the server side collects information from a specific data source, generates a summarized report, and sends it to the terminal. It also provides a system in which the user enters a long-term goal, the AI ​​on the server side works backward to set annual goals, and further generates a task schedule broken down into monthly and weekly units, sends it to the terminal, and allows the user to review and execute it. This enables users to efficiently manage their schedules, process emails, manage tasks, and gather information, leading to increased personal productivity and self-realization.

[0006] "User" refers to an individual or group that uses the system.

[0007] A "terminal" refers to electronic devices such as computers and smartphones that users use for input and output.

[0008] A "server" refers to a centralized management device that processes data received from terminals and transmits the results back to those terminals.

[0009] "Schedule" refers to the planned schedule or timetable created by the user.

[0010] "Analysis" refers to the process of thoroughly examining input data and understanding the meaning and structure of the information.

[0011] "Optimization" refers to adjusting something to achieve maximum efficiency and effectiveness within given conditions.

[0012] "Email" refers to electronic messages sent and received via the internet.

[0013] A "task" refers to an activity or work performed in order to achieve a specific objective.

[0014] "Information gathering" refers to the act of collecting data and facts related to a specific topic.

[0015] "AI" (Artificial Intelligence) refers to a computer system that mimics human intelligence, and in this invention, it is used for data analysis and optimization.

[0016] "Goals" refer to specific outcomes or objectives that users wish to achieve.

[0017] "Working backward" refers to the process of planning the intermediate steps and necessary tasks by working backward from the final goal.

[0018] "Summarizing" refers to shortening and summarizing the main points of information.

[0019] A "suggested reply" refers to a template for an appropriate response to a received message.

[0020] "Priority" refers to the criteria for sorting multiple tasks or schedules based on their importance and urgency.

[0021] "Dependency" refers to a relationship in which one task depends on the completion of another task.

[0022] A "report" refers to a document that compiles collected information and analysis results. [Brief explanation of the drawing]

[0023] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example ② when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example ② when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0024] 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.

[0025] First, let's explain the terminology used in the following explanation.

[0026] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0027] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0028] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0029] 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).

[0030] 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."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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".

[0044] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering. It also provides support for achieving long-term goals for self-realization.

[0045] Schedule management

[0046] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, optimizing it by eliminating duplicates and unnecessary information. The optimized schedule is sent to the device, where the user can review and modify it.

[0047] Specific example:

[0048] When a user registers their schedule for the following week, the AI ​​detects any overlapping meeting times and suggests moving them to a different, more suitable time.

[0049] Email Processing

[0050] The user receives an email on their device. The device sends the received email data to the server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The summary and suggested reply are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[0051] Specific example:

[0052] When a user receives a large volume of emails, the AI ​​prioritizes important emails and provides templates to make replying easier.

[0053] Task management

[0054] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, and sends the generated task schedule to the device. The user confirms and executes the tasks.

[0055] Specific example:

[0056] When a user enters tasks for a new project, the AI ​​considers the dependencies between tasks and suggests a natural order and estimated time for each.

[0057] Information gathering

[0058] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the AI ​​collects information from the specified data source. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report.

[0059] Specific example:

[0060] When a user submits a market research request, the AI ​​gathers the latest statistical data and trending articles and provides a clearly summarized report.

[0061] Support for reverse planning to achieve self-realization

[0062] The user inputs their long-term goal from their device. The server receives the long-term goal, and the AI ​​works backward to set annual goals. Furthermore, the annual goals are broken down into monthly and weekly tasks. The generated task schedule is sent to the device, which the user reviews and executes.

[0063] Specific example:

[0064] If a user sets a goal like "I will become independent and start my own business in 10 years," the AI ​​will work backward to determine the necessary steps, such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[0065] These features enable users to streamline their daily tasks and work towards achieving long-term goals. This system leverages the power of generative AI to effectively support user productivity and self-realization.

[0066] The following describes the processing flow.

[0067] Schedule management

[0068] Step 1:

[0069] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[0070] Step 2:

[0071] The device sends user input data to the server. For example, it might send data in the format "2023-10-01: Meeting, 2023-10-02: Client visit".

[0072] Step 3:

[0073] The server analyzes the schedule data it receives. It checks the format and content of the input data to ensure there are no errors or missing information.

[0074] Step 4:

[0075] The server uses AI to optimize schedule data. Specifically, it adjusts overlapping appointments, prioritizes them based on importance, and reduces unnecessary travel time.

[0076] Step 5:

[0077] The server sends an optimized schedule to the terminal. It is then sent again in JSON format, etc.

[0078] Step 6:

[0079] The device notifies the user of the optimized schedule it has received. The user then uses this information to review and modify their schedule.

[0080] Email Processing

[0081] Step 1:

[0082] The user receives an email on their device. A notification is sent indicating that a new email is available.

[0083] Step 2:

[0084] The device sends received email data to the server. This data includes information such as the email content and sender.

[0085] Step 3:

[0086] The server analyzes the emails it receives. AI determines the importance of the emails and filters them to determine if they are spam.

[0087] Step 4:

[0088] The AI ​​on the server generates email summaries and suggested replies. For example, in response to an email requesting meeting confirmation, it can generate a suggested reply such as "I can attend."

[0089] Step 5:

[0090] The server sends a summary and a draft reply to the terminal. Data containing the summary and draft reply is sent.

[0091] Step 6:

[0092] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[0093] Task management

[0094] Step 1:

[0095] The user enters the task from their device. They fill in the project name and specific task details.

[0096] Step 2:

[0097] The terminal sends the entered task data to the server. The data is sent in JSON format, among others.

[0098] Step 3:

[0099] The server analyzes the received task data. The AI ​​determines the task priorities and dependencies.

[0100] Step 4:

[0101] The AI ​​on the server generates the optimal task order and timeline. For example, it determines the task order based on the project's progress.

[0102] Step 5:

[0103] The server sends the generated task schedule to the terminal. Data containing the detailed schedule is sent.

[0104] Step 6:

[0105] The device notifies the user of the task schedule it has received. The user reviews the schedule and proceeds with execution.

[0106] Information gathering

[0107] Step 1:

[0108] The user enters an information gathering request from their device. They enter the topic or keywords they want to investigate.

[0109] Step 2:

[0110] The device sends an information collection request to the server.

[0111] Step 3:

[0112] The server receives the request, and the AI ​​collects information from specific data sources. It gathers necessary information from sources such as news websites and databases.

[0113] Step 4:

[0114] The AI ​​on the server summarizes the collected information and generates a report. It extracts the most important parts from the collected data.

[0115] Step 5:

[0116] The server sends the generated report to the terminal. Data containing a summary report is sent.

[0117] Step 6:

[0118] The device notifies the user of the reports it has received. The user reviews the reports and takes the necessary actions.

[0119] Support for reverse planning to achieve self-realization

[0120] Step 1:

[0121] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[0122] Step 2:

[0123] The device sends long-term goal data to the server.

[0124] Step 3:

[0125] The server receives the long-term goal, and the AI ​​works backward to set annual goals. Specific goals are defined for each year.

[0126] Step 4:

[0127] The AI ​​on the server breaks down the annual goals into monthly and weekly units and converts them into tasks.

[0128] Step 5:

[0129] The server sends the generated task schedule to the terminal. Detailed schedule data is sent.

[0130] Step 6:

[0131] The device notifies the user of the task schedule it has received. The user reviews the information and takes the necessary actions.

[0132] (Example 1)

[0133] 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."

[0134] We provide a system that efficiently supports users' daily work and self-realization by utilizing generative AI. Conventional systems lacked sufficient integration of schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization, making it difficult to improve user productivity. Furthermore, they lacked features to eliminate duplication and waste and optimize processes, resulting in cumbersome manual management.

[0135] 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.

[0136] In this invention, the server includes means for analyzing received data, means for optimizing the analyzed data, and means for transmitting the generated data to a terminal. This enables schedule optimization, email processing with importance assessment and spam filtering, task management considering priorities and dependencies, information gathering that collects and summarizes information from specific data sources, and self-actualization support that converts long-term goals into concrete tasks by working backward.

[0137] A "schedule" refers to a plan based on time and date, including the user's appointments.

[0138] "Terminal" refers to electronic devices used by users, such as smartphones and computers.

[0139] A "server" refers to a computer system that receives data sent by users and performs analysis and processing on it.

[0140] "Data analysis" refers to the process of processing received data and extracting meaningful information.

[0141] "Optimization" refers to adjustments made to eliminate redundancy and waste, resulting in an efficient state.

[0142] "Email" refers to electronic mail, including digital messages sent and received over the internet.

[0143] A "task" refers to any work or action that needs to be performed in order to achieve a specific goal.

[0144] "Information gathering" refers to the process of collecting data and knowledge necessary for a specific purpose.

[0145] "Long-term goals" refer to major objectives that are planned to be achieved over a long period of time.

[0146] A "generative AI model" refers to a model that uses artificial intelligence technology to generate output based on user input data and requests.

[0147] A "prompt statement" refers to an instruction given as input to an AI model.

[0148] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides five functions: schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization. The details are described below.

[0149] Schedule management

[0150] The user enters their schedule from their device. The device sends the entered schedule data to the server. The server uses a "generative AI model" to analyze the received schedule data, optimizing it by eliminating duplication and waste. The optimized schedule is sent to the device, which the user can then review and modify. For example, if a user registers their schedule for the following week, the "generative AI model" might detect a meeting time conflict and suggest moving it to a different, more appropriate time.

[0151] Example prompt message: "I have entered the schedule for next week. Please check for duplicates and inefficiencies and optimize it."

[0152] Email Processing

[0153] The user receives an email on their device. The device sends the received email data to a server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The generated summary and reply are sent to the device, where the user reviews and modifies them as needed before sending. For example, when a user receives a large number of emails, the AI ​​model on the server prioritizes important emails and provides templates to facilitate replies.

[0154] Example prompt: "Summarize the received email and generate a draft reply."

[0155] Task management

[0156] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. A generative AI model generates the optimal task order and timeline, and sends the generated task schedule to the device. The user reviews and executes the tasks. For example, when a user enters tasks for a new project, the AI ​​model considers the task dependencies and suggests a natural order and estimated time for each task.

[0157] Example prompt: "I have entered the tasks for this project. Please generate the optimal task order and schedule, taking dependencies and priorities into consideration."

[0158] Information gathering

[0159] The user enters a request for information gathering from their device. The device sends the information gathering request to the server. The server receives the request, and the AI ​​collects information from specific data sources. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report. For example, if a user enters a request for market research, the AI ​​model collects the latest statistical data and trending articles and provides a clearly summarized report.

[0160] Example prompt: "Collect data and trend articles for market research and generate a summarized report."

[0161] Support for reverse planning to achieve self-realization

[0162] The user enters a long-term goal from their device. The device sends the entered long-term goal to the server. The server receives the long-term goal and uses a generating AI model to set annual goals. Furthermore, it breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is sent to the device for the user to review and execute. For example, if the user sets "I will become independent and start my own business in 10 years," the AI ​​model will work backward to determine the necessary steps such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[0163] Example prompt: "Please create a schedule outlining the steps and plan necessary to start your own business in 10 years."

[0164] This system leverages the power of generative AI to support users in efficiently performing their tasks and achieving long-term goals. HTTP POST is used for communication between the server and the terminal, and data is exchanged in JSON format. Generative AI models play a crucial role in each function, analyzing user input data and providing optimal suggestions to improve productivity.

[0165] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0166] Schedule management

[0167] Step 1:

[0168] The user enters their schedule using a terminal. The entered data is generated in JSON format via the keyboard or touchscreen.

[0169] Step 2:

[0170] The terminal sends the entered schedule data to the server. Specifically, it sends the schedule data in JSON format using an HTTP POST request.

[0171] Step 3:

[0172] The server analyzes the received schedule data. A generative AI model is used for the analysis, performing pattern recognition to eliminate duplication and waste from the data.

[0173] Step 4:

[0174] The server generates an optimized schedule based on the analyzed data. The generated schedule is also converted to JSON format.

[0175] Step 5:

[0176] The server sends an optimized schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0177] Step 6:

[0178] Users can view the optimized schedule on their device and make adjustments as needed. The adjustment data is also saved in JSON format.

[0179] Email Processing

[0180] Step 1:

[0181] The user receives emails using their device. Emails are received via a standard email application.

[0182] Step 2:

[0183] The device sends the received email data to the server. The transmission format is JSON, and it uses an HTTP POST request.

[0184] Step 3:

[0185] The server analyzes the content of the email. A generative AI model is used for the analysis, including determining importance and filtering spam.

[0186] Step 4:

[0187] The server generates an email summary and a draft reply. The generated summary and draft reply are converted into JSON format.

[0188] Step 5:

[0189] The server sends the generated summary and proposed reply to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0190] Step 6:

[0191] The user reviews the summary and proposed reply on their device and makes revisions as needed. The revised reply is then sent via email.

[0192] Task management

[0193] Step 1:

[0194] The user enters a new task using a terminal. The entered data is generated in JSON format.

[0195] Step 2:

[0196] The terminal sends the entered task data to the server. Specifically, it sends the task data in JSON format using an HTTP POST request.

[0197] Step 3:

[0198] The server analyzes the received task data. A generative AI model is used for the analysis to determine task priorities and dependencies.

[0199] Step 4:

[0200] The server generates the optimal task order and timeline based on the analysis results. The generated task schedule is converted to JSON format.

[0201] Step 5:

[0202] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0203] Step 6:

[0204] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[0205] Information gathering

[0206] Step 1:

[0207] The user enters a data collection request using their device. The entered data is generated in JSON format.

[0208] Step 2:

[0209] The device sends an information collection request to the server. The transmission format is JSON, and it uses an HTTP POST request.

[0210] Step 3:

[0211] The server receives a request and uses a generative AI model to collect information from a specific data source. The collected information is obtained from databases or the internet.

[0212] Step 4:

[0213] The server summarizes the collected information and generates a report. The generated report is converted to JSON format.

[0214] Step 5:

[0215] The server sends the generated report to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0216] Step 6:

[0217] The user views the report on their device. The data in the report is modified as needed.

[0218] Support for reverse planning to achieve self-realization

[0219] Step 1:

[0220] The user enters their long-term goals using a device. The entered data is generated in JSON format.

[0221] Step 2:

[0222] The terminal sends the entered long-term goals to the server. The transmission format is JSON, and it uses an HTTP POST request.

[0223] Step 3:

[0224] The server receives the long-term goals and uses a generative AI model to set annual goals. The set goals are then converted into JSON format.

[0225] Step 4:

[0226] The server breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is then converted into JSON format.

[0227] Step 5:

[0228] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0229] Step 6:

[0230] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[0231] This allows the system to perform specific data processing and calculations for each function, providing optimized data and thereby improving user productivity.

[0232] (Application Example 1)

[0233] 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."

[0234] In traditional virtual store operations, managing staff schedules, handling customer inquiries via email, and managing tasks were often done manually, resulting in inefficiencies. Furthermore, there was a lack of tools to streamline operations, such as optimizing schedules, promptly addressing important emails, and prioritizing tasks. As a result, operational efficiency declined, placing a burden on store management.

[0235] 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.

[0236] In this invention, the server includes means for the user to input a schedule, means for the terminal to transmit the user's input data to the server, means for the server to analyze the received schedule data, means for optimizing the analyzed schedule data, means for transmitting the optimized schedule to the terminal, means for the user to confirm and modify the optimized schedule, means for optimizing staff schedules in a virtual store, and means for generating prompt statements when optimizing the schedule using a generative AI model. This enables efficient management of staff schedules in a virtual store.

[0237] A "user" is an individual or legal entity that uses the system or terminals to operate and manage a virtual store.

[0238] A "schedule" is a plan of the date, time, and content of events and tasks that the user enters.

[0239] A "device" refers to an input and display device such as a smartphone, tablet, or personal computer used by a user.

[0240] A "server" is a computer system that receives, analyzes, and optimizes data sent by users, and then returns the results to the terminal.

[0241] "Schedule data" refers to information about the schedule entered by the user.

[0242] "Analysis" refers to the process of analyzing schedule data and email data received by a server to extract and evaluate appropriate information.

[0243] "Optimization" refers to the efficient and effective organization and adjustment of schedules and task data.

[0244] A "virtual store" is an online store that provides goods and services via the internet.

[0245] "Staff" refers to the personnel who support the operation of the virtual store.

[0246] A "generative AI model" refers to an artificial intelligence algorithm trained to perform a specific task.

[0247] A "prompt statement" is an instruction given to a generative AI model, containing instructions for obtaining a specific result.

[0248] "Email" refers to messages sent and received electronically, and is used for customer inquiries and internal company communications.

[0249] A "task" refers to the work or tasks that a user is supposed to perform.

[0250] "Priority" refers to the order in which tasks and schedules are arranged based on their importance and urgency.

[0251] "Dependency" refers to a relationship where one task or schedule depends on another task or event.

[0252] A "summary" refers to a concise compilation of key information.

[0253] A "suggested reply" is a proposed response to a message, such as an email.

[0254] This invention is a system that utilizes a generative AI model to streamline daily operations in virtual stores and improve user productivity. This system primarily provides three main functions: schedule management, email processing, and task management. The implementation methods for each function are described below.

[0255] Schedule management

[0256] The user enters the staff schedule for the virtual store using a terminal. This schedule data is sent from the terminal to the server. The server analyzes the received schedule data, eliminating duplication and inefficiencies to optimize it. The optimized schedule is sent back to the terminal for the user to review and modify. At this time, a generation AI model is used to generate prompts for schedule optimization, and the AI ​​is instructed to perform the optimization work.

[0257] Email Processing

[0258] Emails received by the user are received on the device, and the data is sent to the server. The server analyzes the content of the emails, determines their importance, and performs spam filtering. Based on the analyzed content of the emails, AI generates summaries and suggested replies. The generated summaries and suggested replies are sent to the device, where the user reviews and modifies them, and sends them as needed.

[0259] Task management

[0260] When a user enters a new task from their device, the task data is sent to the server. The server analyzes the task data and uses a generative AI model to determine priorities and dependencies, generating an optimal task sequence and timeline. This enables efficient task management. The generated task schedule is sent to the device, where the user can review and execute it.

[0261] Hardware and software used

[0262] Hardware: Servers (e.g., AWS® EC2 instances), user devices (smartphones, tablets, PCs)

[0263] Software: Django framework (server-side program), generative AI model (e.g., OpenAI®, GPT-3®)

[0264] Examples of specific cases and prompt statements

[0265] Specific example

[0266] For example, consider a scenario where a store manager inputs staff shift schedules. If different shifts overlap, the server uses a generated AI model to optimize the schedule and suggest the best shift arrangement. Furthermore, when a large volume of customer inquiry emails arrive, the AI ​​generates summaries and suggested replies to support a quick response.

[0267] Example of a prompt

[0268] For schedule optimization: "Optimize this schedule: {'Mon': ['StaffA', 'StaffB'], 'Tue': ['StaffC', 'StaffD'], 'Wed': ['StaffA', 'StaffE']}"

[0269] For email processing: "Summarize and create a reply draft for this email: 'Dear Store, We have an urgent issue regarding our recent order...'"

[0270] Based on the above, the system of the present invention provides a concrete means to streamline daily operations in virtual store management and reduce the workload of users.

[0271] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0272] Step 1:

[0273] The user enters their schedule into the terminal. The terminal receives the entered schedule data and sends it to the server. The input data includes the date and time, event details, and information about the staff in charge. The output is the schedule data sent to the server.

[0274] Step 2:

[0275] The server analyzes the received schedule data. The analysis verifies data integrity and checks for duplication and unnecessary information. The input is the schedule data, and the output is the analysis results.

[0276] Step 3:

[0277] The server optimizes the analyzed schedule data. A generative AI model is used to generate prompts for optimization. These prompts are input to the AI ​​model to obtain the optimal schedule. The input consists of the analysis results and prompts, and the output is the optimized schedule data.

[0278] Step 4:

[0279] The server sends the optimized schedule data to the terminal. The terminal displays the received data and prompts the user for confirmation and correction. The input is the optimized schedule data, and the output is the schedule displayed on the terminal.

[0280] Step 5:

[0281] The user checks the received schedule and makes corrections if necessary. The corrected schedule data on the terminal is sent to the server again. The input is the correction data by the user, and the output is the corrected schedule data.

[0282] Step 6:

[0283] The user receives an email on the terminal. The terminal sends the received email data to the server. The input is the email data, and the output is the email data sent to the server.

[0284] Step 7:

[0285] The server analyzes the received email data, performs importance judgment and spam filtering. Using the generated AI model based on the analysis results, a summary and a reply plan are generated. The input is the email data, and the output is the summary and the reply plan.

[0286] Step 8:

[0287] The server sends the generated summary and reply plan to the terminal. The terminal displays them to the user, and the user makes confirmation and correction. The input is the summary and the reply plan, and the output is the data displayed to the user.

[0288] Step 9:

[0289] The user re - sends the summary and reply plan that have been confirmed and corrected to the server for final transmission. The input is the corrected summary and reply plan, and the output is the sent email.

[0290] Step 10:

[0291] The user enters a new task into the terminal. The terminal sends the entered task data to the server. The input is the task data, and the output is the task data sent to the server.

[0292] Step 11:

[0293] The server analyzes the received task data to determine priorities and dependencies. Based on the analysis results, a generative AI model is used to generate the optimal task order and timeline. The input is task data, and the output is the optimized task order and timeline.

[0294] Step 12:

[0295] The server sends the generated task schedule to the terminal. The terminal displays it to the user, who then reviews and executes the task schedule. The input is the optimized task schedule, and the output is the data displayed to the user.

[0296] Through the steps described above, the present invention provides concrete means for streamlining users' daily operations and supporting virtual store management.

[0297] 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.

[0298] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[0299] Schedule management

[0300] The user inputs a schedule from the terminal. The terminal sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotion and optimizes the schedule based on that emotion. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the terminal, and the user can view and modify it.

[0301] Specific example:

[0302] When the user registers a schedule for a meeting or a client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[0303] E-mail processing

[0304] The user receives an e-mail from the terminal. The terminal sends the received e-mail data to the server. The server analyzes the content of the e-mail, and the emotion engine recognizes the user's emotion and performs importance judgment and spam filtering. Also, the AI generates a summary and a reply proposal for the e-mail, and adjustments are made based on the user's emotion at that time. For example, if the user is tired, a simple reply proposal is made. The summary and the reply proposal are sent to the terminal, and the user can view, modify, and send them as needed.

[0305] Specific example:

[0306] When the user receives an important e-mail while feeling tired, the emotion engine generates a simple and quick reply proposal to reduce the user's burden.

[0307] Task management

[0308] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[0309] Specific example:

[0310] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[0311] Information gathering

[0312] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[0313] Specific example:

[0314] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[0315] Support for reverse planning to achieve self-realization

[0316] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[0317] Specific example:

[0318] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[0319] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[0320] The following describes the processing flow.

[0321] Schedule management processing steps

[0322] Step 1:

[0323] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[0324] Step 2:

[0325] The terminal sends user input data to the server. The data is often sent in formats such as JSON or XML.

[0326] Step 3:

[0327] The server analyzes the received schedule data. It checks the data format and performs checks for any discrepancies if necessary.

[0328] Step 4:

[0329] The server uses an emotion engine to recognize the user's current emotions. Specifically, it refers to emotion data previously recorded by the user or real-time emotion input.

[0330] Step 5:

[0331] The server optimizes the schedule data. For example, if a user is feeling stressed, it might add breaks to slow down the pace or adjust the order of important tasks.

[0332] Step 6:

[0333] The server sends an optimized schedule to the terminal.

[0334] Step 7:

[0335] The device notifies the user of an optimized schedule. The user can then review and modify the schedule based on this information.

[0336] Email Processing Steps

[0337] Step 1:

[0338] The user receives an email from their device. A notification appears as a pop-up or alert.

[0339] Step 2:

[0340] The device sends received email data to the server. This data includes information such as the email body, sender, and date / time.

[0341] Step 3:

[0342] The server analyzes the received emails, checking their content and determining their importance or whether they are spam.

[0343] Step 4:

[0344] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's fatigue level and stress level.

[0345] Step 5:

[0346] The server generates email summaries and suggested replies. For example, if the user is tired, it will generate a concise suggested reply.

[0347] Step 6:

[0348] The server sends a summary and a draft reply to the terminal.

[0349] Step 7:

[0350] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[0351] Task management processing steps

[0352] Step 1:

[0353] The user enters the task from their device. They fill in the project name and specific task details.

[0354] Step 2:

[0355] The terminal sends the entered task data to the server. The data format used is typically JSON or XML.

[0356] Step 3:

[0357] The server analyzes the received task data. It checks the data format and determines priorities and dependencies.

[0358] Step 4:

[0359] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's energy level and mood.

[0360] Step 5:

[0361] The server generates the optimal order and timeline for tasks, making adjustments based on emotions, such as scheduling important tasks during times of high concentration.

[0362] Step 6:

[0363] The server sends the generated task schedule to the terminal.

[0364] Step 7:

[0365] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[0366] Information gathering processing steps

[0367] Step 1:

[0368] The user enters an information gathering request from their device. They enter the topic, keywords, and purpose they want to investigate.

[0369] Step 2:

[0370] The device sends an information collection request to the server.

[0371] Step 3:

[0372] The server receives the request and uses an emotion engine to recognize the user's emotions.

[0373] Step 4:

[0374] The server collects information from specific data sources. It retrieves necessary information from sources such as news websites and academic journal databases.

[0375] Step 5:

[0376] The server summarizes the collected information and adjusts the report based on the user's emotions. For example, if the user is easily fatigued, a concise summary is generated.

[0377] Step 6:

[0378] The server sends the generated report to the terminal.

[0379] Step 7:

[0380] The device notifies the user of the report it has received. The user reviews the report and takes the necessary action.

[0381] Processing steps for supporting reverse engineering for self-realization

[0382] Step 1:

[0383] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[0384] Step 2:

[0385] The device sends long-term goal data to the server.

[0386] Step 3:

[0387] The server receives the long-term goals and uses an emotion engine to recognize the user's emotions.

[0388] Step 4:

[0389] The server uses AI to work backward and set annual goals. It defines specific steps and milestones.

[0390] Step 5:

[0391] The server breaks down annual goals into monthly and weekly units and converts them into tasks. It also makes adjustments based on emotions.

[0392] Step 6:

[0393] The server sends the generated task schedule to the terminal.

[0394] Step 7:

[0395] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[0396] (Example 2)

[0397] 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".

[0398] Traditional scheduling, email processing, task management, and information gathering systems often fail to consider user emotions, leading to stress and decreased work efficiency. This frequently resulted in users being unable to achieve their full productivity. To address this problem, dynamic adjustments based on user emotional states are required.

[0399] 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.

[0400] In this invention, the server includes means for an emotion engine to recognize the user's emotions, means for optimizing the schedule based on analysis and emotion recognition, and means for adjusting the generated summaries and response suggestions based on the emotions. This enables improved user productivity and reduced stress by making optimal adjustments according to the user's emotional state.

[0401] A "user" refers to a person who uses this system to manage their schedule, process emails, manage tasks, and gather information.

[0402] "Device" refers to electronic devices used by users, such as personal computers, smartphones, and tablets.

[0403] A "server" refers to a computer system that receives data sent from a terminal and performs analysis and optimization.

[0404] An "emotion engine" refers to software or hardware that recognizes a user's emotions and optimizes data based on those recognition results.

[0405] "Schedule data" refers to information about appointments and plans entered by the user.

[0406] "Analysis" refers to the process by which a server processes received data to understand and interpret its content, importance, dependencies, and other relevant information.

[0407] "Optimization" refers to adjusting schedules, task sequences, email summaries, and response drafts more effectively and efficiently based on analyzed data and user sentiment recognition results.

[0408] "Email data" refers to the content of emails received by a user and any accompanying information.

[0409] A "summary" refers to information that has been extracted and concisely compiled from the most important parts of an email or other information gathering results.

[0410] A "draft reply" refers to a suggested text that will be generated as a response to an email.

[0411] "Task data" refers to information about jobs and tasks entered by the user.

[0412] "Priority" refers to the criteria used to determine the order in which tasks and appointments entered by the user are executed, based on factors such as importance and urgency.

[0413] A "dependency" refers to a relationship where one task presupposes the completion of another task.

[0414] A "timeline" refers to a chronological arrangement of tasks and appointments that need to be completed within a specific period.

[0415] "Information gathering" refers to the process of obtaining necessary data from specific sources based on user instructions.

[0416] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[0417] Schedule management

[0418] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotions and optimizes the schedule based on those emotions. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the device, and the user can review and modify it.

[0419] Specific example:

[0420] When a user schedules a meeting or client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[0421] Example of a prompt:

[0422] "I'm entering this week's schedule. There are two important meetings and one client visit. Please adjust the schedule considering the stress level."

[0423] Email Processing

[0424] The user receives an email from their device. The device sends the received email data to the server. The server analyzes the email content, and the sentiment engine recognizes the user's emotions to determine importance and perform spam filtering. The AI ​​also generates an email summary and suggested replies, adjusting them based on the user's emotions. For example, if the user is fatigued, a simple reply suggestion might be made. The summary and suggested replies are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[0425] Specific example:

[0426] When a user receives an important email while feeling fatigued, the emotion engine generates a simple and quick response suggestion to reduce the user's burden.

[0427] Example of a prompt:

[0428] "Please provide a summary of the important email I received today and a draft reply. I am very tired right now, so a brief reply would be appreciated."

[0429] Task management

[0430] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[0431] Specific example:

[0432] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[0433] Example of a prompt:

[0434] "I'll enter today's tasks. These include meeting preparation, report writing, and presentation practice. Please create a schedule in the optimal order, taking my energy level into consideration."

[0435] Information gathering

[0436] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[0437] Specific example:

[0438] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[0439] Example of a prompt:

[0440] "Please gather information on recent market trends. I'm currently exhausted, so I'd prefer a concise summary report."

[0441] Support for reverse planning to achieve self-realization

[0442] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[0443] Specific example:

[0444] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[0445] Example of a prompt:

[0446] "My goal is to become independent and start my own business in 10 years. Please create annual, monthly, and weekly plans to achieve this goal, and adjust them to take my stress levels into consideration."

[0447] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[0448] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0449] Schedule management

[0450] Step 1:

[0451] The user enters their schedule from their device. For example, the user enters appointments for meetings or client visits into their device. This input data includes the date, time, and content of the appointment.

[0452] Step 2:

[0453] The terminal sends the entered schedule data to the server. The entered data is transferred to the server using an HTTP request. This operation constitutes data communication from the terminal to the server.

[0454] Step 3:

[0455] The server analyzes the received schedule data. A natural language processing engine (e.g., spaCy) is used to analyze the data's content. Here, the schedule's content, importance, and deadline are determined. The results of this analysis become the input data for the next processing step.

[0456] Step 4:

[0457] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., IBM Watson® Tone Analyzer) is used to evaluate the user's stress level. Past user response data and temporary emotion data are used as input data.

[0458] Step 5:

[0459] The server optimizes the schedule based on analysis and sentiment recognition. AI models (e.g., GPT-4®) are used to make adjustments such as postponing or easing important tasks and inserting relaxation time. The data generated during this optimization process is output as optimized schedule data.

[0460] Step 6:

[0461] The optimized schedule is sent to the device. The final generated optimized schedule data is sent to the device as an HTTP response.

[0462] Step 7:

[0463] Users can review and modify their optimized schedules. Users can check their schedules on their devices and make additional changes or modifications as needed.

[0464] ---

[0465] Email Processing

[0466] Step 1:

[0467] The user receives an email on their device. The user receives a new email through an email client (e.g., Outlook or Gmail).

[0468] Step 2:

[0469] The device sends the received email data to the server. The received email data is sent to the server via an HTTP request.

[0470] Step 3:

[0471] The server analyzes the content of the email. Using a natural language processing engine (e.g., NLTK or spaCy), it analyzes the email content and evaluates the importance of the body and attachments. This result is stored on the server and used as input data for the next processing step.

[0472] Step 4:

[0473] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., TextBlob) is used to determine the user's emotional state (e.g., fatigue level, stress). The user's past behavior and emotional data are used as input data.

[0474] Step 5:

[0475] The server determines the importance and whether an email is spam. A spam detection algorithm (e.g., Naive Bayes) is used to determine importance and filter out spam. The determination result is used as input data for the next processing step.

[0476] Step 6:

[0477] AI generates and adjusts email summaries and response drafts based on sentiment. Using an AI model (e.g., GPT-4), it generates summary texts and response drafts, and adjusts the wording to match the user's sentiment.

[0478] Step 7:

[0479] The summary and proposed reply are sent to the terminal. The final generated summary and proposed reply are sent to the terminal as an HTTP response.

[0480] Step 8:

[0481] The user reviews the summary and draft reply, makes revisions as needed, and sends it. The user reviews the summary and draft reply on their device, makes revisions as needed, and sends the final email.

[0482] ---

[0483] Task management

[0484] Step 1:

[0485] The user enters tasks from the terminal. The user enters tasks such as "report creation" or "data analysis" into the terminal.

[0486] Step 2:

[0487] The terminal sends the entered task data to the server. The entered task data is sent to the server using an HTTP request.

[0488] Step 3:

[0489] The server analyzes the task data. Using a natural language processing engine (e.g., SpaCy), it analyzes the task content, importance, dependencies, etc. The analysis results become input data for the next processing step.

[0490] Step 4:

[0491] The emotion engine recognizes the user's emotions. It uses an emotion analysis library (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Past user response data and temporary emotion data are used as input data.

[0492] Step 5:

[0493] The server determines priorities and dependencies. Based on the analysis results and sentiment recognition results, it determines the priority and dependencies of tasks. This determination becomes the input data for the next processing step.

[0494] Step 6:

[0495] The AI ​​generates and adjusts the optimal task order and timeline based on emotions. Using an AI model (e.g., GPT-4), it generates the optimal task order and timeline and adjusts it to match the user's emotions.

[0496] Step 7:

[0497] The generated task schedule is sent to the terminal. The final task schedule data is sent to the terminal as an HTTP response.

[0498] Step 8:

[0499] The user reviews and executes the task schedule. The user reviews the task schedule generated on their device, makes any necessary modifications, and then proceeds with execution.

[0500] ---

[0501] Information gathering

[0502] Step 1:

[0503] The user enters a request for information gathering from their device. For example, the user enters a request to find out about "recent market trends" into their device.

[0504] Step 2:

[0505] The device sends an information collection request to the server. The information collection request data is sent to the server using an HTTP request.

[0506] Step 3:

[0507] The server receives and analyzes the request. Using a natural language processing engine, it analyzes the request content and identifies the data necessary for information gathering.

[0508] Step 4:

[0509] The emotion engine recognizes the user's emotions. It uses an emotion analysis library to recognize the user's emotional state. Input data includes information related to the user's stress and fatigue levels.

[0510] Step 5:

[0511] The server collects information. It uses web scraping techniques (e.g., Beautiful Soup) to collect the necessary information from the specified data source.

[0512] Step 6:

[0513] The AI ​​summarizes and reframes the collected information based on sentiment. Using an AI model (e.g., GPT-4), it summarizes the collected information and presents it in a format that aligns with the user's emotions.

[0514] Step 7:

[0515] The generated report is sent to the terminal. The final report data is sent to the terminal as an HTTP response.

[0516] Step 8:

[0517] The user reviews the report. The user reviews the report generated on their device and provides feedback as needed.

[0518] ---

[0519] Support for reverse planning to achieve self-realization

[0520] Step 1:

[0521] The user enters their long-term goal from their device. For example, the user might enter the goal "I will become independent and start my own business in 10 years" into their device.

[0522] Step 2:

[0523] The device sends long-term goal data to the server. The long-term goal data is sent to the server using an HTTP request.

[0524] Step 3:

[0525] The server receives and analyzes the data. A natural language processing engine is used to analyze the content of the input long-term goals. The analysis results obtained here are used as input data for the next processing step.

[0526] Step 4:

[0527] The emotion engine recognizes the user's emotions. An emotion analysis library is used to recognize the user's emotional state. Here, the user's stress level and motivation are used as input data.

[0528] Step 5:

[0529] The AI ​​works backward to set annual targets. Using an AI model (e.g., GPT-4), it sets the annual targets necessary to achieve the long-term goal. This backward calculation result is used as input data for the next processing step.

[0530] Step 6:

[0531] The AI ​​breaks down annual goals into monthly and weekly tasks. These generated tasks are then converted into monthly and weekly goals based on the annual plan.

[0532] Step 7:

[0533] The server optimizes generated task schedules based on emotions. It considers the user's emotional state and optimizes the task schedule accordingly. For example, it reduces the workload during periods of high stress.

[0534] Step 8:

[0535] A task schedule optimized for the device is sent. The optimized task schedule is sent to the device as an HTTP response.

[0536] Step 9:

[0537] The user reviews and executes the task schedule. The user reviews the generated task schedule, makes any necessary corrections or adjustments, and then proceeds with execution.

[0538] ---

[0539] This allows users to efficiently manage schedules, tasks, and emails, and gather information. Furthermore, by utilizing an emotion engine, appropriate adjustments are made based on the user's emotional state, resulting in increased productivity and reduced stress.

[0540] (Application Example 2)

[0541] 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".

[0542] Traditional food delivery systems have a problem in that they do not consider the user's emotional state when suggesting dishes or restaurants, thus failing to reduce user stress and improve satisfaction. Furthermore, the ordering process lacks consideration for reducing the user's psychological burden, resulting in an unoptimized user experience. To solve these problems, a system is needed that provides optimal suggestions based on the user's emotional state.

[0543] 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. In this invention, the server includes means for analyzing user input data and optimally adjusting schedules and suggestions using a generative AI and an emotion engine, means for making suggestions and optimizations regarding food delivery based on the user's emotional state, and means for transmitting the suggested and optimized data to a terminal for the user to confirm and modify. This enables optimal food delivery suggestions based on the user's emotional state and an ordering process that reduces psychological burden.

[0544] A "schedule" is a planner that allows users to manage their daily activities and appointments hour by hour.

[0545] A "terminal" refers to an electronic device that a user can operate and use to input and receive information.

[0546] A "server" is a central computer system that processes and manages data over a network.

[0547] "Analysis" is the process of meticulously examining data to find specific information or patterns within it.

[0548] "Generative AI" refers to artificial intelligence that automatically generates new data and information based on user input.

[0549] An "emotion engine" is a technology that recognizes the user's emotional state and provides appropriate responses and suggestions based on those emotions.

[0550] "Optimization" is the process of adjusting to the most effective state or conditions for a specific purpose.

[0551] "Food delivery" is a service where users order food and have it delivered to a specified location.

[0552] "Email" refers to electronic messages sent and received via the internet.

[0553] A "task" is a specific task or activity that needs to be performed in order to achieve a particular goal.

[0554] A "summary" is a short, concise piece of text or content that captures the main points of a long piece of information.

[0555] A "suggested reply" is a proposed or suggested response to a received message.

[0556] This invention provides a food delivery system for realizing the described invention. This system consists of a terminal operated by the user and a server that centrally processes and manages data.

[0557] First, when a user enters their schedule from a device such as a smartphone, the device sends the user's input data to the server. The server analyzes the received schedule data and optimizes it using generative AI and an emotion engine. In particular, it recognizes the user's emotional state and fine-tunes the schedule based on that. For example, if the user is feeling stressed, adjustments such as adding relaxation time are made according to that emotional state. The optimized schedule is sent back to the device, where the user can review and modify it.

[0558] Next, if the user's emotional state is affected, the system optimizes the food delivery suggestions. Based on the user's emotional state, for example, states such as "fatigue" or "stress" are recognized, and appropriate meals (e.g., healthy dishes or refreshing desserts) are suggested. These suggestions are optimized for easy selection by the user and are displayed on the device.

[0559] When a user inputs a specific emotion or state, the server uses an emotion engine to analyze that state and suggest the most suitable dishes or restaurants. For example, if a user inputs "I'm tired today," the server uses the emotion engine to recognize "fatigue" and suggests healthy dishes. This process reduces the user's psychological burden and provides an optimal service experience.

[0560] The system requires hardware such as smartphones, and software such as the EmotionEngine and FoodDeliveryAPI. Through these components, user emotion recognition, data analysis, suggestion generation, and the ordering process are integrated.

[0561] For example, if a user enters "I'm tired today," the emotion engine recognizes "fatigue," and the food delivery API suggests three healthy dishes. For instance, "green salad," "chicken soup," and "fruit bowl" might be displayed. The user then reviews and modifies their selections, and the order is finalized.

[0562] Examples of prompt statements for input to a generative AI model include the following:

[0563] "I'm feeling stressed and tired right now. Could you recommend some dishes?"

[0564] In this way, it becomes possible to provide optimal food delivery suggestions based on the user's emotional state.

[0565] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0566] Step 1:

[0567] Users input their schedules and emotional states from a smartphone or other device. Specifically, users input their emotional state in text format, such as "I'm tired today." This data is temporarily stored on the device.

[0568] Step 2:

[0569] The device sends user input data (schedule and emotional state) to the server. This transmission process involves sending data to the server via an API. The server receives the entered emotional state data.

[0570] Step 3:

[0571] The server analyzes the received data. Here, the EmotionEngine is used to analyze emotions from text data. For example, it extracts the emotional state "fatigue" from the input "tired." The analysis results are stored on the server.

[0572] Step 4:

[0573] The server uses generative AI to suggest the most suitable dishes and restaurants based on the user's emotional state. It calls a food delivery API to retrieve data on dishes appropriate for that emotional state. For example, for the emotion of "fatigue," it might suggest healthy dishes such as "green salad," "chicken soup," and "fruit bowl." This information is temporarily stored on the server.

[0574] Step 5:

[0575] The server sends suggestion data to the device. The API then forwards dish suggestions, tailored to the user's emotional state, to the device. The device displays the received data and shows the suggestions to the user.

[0576] Step 6:

[0577] The user reviews, selects, and modifies the suggested dishes. From the dish options displayed on the device, the user selects their desired dish. The information about the user's selected dish is temporarily saved on the device.

[0578] Step 7:

[0579] The device sends user selection data to the server. Information about the selected dish is sent to the server via API. The transmitted data is received by the server.

[0580] Step 8:

[0581] The server generates the final order and sends it to the food delivery service. Order information is generated and sent to the delivery service via the food delivery API along with the user's delivery address information. A final order confirmation message is sent to the user's device and displayed on it.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] [Second Embodiment]

[0586] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0587] 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.

[0588] 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).

[0589] 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.

[0590] 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.

[0591] 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).

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering. It also provides support for achieving long-term goals for self-realization.

[0599] Schedule management

[0600] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, optimizing it by eliminating duplicates and unnecessary information. The optimized schedule is sent to the device, where the user can review and modify it.

[0601] Specific example:

[0602] When a user registers their schedule for the following week, the AI ​​detects any overlapping meeting times and suggests moving them to a different, more suitable time.

[0603] Email Processing

[0604] The user receives an email on their device. The device sends the received email data to the server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The summary and suggested reply are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[0605] Specific example:

[0606] When a user receives a large volume of emails, the AI ​​prioritizes important emails and provides templates to make replying easier.

[0607] Task management

[0608] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, and sends the generated task schedule to the device. The user confirms and executes the tasks.

[0609] Specific example:

[0610] When a user enters tasks for a new project, the AI ​​considers the dependencies between tasks and suggests a natural order and estimated time for each.

[0611] Information gathering

[0612] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the AI ​​collects information from the specified data source. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report.

[0613] Specific example:

[0614] When a user submits a market research request, the AI ​​gathers the latest statistical data and trending articles and provides a clearly summarized report.

[0615] Support for reverse planning to achieve self-realization

[0616] The user inputs their long-term goal from their device. The server receives the long-term goal, and the AI ​​works backward to set annual goals. Furthermore, the annual goals are broken down into monthly and weekly tasks. The generated task schedule is sent to the device, which the user reviews and executes.

[0617] Specific example:

[0618] If a user sets a goal like "I will become independent and start my own business in 10 years," the AI ​​will work backward to determine the necessary steps, such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[0619] These features enable users to streamline their daily tasks and work towards achieving long-term goals. This system leverages the power of generative AI to effectively support user productivity and self-realization.

[0620] The following describes the processing flow.

[0621] Schedule management

[0622] Step 1:

[0623] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[0624] Step 2:

[0625] The device sends user input data to the server. For example, it might send data in the format "2023-10-01: Meeting, 2023-10-02: Client visit".

[0626] Step 3:

[0627] The server analyzes the schedule data it receives. It checks the format and content of the input data to ensure there are no errors or missing information.

[0628] Step 4:

[0629] The server uses AI to optimize schedule data. Specifically, it adjusts overlapping appointments, prioritizes them based on importance, and reduces unnecessary travel time.

[0630] Step 5:

[0631] The server sends an optimized schedule to the terminal. It is then sent again in JSON format, etc.

[0632] Step 6:

[0633] The device notifies the user of the optimized schedule it has received. The user then uses this information to review and modify their schedule.

[0634] Email Processing

[0635] Step 1:

[0636] The user receives an email on their device. A notification is sent indicating that a new email is available.

[0637] Step 2:

[0638] The device sends received email data to the server. This data includes information such as the email content and sender.

[0639] Step 3:

[0640] The server analyzes the emails it receives. AI determines the importance of the emails and filters them to determine if they are spam.

[0641] Step 4:

[0642] The AI ​​on the server generates email summaries and suggested replies. For example, in response to an email requesting meeting confirmation, it can generate a suggested reply such as "I can attend."

[0643] Step 5:

[0644] The server sends a summary and a draft reply to the terminal. Data containing the summary and draft reply is sent.

[0645] Step 6:

[0646] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[0647] Task management

[0648] Step 1:

[0649] The user enters the task from their device. They fill in the project name and specific task details.

[0650] Step 2:

[0651] The terminal sends the entered task data to the server. The data is sent in JSON format, among others.

[0652] Step 3:

[0653] The server analyzes the received task data. The AI ​​determines the task priorities and dependencies.

[0654] Step 4:

[0655] The AI ​​on the server generates the optimal task order and timeline. For example, it determines the task order based on the project's progress.

[0656] Step 5:

[0657] The server sends the generated task schedule to the terminal. Data containing the detailed schedule is sent.

[0658] Step 6:

[0659] The device notifies the user of the task schedule it has received. The user reviews the schedule and proceeds with execution.

[0660] Information gathering

[0661] Step 1:

[0662] The user enters an information gathering request from their device. They enter the topic or keywords they want to investigate.

[0663] Step 2:

[0664] The device sends an information collection request to the server.

[0665] Step 3:

[0666] The server receives the request, and the AI ​​collects information from specific data sources. It gathers necessary information from sources such as news websites and databases.

[0667] Step 4:

[0668] The AI ​​on the server summarizes the collected information and generates a report. It extracts the most important parts from the collected data.

[0669] Step 5:

[0670] The server sends the generated report to the terminal. Data containing a summary report is sent.

[0671] Step 6:

[0672] The device notifies the user of the reports it has received. The user reviews the reports and takes the necessary actions.

[0673] Support for reverse planning to achieve self-realization

[0674] Step 1:

[0675] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[0676] Step 2:

[0677] The device sends long-term goal data to the server.

[0678] Step 3:

[0679] The server receives the long-term goal, and the AI ​​works backward to set annual goals. Specific goals are defined for each year.

[0680] Step 4:

[0681] The AI ​​on the server breaks down the annual goals into monthly and weekly units and converts them into tasks.

[0682] Step 5:

[0683] The server sends the generated task schedule to the terminal. Detailed schedule data is sent.

[0684] Step 6:

[0685] The device notifies the user of the task schedule it has received. The user reviews the information and takes the necessary actions.

[0686] (Example 1)

[0687] 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."

[0688] We provide a system that efficiently supports users' daily work and self-realization by utilizing generative AI. Conventional systems lacked sufficient integration of schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization, making it difficult to improve user productivity. Furthermore, they lacked features to eliminate duplication and waste and optimize processes, resulting in cumbersome manual management.

[0689] 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.

[0690] In this invention, the server includes means for analyzing received data, means for optimizing the analyzed data, and means for transmitting the generated data to a terminal. This enables schedule optimization, email processing with importance assessment and spam filtering, task management considering priorities and dependencies, information gathering that collects and summarizes information from specific data sources, and self-actualization support that converts long-term goals into concrete tasks by working backward.

[0691] A "schedule" refers to a plan based on time and date, including the user's appointments.

[0692] "Terminal" refers to electronic devices used by users, such as smartphones and computers.

[0693] A "server" refers to a computer system that receives data sent by users and performs analysis and processing on it.

[0694] "Data analysis" refers to the process of processing received data and extracting meaningful information.

[0695] "Optimization" refers to adjustments made to eliminate redundancy and waste, resulting in an efficient state.

[0696] "Email" refers to electronic mail, including digital messages sent and received over the internet.

[0697] A "task" refers to any work or action that needs to be performed in order to achieve a specific goal.

[0698] "Information gathering" refers to the process of collecting data and knowledge necessary for a specific purpose.

[0699] "Long-term goals" refer to major objectives that are planned to be achieved over a long period of time.

[0700] A "generative AI model" refers to a model that uses artificial intelligence technology to generate output based on user input data and requests.

[0701] A "prompt statement" refers to an instruction given as input to an AI model.

[0702] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides five functions: schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization. The details are described below.

[0703] Schedule management

[0704] The user enters their schedule from their device. The device sends the entered schedule data to the server. The server uses a "generative AI model" to analyze the received schedule data, optimizing it by eliminating duplication and waste. The optimized schedule is sent to the device, which the user can then review and modify. For example, if a user registers their schedule for the following week, the "generative AI model" might detect a meeting time conflict and suggest moving it to a different, more appropriate time.

[0705] Example prompt message: "I have entered the schedule for next week. Please check for duplicates and inefficiencies and optimize it."

[0706] Email Processing

[0707] The user receives an email on their device. The device sends the received email data to a server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The generated summary and reply are sent to the device, where the user reviews and modifies them as needed before sending. For example, when a user receives a large number of emails, the AI ​​model on the server prioritizes important emails and provides templates to facilitate replies.

[0708] Example prompt: "Summarize the received email and generate a draft reply."

[0709] Task management

[0710] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. A generative AI model generates the optimal task order and timeline, and sends the generated task schedule to the device. The user reviews and executes the tasks. For example, when a user enters tasks for a new project, the AI ​​model considers the task dependencies and suggests a natural order and estimated time for each task.

[0711] Example prompt: "I have entered the tasks for this project. Please generate the optimal task order and schedule, taking dependencies and priorities into consideration."

[0712] Information gathering

[0713] The user enters a request for information gathering from their device. The device sends the information gathering request to the server. The server receives the request, and the AI ​​collects information from specific data sources. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report. For example, if a user enters a request for market research, the AI ​​model collects the latest statistical data and trending articles and provides a clearly summarized report.

[0714] Example prompt: "Collect data and trend articles for market research and generate a summarized report."

[0715] Support for reverse planning to achieve self-realization

[0716] The user enters a long-term goal from their device. The device sends the entered long-term goal to the server. The server receives the long-term goal and uses a generating AI model to set annual goals. Furthermore, it breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is sent to the device for the user to review and execute. For example, if the user sets "I will become independent and start my own business in 10 years," the AI ​​model will work backward to determine the necessary steps such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[0717] Example prompt: "Please create a schedule outlining the steps and plan necessary to start your own business in 10 years."

[0718] This system leverages the power of generative AI to support users in efficiently performing their tasks and achieving long-term goals. HTTP POST is used for communication between the server and the terminal, and data is exchanged in JSON format. Generative AI models play a crucial role in each function, analyzing user input data and providing optimal suggestions to improve productivity.

[0719] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0720] Schedule management

[0721] Step 1:

[0722] The user enters their schedule using a terminal. The entered data is generated in JSON format via the keyboard or touchscreen.

[0723] Step 2:

[0724] The terminal sends the entered schedule data to the server. Specifically, it sends the schedule data in JSON format using an HTTP POST request.

[0725] Step 3:

[0726] The server analyzes the received schedule data. A generative AI model is used for the analysis, performing pattern recognition to eliminate duplication and waste from the data.

[0727] Step 4:

[0728] The server generates an optimized schedule based on the analyzed data. The generated schedule is also converted to JSON format.

[0729] Step 5:

[0730] The server sends an optimized schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0731] Step 6:

[0732] Users can view the optimized schedule on their device and make adjustments as needed. The adjustment data is also saved in JSON format.

[0733] Email Processing

[0734] Step 1:

[0735] The user receives emails using their device. Emails are received via a standard email application.

[0736] Step 2:

[0737] The device sends the received email data to the server. The transmission format is JSON, and it uses an HTTP POST request.

[0738] Step 3:

[0739] The server analyzes the content of the email. A generative AI model is used for the analysis, including determining importance and filtering spam.

[0740] Step 4:

[0741] The server generates an email summary and a draft reply. The generated summary and draft reply are converted into JSON format.

[0742] Step 5:

[0743] The server sends the generated summary and proposed reply to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0744] Step 6:

[0745] The user reviews the summary and proposed reply on their device and makes revisions as needed. The revised reply is then sent via email.

[0746] Task management

[0747] Step 1:

[0748] The user enters a new task using a terminal. The entered data is generated in JSON format.

[0749] Step 2:

[0750] The terminal sends the entered task data to the server. Specifically, it sends the task data in JSON format using an HTTP POST request.

[0751] Step 3:

[0752] The server analyzes the received task data. A generative AI model is used for the analysis to determine task priorities and dependencies.

[0753] Step 4:

[0754] The server generates the optimal task order and timeline based on the analysis results. The generated task schedule is converted to JSON format.

[0755] Step 5:

[0756] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0757] Step 6:

[0758] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[0759] Information gathering

[0760] Step 1:

[0761] The user enters a data collection request using their device. The entered data is generated in JSON format.

[0762] Step 2:

[0763] The device sends an information collection request to the server. The transmission format is JSON, and it uses an HTTP POST request.

[0764] Step 3:

[0765] The server receives a request and uses a generative AI model to collect information from a specific data source. The collected information is obtained from databases or the internet.

[0766] Step 4:

[0767] The server summarizes the collected information and generates a report. The generated report is converted to JSON format.

[0768] Step 5:

[0769] The server sends the generated report to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0770] Step 6:

[0771] The user views the report on their device. The data in the report is modified as needed.

[0772] Support for reverse planning to achieve self-realization

[0773] Step 1:

[0774] The user enters their long-term goals using a device. The entered data is generated in JSON format.

[0775] Step 2:

[0776] The terminal sends the entered long-term goals to the server. The transmission format is JSON, and it uses an HTTP POST request.

[0777] Step 3:

[0778] The server receives the long-term goals and uses a generative AI model to set annual goals. The set goals are then converted into JSON format.

[0779] Step 4:

[0780] The server breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is then converted into JSON format.

[0781] Step 5:

[0782] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[0783] Step 6:

[0784] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[0785] This allows the system to perform specific data processing and calculations for each function, providing optimized data and thereby improving user productivity.

[0786] (Application Example 1)

[0787] 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 glasses 214 will be referred to as the "terminal."

[0788] In traditional virtual store operations, managing staff schedules, handling customer inquiries via email, and managing tasks were often done manually, resulting in inefficiencies. Furthermore, there was a lack of tools to streamline operations, such as optimizing schedules, promptly addressing important emails, and prioritizing tasks. As a result, operational efficiency declined, placing a burden on store management.

[0789] 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.

[0790] In this invention, the server includes means for the user to input a schedule, means for the terminal to transmit the user's input data to the server, means for the server to analyze the received schedule data, means for optimizing the analyzed schedule data, means for transmitting the optimized schedule to the terminal, means for the user to confirm and modify the optimized schedule, means for optimizing staff schedules in a virtual store, and means for generating prompt statements when optimizing the schedule using a generative AI model. This enables efficient management of staff schedules in a virtual store.

[0791] A "user" is an individual or legal entity that uses the system or terminals to operate and manage a virtual store.

[0792] A "schedule" is a plan of the date, time, and content of events and tasks that the user enters.

[0793] A "device" refers to an input and display device such as a smartphone, tablet, or personal computer used by a user.

[0794] A "server" is a computer system that receives, analyzes, and optimizes data sent by users, and then returns the results to the terminal.

[0795] "Schedule data" refers to information about the schedule entered by the user.

[0796] "Analysis" refers to the process of analyzing schedule data and email data received by a server to extract and evaluate appropriate information.

[0797] "Optimization" refers to the efficient and effective organization and adjustment of schedules and task data.

[0798] A "virtual store" is an online store that provides goods and services via the internet.

[0799] "Staff" refers to the personnel who support the operation of the virtual store.

[0800] A "generative AI model" refers to an artificial intelligence algorithm trained to perform a specific task.

[0801] A "prompt statement" is an instruction given to a generative AI model, containing instructions for obtaining a specific result.

[0802] "Email" refers to messages sent and received electronically, and is used for customer inquiries and internal company communications.

[0803] A "task" refers to the work or tasks that a user is supposed to perform.

[0804] "Priority" refers to the order in which tasks and schedules are arranged based on their importance and urgency.

[0805] "Dependency" refers to a relationship where one task or schedule depends on another task or event.

[0806] A "summary" refers to a concise compilation of key information.

[0807] A "suggested reply" is a proposed response to a message, such as an email.

[0808] This invention is a system that utilizes a generative AI model to streamline daily operations in virtual stores and improve user productivity. This system primarily provides three main functions: schedule management, email processing, and task management. The implementation methods for each function are described below.

[0809] Schedule management

[0810] The user enters the staff schedule for the virtual store using a terminal. This schedule data is sent from the terminal to the server. The server analyzes the received schedule data, eliminating duplication and inefficiencies to optimize it. The optimized schedule is sent back to the terminal for the user to review and modify. At this time, a generation AI model is used to generate prompts for schedule optimization, and the AI ​​is instructed to perform the optimization work.

[0811] Email Processing

[0812] Emails received by the user are received on the device, and the data is sent to the server. The server analyzes the content of the emails, determines their importance, and performs spam filtering. Based on the analyzed content of the emails, AI generates summaries and suggested replies. The generated summaries and suggested replies are sent to the device, where the user reviews and modifies them, and sends them as needed.

[0813] Task management

[0814] When a user enters a new task from their device, the task data is sent to the server. The server analyzes the task data and uses a generative AI model to determine priorities and dependencies, generating an optimal task sequence and timeline. This enables efficient task management. The generated task schedule is sent to the device, where the user can review and execute it.

[0815] Hardware and software used

[0816] Hardware: Servers (e.g., AWS EC2 instances), user devices (smartphones, tablets, PCs)

[0817] Software: Django framework (server-side program), generative AI model (e.g., OpenAI GPT-3)

[0818] Examples of specific cases and prompt statements

[0819] Specific example

[0820] For example, consider a scenario where a store manager inputs staff shift schedules. If different shifts overlap, the server uses a generated AI model to optimize the schedule and suggest the best shift arrangement. Furthermore, when a large volume of customer inquiry emails arrive, the AI ​​generates summaries and suggested replies to support a quick response.

[0821] Example of a prompt

[0822] For schedule optimization: "Optimize this schedule: {'Mon': ['StaffA', 'StaffB'], 'Tue': ['StaffC', 'StaffD'], 'Wed': ['StaffA', 'StaffE']}"

[0823] For email processing: "Summarize and create a reply draft for this email: 'Dear Store, We have an urgent issue regarding our recent order...'"

[0824] Based on the above, the system of the present invention provides a concrete means to streamline daily operations in virtual store management and reduce the workload of users.

[0825] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0826] Step 1:

[0827] The user enters their schedule into the terminal. The terminal receives the entered schedule data and sends it to the server. The input data includes the date and time, event details, and information about the staff in charge. The output is the schedule data sent to the server.

[0828] Step 2:

[0829] The server analyzes the received schedule data. The analysis verifies data integrity and checks for duplication and unnecessary information. The input is the schedule data, and the output is the analysis results.

[0830] Step 3:

[0831] The server optimizes the analyzed schedule data. A generative AI model is used to generate prompts for optimization. These prompts are input to the AI ​​model to obtain the optimal schedule. The input consists of the analysis results and prompts, and the output is the optimized schedule data.

[0832] Step 4:

[0833] The server sends optimized schedule data to the terminal. The terminal displays the received data and prompts the user for confirmation and correction. The input is the optimized schedule data, and the output is the schedule displayed on the terminal.

[0834] Step 5:

[0835] The system reviews the schedule received by the user and makes corrections as needed. The corrected schedule data is then sent back to the server. The input is the user's corrected data, and the output is the corrected schedule data.

[0836] Step 6:

[0837] The user receives an email on their device. The device then sends the received email data to the server. The input is the email data, and the output is the email data sent to the server.

[0838] Step 7:

[0839] The server analyzes received email data, performs importance assessment, and filters out spam. Based on the analysis results, an AI model is used to generate summaries and suggested replies. The input is email data, and the output is summaries and suggested replies.

[0840] Step 8:

[0841] The server sends the generated summary and draft reply to the terminal. The terminal displays it to the user, who then reviews and makes corrections. The input is the summary and draft reply, and the output is the data displayed to the user.

[0842] Step 9:

[0843] The user reviews and corrects the summary and draft reply, then resends them to the server for final delivery. The input is the corrected summary and draft reply, and the output is the sent email.

[0844] Step 10:

[0845] The user enters a new task into the terminal. The terminal sends the entered task data to the server. The input is the task data, and the output is the task data sent to the server.

[0846] Step 11:

[0847] The server analyzes the received task data to determine priorities and dependencies. Based on the analysis results, a generative AI model is used to generate the optimal task order and timeline. The input is task data, and the output is the optimized task order and timeline.

[0848] Step 12:

[0849] The server sends the generated task schedule to the terminal. The terminal displays it to the user, who then reviews and executes the task schedule. The input is the optimized task schedule, and the output is the data displayed to the user.

[0850] Through the steps described above, the present invention provides concrete means for streamlining users' daily operations and supporting virtual store management.

[0851] 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.

[0852] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[0853] Schedule management

[0854] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotions and optimizes the schedule based on those emotions. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the device, and the user can review and modify it.

[0855] Specific example:

[0856] When a user schedules a meeting or client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[0857] Email Processing

[0858] The user receives an email from their device. The device sends the received email data to the server. The server analyzes the email content, and the sentiment engine recognizes the user's emotions to determine importance and perform spam filtering. The AI ​​also generates an email summary and suggested replies, adjusting them based on the user's emotions. For example, if the user is fatigued, a simple reply suggestion might be made. The summary and suggested replies are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[0859] Specific example:

[0860] When a user receives an important email while feeling fatigued, the emotion engine generates a simple and quick response suggestion to reduce the user's burden.

[0861] Task management

[0862] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[0863] Specific example:

[0864] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[0865] Information gathering

[0866] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[0867] Specific example:

[0868] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[0869] Support for reverse planning to achieve self-realization

[0870] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[0871] Specific example:

[0872] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[0873] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[0874] The following describes the processing flow.

[0875] Schedule management processing steps

[0876] Step 1:

[0877] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[0878] Step 2:

[0879] The terminal sends user input data to the server. The data is often sent in formats such as JSON or XML.

[0880] Step 3:

[0881] The server analyzes the received schedule data. It checks the data format and performs checks for any discrepancies if necessary.

[0882] Step 4:

[0883] The server uses an emotion engine to recognize the user's current emotions. Specifically, it refers to emotion data previously recorded by the user or real-time emotion input.

[0884] Step 5:

[0885] The server optimizes the schedule data. For example, if a user is feeling stressed, it might add breaks to slow down the pace or adjust the order of important tasks.

[0886] Step 6:

[0887] The server sends an optimized schedule to the terminal.

[0888] Step 7:

[0889] The device notifies the user of an optimized schedule. The user can then review and modify the schedule based on this information.

[0890] Email Processing Steps

[0891] Step 1:

[0892] The user receives an email from their device. A notification appears as a pop-up or alert.

[0893] Step 2:

[0894] The device sends received email data to the server. This data includes information such as the email body, sender, and date / time.

[0895] Step 3:

[0896] The server analyzes the received emails, checking their content and determining their importance or whether they are spam.

[0897] Step 4:

[0898] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's fatigue level and stress level.

[0899] Step 5:

[0900] The server generates email summaries and suggested replies. For example, if the user is tired, it will generate a concise suggested reply.

[0901] Step 6:

[0902] The server sends a summary and a draft reply to the terminal.

[0903] Step 7:

[0904] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[0905] Task management processing steps

[0906] Step 1:

[0907] The user enters the task from their device. They fill in the project name and specific task details.

[0908] Step 2:

[0909] The terminal sends the entered task data to the server. The data format used is typically JSON or XML.

[0910] Step 3:

[0911] The server analyzes the received task data. It checks the data format and determines priorities and dependencies.

[0912] Step 4:

[0913] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's energy level and mood.

[0914] Step 5:

[0915] The server generates the optimal order and timeline for tasks, making adjustments based on emotions, such as scheduling important tasks during times of high concentration.

[0916] Step 6:

[0917] The server sends the generated task schedule to the terminal.

[0918] Step 7:

[0919] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[0920] Information gathering processing steps

[0921] Step 1:

[0922] The user enters an information gathering request from their device. They enter the topic, keywords, and purpose they want to investigate.

[0923] Step 2:

[0924] The device sends an information collection request to the server.

[0925] Step 3:

[0926] The server receives the request and uses an emotion engine to recognize the user's emotions.

[0927] Step 4:

[0928] The server collects information from specific data sources. It retrieves necessary information from sources such as news websites and academic journal databases.

[0929] Step 5:

[0930] The server summarizes the collected information and adjusts the report based on the user's emotions. For example, if the user is easily fatigued, a concise summary is generated.

[0931] Step 6:

[0932] The server sends the generated report to the terminal.

[0933] Step 7:

[0934] The device notifies the user of the report it has received. The user reviews the report and takes the necessary action.

[0935] Processing steps for supporting reverse engineering for self-realization

[0936] Step 1:

[0937] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[0938] Step 2:

[0939] The device sends long-term goal data to the server.

[0940] Step 3:

[0941] The server receives the long-term goals and uses an emotion engine to recognize the user's emotions.

[0942] Step 4:

[0943] The server uses AI to work backward and set annual goals. It defines specific steps and milestones.

[0944] Step 5:

[0945] The server breaks down annual goals into monthly and weekly units and converts them into tasks. It also makes adjustments based on emotions.

[0946] Step 6:

[0947] The server sends the generated task schedule to the terminal.

[0948] Step 7:

[0949] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[0950] (Example 2)

[0951] 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".

[0952] Traditional scheduling, email processing, task management, and information gathering systems often fail to consider user emotions, leading to stress and decreased work efficiency. This frequently resulted in users being unable to achieve their full productivity. To address this problem, dynamic adjustments based on user emotional states are required.

[0953] 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.

[0954] In this invention, the server includes means for an emotion engine to recognize the user's emotions, means for optimizing the schedule based on analysis and emotion recognition, and means for adjusting the generated summaries and response suggestions based on the emotions. This enables improved user productivity and reduced stress by making optimal adjustments according to the user's emotional state.

[0955] A "user" refers to a person who uses this system to manage their schedule, process emails, manage tasks, and gather information.

[0956] "Device" refers to electronic devices used by users, such as personal computers, smartphones, and tablets.

[0957] A "server" refers to a computer system that receives data sent from a terminal and performs analysis and optimization.

[0958] An "emotion engine" refers to software or hardware that recognizes a user's emotions and optimizes data based on those recognition results.

[0959] "Schedule data" refers to information about appointments and plans entered by the user.

[0960] "Analysis" refers to the process by which a server processes received data to understand and interpret its content, importance, dependencies, and other relevant information.

[0961] "Optimization" refers to adjusting schedules, task sequences, email summaries, and response drafts more effectively and efficiently based on analyzed data and user sentiment recognition results.

[0962] "Email data" refers to the content of emails received by a user and any accompanying information.

[0963] A "summary" refers to information that has been extracted and concisely compiled from the most important parts of an email or other information gathering results.

[0964] A "draft reply" refers to a suggested text that will be generated as a response to an email.

[0965] "Task data" refers to information about jobs and tasks entered by the user.

[0966] "Priority" refers to the criteria used to determine the order in which tasks and appointments entered by the user are executed, based on factors such as importance and urgency.

[0967] A "dependency" refers to a relationship where one task presupposes the completion of another task.

[0968] A "timeline" refers to a chronological arrangement of tasks and appointments that need to be completed within a specific period.

[0969] "Information gathering" refers to the process of obtaining necessary data from specific sources based on user instructions.

[0970] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[0971] Schedule management

[0972] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotions and optimizes the schedule based on those emotions. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the device, and the user can review and modify it.

[0973] Specific example:

[0974] When a user schedules a meeting or client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[0975] Example of a prompt:

[0976] "I'm entering this week's schedule. There are two important meetings and one client visit. Please adjust the schedule considering the stress level."

[0977] Email Processing

[0978] The user receives an email from their device. The device sends the received email data to the server. The server analyzes the email content, and the sentiment engine recognizes the user's emotions to determine importance and perform spam filtering. The AI ​​also generates an email summary and suggested replies, adjusting them based on the user's emotions. For example, if the user is fatigued, a simple reply suggestion might be made. The summary and suggested replies are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[0979] Specific example:

[0980] When a user receives an important email while feeling fatigued, the emotion engine generates a simple and quick response suggestion to reduce the user's burden.

[0981] Example of a prompt:

[0982] "Please provide a summary of the important email I received today and a draft reply. I am very tired right now, so a brief reply would be appreciated."

[0983] Task management

[0984] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[0985] Specific example:

[0986] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[0987] Example of a prompt:

[0988] "I'll enter today's tasks. These include meeting preparation, report writing, and presentation practice. Please create a schedule in the optimal order, taking my energy level into consideration."

[0989] Information gathering

[0990] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[0991] Specific example:

[0992] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[0993] Example of a prompt:

[0994] "Please gather information on recent market trends. I'm currently exhausted, so I'd prefer a concise summary report."

[0995] Support for reverse planning to achieve self-realization

[0996] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[0997] Specific example:

[0998] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[0999] Example of a prompt:

[1000] "My goal is to become independent and start my own business in 10 years. Please create annual, monthly, and weekly plans to achieve this goal, and adjust them to take my stress levels into consideration."

[1001] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[1002] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1003] Schedule management

[1004] Step 1:

[1005] The user enters their schedule from their device. For example, the user enters appointments for meetings or client visits into their device. This input data includes the date, time, and content of the appointment.

[1006] Step 2:

[1007] The terminal sends the entered schedule data to the server. The entered data is transferred to the server using an HTTP request. This operation constitutes data communication from the terminal to the server.

[1008] Step 3:

[1009] The server analyzes the received schedule data. A natural language processing engine (e.g., spaCy) is used to analyze the data's content. Here, the schedule's content, importance, and deadline are determined. The results of this analysis become the input data for the next processing step.

[1010] Step 4:

[1011] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., IBM Watson Tone Analyzer) is used to evaluate the user's stress level. Past user response data and temporary emotion data are used as input data.

[1012] Step 5:

[1013] The server optimizes the schedule based on analysis and sentiment recognition. An AI model (e.g., GPT-4) is used to make adjustments such as postponing or easing important tasks and inserting relaxation time. The data generated during this optimization process is output as optimized schedule data.

[1014] Step 6:

[1015] The optimized schedule is sent to the device. The final generated optimized schedule data is sent to the device as an HTTP response.

[1016] Step 7:

[1017] Users can review and modify their optimized schedules. Users can check their schedules on their devices and make additional changes or modifications as needed.

[1018] ---

[1019] Email Processing

[1020] Step 1:

[1021] The user receives an email on their device. The user receives a new email through an email client (e.g., Outlook or Gmail).

[1022] Step 2:

[1023] The device sends the received email data to the server. The received email data is sent to the server via an HTTP request.

[1024] Step 3:

[1025] The server analyzes the content of the email. Using a natural language processing engine (e.g., NLTK or spaCy), it analyzes the email content and evaluates the importance of the body and attachments. This result is stored on the server and used as input data for the next processing step.

[1026] Step 4:

[1027] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., TextBlob) is used to determine the user's emotional state (e.g., fatigue level, stress). The user's past behavior and emotional data are used as input data.

[1028] Step 5:

[1029] The server determines the importance and whether an email is spam. A spam detection algorithm (e.g., Naive Bayes) is used to determine importance and filter out spam. The determination result is used as input data for the next processing step.

[1030] Step 6:

[1031] AI generates and adjusts email summaries and response drafts based on sentiment. Using an AI model (e.g., GPT-4), it generates summary texts and response drafts, and adjusts the wording to match the user's sentiment.

[1032] Step 7:

[1033] The summary and proposed reply are sent to the terminal. The final generated summary and proposed reply are sent to the terminal as an HTTP response.

[1034] Step 8:

[1035] The user reviews the summary and draft reply, makes revisions as needed, and sends it. The user reviews the summary and draft reply on their device, makes revisions as needed, and sends the final email.

[1036] ---

[1037] Task management

[1038] Step 1:

[1039] The user enters tasks from the terminal. The user enters tasks such as "report creation" or "data analysis" into the terminal.

[1040] Step 2:

[1041] The terminal sends the entered task data to the server. The entered task data is sent to the server using an HTTP request.

[1042] Step 3:

[1043] The server analyzes the task data. Using a natural language processing engine (e.g., SpaCy), it analyzes the task content, importance, dependencies, etc. The analysis results become input data for the next processing step.

[1044] Step 4:

[1045] The emotion engine recognizes the user's emotions. It uses an emotion analysis library (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Past user response data and temporary emotion data are used as input data.

[1046] Step 5:

[1047] The server determines priorities and dependencies. Based on the analysis results and sentiment recognition results, it determines the priority and dependencies of tasks. This determination becomes the input data for the next processing step.

[1048] Step 6:

[1049] The AI ​​generates and adjusts the optimal task order and timeline based on emotions. Using an AI model (e.g., GPT-4), it generates the optimal task order and timeline and adjusts it to match the user's emotions.

[1050] Step 7:

[1051] The generated task schedule is sent to the terminal. The final task schedule data is sent to the terminal as an HTTP response.

[1052] Step 8:

[1053] The user reviews and executes the task schedule. The user reviews the task schedule generated on their device, makes any necessary modifications, and then proceeds with execution.

[1054] ---

[1055] Information gathering

[1056] Step 1:

[1057] The user enters a request for information gathering from their device. For example, the user enters a request to find out about "recent market trends" into their device.

[1058] Step 2:

[1059] The device sends an information collection request to the server. The information collection request data is sent to the server using an HTTP request.

[1060] Step 3:

[1061] The server receives and analyzes the request. Using a natural language processing engine, it analyzes the request content and identifies the data necessary for information gathering.

[1062] Step 4:

[1063] The emotion engine recognizes the user's emotions. It uses an emotion analysis library to recognize the user's emotional state. Input data includes information related to the user's stress and fatigue levels.

[1064] Step 5:

[1065] The server collects information. It uses web scraping techniques (e.g., Beautiful Soup) to collect the necessary information from the specified data source.

[1066] Step 6:

[1067] The AI ​​summarizes and reframes the collected information based on sentiment. Using an AI model (e.g., GPT-4), it summarizes the collected information and presents it in a format that aligns with the user's emotions.

[1068] Step 7:

[1069] The generated report is sent to the terminal. The final report data is sent to the terminal as an HTTP response.

[1070] Step 8:

[1071] The user reviews the report. The user reviews the report generated on their device and provides feedback as needed.

[1072] ---

[1073] Support for reverse planning to achieve self-realization

[1074] Step 1:

[1075] The user enters their long-term goal from their device. For example, the user might enter the goal "I will become independent and start my own business in 10 years" into their device.

[1076] Step 2:

[1077] The device sends long-term goal data to the server. The long-term goal data is sent to the server using an HTTP request.

[1078] Step 3:

[1079] The server receives and analyzes the data. A natural language processing engine is used to analyze the content of the input long-term goals. The analysis results obtained here are used as input data for the next processing step.

[1080] Step 4:

[1081] The emotion engine recognizes the user's emotions. An emotion analysis library is used to recognize the user's emotional state. Here, the user's stress level and motivation are used as input data.

[1082] Step 5:

[1083] The AI ​​works backward to set annual targets. Using an AI model (e.g., GPT-4), it sets the annual targets necessary to achieve the long-term goal. This backward calculation result is used as input data for the next processing step.

[1084] Step 6:

[1085] The AI ​​breaks down annual goals into monthly and weekly tasks. These generated tasks are then converted into monthly and weekly goals based on the annual plan.

[1086] Step 7:

[1087] The server optimizes generated task schedules based on emotions. It considers the user's emotional state and optimizes the task schedule accordingly. For example, it reduces the workload during periods of high stress.

[1088] Step 8:

[1089] A task schedule optimized for the device is sent. The optimized task schedule is sent to the device as an HTTP response.

[1090] Step 9:

[1091] The user reviews and executes the task schedule. The user reviews the generated task schedule, makes any necessary corrections or adjustments, and then proceeds with execution.

[1092] ---

[1093] This allows users to efficiently manage schedules, tasks, and emails, and gather information. Furthermore, by utilizing an emotion engine, appropriate adjustments are made based on the user's emotional state, resulting in increased productivity and reduced stress.

[1094] (Application Example 2)

[1095] 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."

[1096] Traditional food delivery systems have a problem in that they do not consider the user's emotional state when suggesting dishes or restaurants, thus failing to reduce user stress and improve satisfaction. Furthermore, the ordering process lacks consideration for reducing the user's psychological burden, resulting in an unoptimized user experience. To solve these problems, a system is needed that provides optimal suggestions based on the user's emotional state.

[1097] 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. In this invention, the server includes means for analyzing user input data and optimally adjusting schedules and suggestions using a generative AI and an emotion engine, means for making suggestions and optimizations regarding food delivery based on the user's emotional state, and means for transmitting the suggested and optimized data to a terminal for the user to confirm and modify. This enables optimal food delivery suggestions based on the user's emotional state and an ordering process that reduces psychological burden.

[1098] A "schedule" is a planner that allows users to manage their daily activities and appointments hour by hour.

[1099] A "terminal" refers to an electronic device that a user can operate and use to input and receive information.

[1100] A "server" is a central computer system that processes and manages data over a network.

[1101] "Analysis" is the process of meticulously examining data to find specific information or patterns within it.

[1102] "Generative AI" refers to artificial intelligence that automatically generates new data and information based on user input.

[1103] An "emotion engine" is a technology that recognizes the user's emotional state and provides appropriate responses and suggestions based on those emotions.

[1104] "Optimization" is the process of adjusting to the most effective state or conditions for a specific purpose.

[1105] "Food delivery" is a service where users order food and have it delivered to a specified location.

[1106] "Email" refers to electronic messages sent and received via the internet.

[1107] A "task" is a specific task or activity that needs to be performed in order to achieve a particular goal.

[1108] A "summary" is a short, concise piece of text or content that captures the main points of a long piece of information.

[1109] A "suggested reply" is a proposed or suggested response to a received message.

[1110] This invention provides a food delivery system for realizing the described invention. This system consists of a terminal operated by the user and a server that centrally processes and manages data.

[1111] First, when a user enters their schedule from a device such as a smartphone, the device sends the user's input data to the server. The server analyzes the received schedule data and optimizes it using generative AI and an emotion engine. In particular, it recognizes the user's emotional state and fine-tunes the schedule based on that. For example, if the user is feeling stressed, adjustments such as adding relaxation time are made according to that emotional state. The optimized schedule is sent back to the device, where the user can review and modify it.

[1112] Next, if the user's emotional state is affected, the system optimizes the food delivery suggestions. Based on the user's emotional state, for example, states such as "fatigue" or "stress" are recognized, and appropriate meals (e.g., healthy dishes or refreshing desserts) are suggested. These suggestions are optimized for easy selection by the user and are displayed on the device.

[1113] When a user inputs a specific emotion or state, the server uses an emotion engine to analyze that state and suggest the most suitable dishes or restaurants. For example, if a user inputs "I'm tired today," the server uses the emotion engine to recognize "fatigue" and suggests healthy dishes. This process reduces the user's psychological burden and provides an optimal service experience.

[1114] The system requires hardware such as smartphones, and software such as the EmotionEngine and FoodDeliveryAPI. Through these components, user emotion recognition, data analysis, suggestion generation, and the ordering process are integrated.

[1115] For example, if a user enters "I'm tired today," the emotion engine recognizes "fatigue," and the food delivery API suggests three healthy dishes. For instance, "green salad," "chicken soup," and "fruit bowl" might be displayed. The user then reviews and modifies their selections, and the order is finalized.

[1116] Examples of prompt statements for input to a generative AI model include the following:

[1117] "I'm feeling stressed and tired right now. Could you recommend some dishes?"

[1118] In this way, it becomes possible to provide optimal food delivery suggestions based on the user's emotional state.

[1119] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1120] Step 1:

[1121] Users input their schedules and emotional states from a smartphone or other device. Specifically, users input their emotional state in text format, such as "I'm tired today." This data is temporarily stored on the device.

[1122] Step 2:

[1123] The device sends user input data (schedule and emotional state) to the server. This transmission process involves sending data to the server via an API. The server receives the entered emotional state data.

[1124] Step 3:

[1125] The server analyzes the received data. Here, the EmotionEngine is used to analyze emotions from text data. For example, it extracts the emotional state "fatigue" from the input "tired." The analysis results are stored on the server.

[1126] Step 4:

[1127] The server uses generative AI to suggest the most suitable dishes and restaurants based on the user's emotional state. It calls a food delivery API to retrieve data on dishes appropriate for that emotional state. For example, for the emotion of "fatigue," it might suggest healthy dishes such as "green salad," "chicken soup," and "fruit bowl." This information is temporarily stored on the server.

[1128] Step 5:

[1129] The server sends suggestion data to the device. The API then forwards dish suggestions, tailored to the user's emotional state, to the device. The device displays the received data and shows the suggestions to the user.

[1130] Step 6:

[1131] The user reviews, selects, and modifies the suggested dishes. From the dish options displayed on the device, the user selects their desired dish. The information about the user's selected dish is temporarily saved on the device.

[1132] Step 7:

[1133] The device sends user selection data to the server. Information about the selected dish is sent to the server via API. The transmitted data is received by the server.

[1134] Step 8:

[1135] The server generates the final order and sends it to the food delivery service. Order information is generated and sent to the delivery service via the food delivery API along with the user's delivery address information. A final order confirmation message is sent to the user's device and displayed on it.

[1136] 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.

[1137] 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.

[1138] 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.

[1139] [Third Embodiment]

[1140] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1141] 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.

[1142] 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).

[1143] 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.

[1144] 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.

[1145] 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).

[1146] 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.

[1147] 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.

[1148] 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.

[1149] 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.

[1150] 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.

[1151] 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".

[1152] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering. It also provides support for achieving long-term goals for self-realization.

[1153] Schedule management

[1154] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, optimizing it by eliminating duplicates and unnecessary information. The optimized schedule is sent to the device, where the user can review and modify it.

[1155] Specific example:

[1156] When a user registers their schedule for the following week, the AI ​​detects any overlapping meeting times and suggests moving them to a different, more suitable time.

[1157] Email Processing

[1158] The user receives an email on their device. The device sends the received email data to the server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The summary and suggested reply are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[1159] Specific example:

[1160] When a user receives a large volume of emails, the AI ​​prioritizes important emails and provides templates to make replying easier.

[1161] Task management

[1162] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, and sends the generated task schedule to the device. The user confirms and executes the tasks.

[1163] Specific example:

[1164] When a user enters tasks for a new project, the AI ​​considers the dependencies between tasks and suggests a natural order and estimated time for each.

[1165] Information gathering

[1166] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the AI ​​collects information from the specified data source. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report.

[1167] Specific example:

[1168] When a user submits a market research request, the AI ​​gathers the latest statistical data and trending articles and provides a clearly summarized report.

[1169] Support for reverse planning to achieve self-realization

[1170] The user inputs their long-term goal from their device. The server receives the long-term goal, and the AI ​​works backward to set annual goals. Furthermore, the annual goals are broken down into monthly and weekly tasks. The generated task schedule is sent to the device, which the user reviews and executes.

[1171] Specific example:

[1172] If a user sets a goal like "I will become independent and start my own business in 10 years," the AI ​​will work backward to determine the necessary steps, such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[1173] These features enable users to streamline their daily tasks and work towards achieving long-term goals. This system leverages the power of generative AI to effectively support user productivity and self-realization.

[1174] The following describes the processing flow.

[1175] Schedule management

[1176] Step 1:

[1177] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[1178] Step 2:

[1179] The device sends user input data to the server. For example, it might send data in the format "2023-10-01: Meeting, 2023-10-02: Client visit".

[1180] Step 3:

[1181] The server analyzes the schedule data it receives. It checks the format and content of the input data to ensure there are no errors or missing information.

[1182] Step 4:

[1183] The server uses AI to optimize schedule data. Specifically, it adjusts overlapping appointments, prioritizes them based on importance, and reduces unnecessary travel time.

[1184] Step 5:

[1185] The server sends an optimized schedule to the terminal. It is then sent again in JSON format, etc.

[1186] Step 6:

[1187] The device notifies the user of the optimized schedule it has received. The user then uses this information to review and modify their schedule.

[1188] Email Processing

[1189] Step 1:

[1190] The user receives an email on their device. A notification is sent indicating that a new email is available.

[1191] Step 2:

[1192] The device sends received email data to the server. This data includes information such as the email content and sender.

[1193] Step 3:

[1194] The server analyzes the emails it receives. AI determines the importance of the emails and filters them to determine if they are spam.

[1195] Step 4:

[1196] The AI ​​on the server generates email summaries and suggested replies. For example, in response to an email requesting meeting confirmation, it can generate a suggested reply such as "I can attend."

[1197] Step 5:

[1198] The server sends a summary and a draft reply to the terminal. Data containing the summary and draft reply is sent.

[1199] Step 6:

[1200] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[1201] Task management

[1202] Step 1:

[1203] The user enters the task from their device. They fill in the project name and specific task details.

[1204] Step 2:

[1205] The terminal sends the entered task data to the server. The data is sent in JSON format, among others.

[1206] Step 3:

[1207] The server analyzes the received task data. The AI ​​determines the task priorities and dependencies.

[1208] Step 4:

[1209] The AI ​​on the server generates the optimal task order and timeline. For example, it determines the task order based on the project's progress.

[1210] Step 5:

[1211] The server sends the generated task schedule to the terminal. Data containing the detailed schedule is sent.

[1212] Step 6:

[1213] The device notifies the user of the task schedule it has received. The user reviews the schedule and proceeds with execution.

[1214] Information gathering

[1215] Step 1:

[1216] The user enters an information gathering request from their device. They enter the topic or keywords they want to investigate.

[1217] Step 2:

[1218] The device sends an information collection request to the server.

[1219] Step 3:

[1220] The server receives the request, and the AI ​​collects information from specific data sources. It gathers necessary information from sources such as news websites and databases.

[1221] Step 4:

[1222] The AI ​​on the server summarizes the collected information and generates a report. It extracts the most important parts from the collected data.

[1223] Step 5:

[1224] The server sends the generated report to the terminal. Data containing a summary report is sent.

[1225] Step 6:

[1226] The device notifies the user of the reports it has received. The user reviews the reports and takes the necessary actions.

[1227] Support for reverse planning to achieve self-realization

[1228] Step 1:

[1229] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[1230] Step 2:

[1231] The device sends long-term goal data to the server.

[1232] Step 3:

[1233] The server receives the long-term goal, and the AI ​​works backward to set annual goals. Specific goals are defined for each year.

[1234] Step 4:

[1235] The AI ​​on the server breaks down the annual goals into monthly and weekly units and converts them into tasks.

[1236] Step 5:

[1237] The server sends the generated task schedule to the terminal. Detailed schedule data is sent.

[1238] Step 6:

[1239] The device notifies the user of the task schedule it has received. The user reviews the information and takes the necessary actions.

[1240] (Example 1)

[1241] 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."

[1242] We provide a system that efficiently supports users' daily work and self-realization by utilizing generative AI. Conventional systems lacked sufficient integration of schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization, making it difficult to improve user productivity. Furthermore, they lacked features to eliminate duplication and waste and optimize processes, resulting in cumbersome manual management.

[1243] 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.

[1244] In this invention, the server includes means for analyzing received data, means for optimizing the analyzed data, and means for transmitting the generated data to a terminal. This enables schedule optimization, email processing with importance assessment and spam filtering, task management considering priorities and dependencies, information gathering that collects and summarizes information from specific data sources, and self-actualization support that converts long-term goals into concrete tasks by working backward.

[1245] A "schedule" refers to a plan based on time and date, including the user's appointments.

[1246] "Terminal" refers to electronic devices used by users, such as smartphones and computers.

[1247] A "server" refers to a computer system that receives data sent by users and performs analysis and processing on it.

[1248] "Data analysis" refers to the process of processing received data and extracting meaningful information.

[1249] "Optimization" refers to adjustments made to eliminate redundancy and waste, resulting in an efficient state.

[1250] "Email" refers to electronic mail, including digital messages sent and received over the internet.

[1251] A "task" refers to any work or action that needs to be performed in order to achieve a specific goal.

[1252] "Information gathering" refers to the process of collecting data and knowledge necessary for a specific purpose.

[1253] "Long-term goals" refer to major objectives that are planned to be achieved over a long period of time.

[1254] A "generative AI model" refers to a model that uses artificial intelligence technology to generate output based on user input data and requests.

[1255] A "prompt statement" refers to an instruction given as input to an AI model.

[1256] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides five functions: schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization. The details are described below.

[1257] Schedule management

[1258] The user enters their schedule from their device. The device sends the entered schedule data to the server. The server uses a "generative AI model" to analyze the received schedule data, optimizing it by eliminating duplication and waste. The optimized schedule is sent to the device, which the user can then review and modify. For example, if a user registers their schedule for the following week, the "generative AI model" might detect a meeting time conflict and suggest moving it to a different, more appropriate time.

[1259] Example prompt message: "I have entered the schedule for next week. Please check for duplicates and inefficiencies and optimize it."

[1260] Email Processing

[1261] The user receives an email on their device. The device sends the received email data to a server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The generated summary and reply are sent to the device, where the user reviews and modifies them as needed before sending. For example, when a user receives a large number of emails, the AI ​​model on the server prioritizes important emails and provides templates to facilitate replies.

[1262] Example prompt: "Summarize the received email and generate a draft reply."

[1263] Task management

[1264] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. A generative AI model generates the optimal task order and timeline, and sends the generated task schedule to the device. The user reviews and executes the tasks. For example, when a user enters tasks for a new project, the AI ​​model considers the task dependencies and suggests a natural order and estimated time for each task.

[1265] Example prompt: "I have entered the tasks for this project. Please generate the optimal task order and schedule, taking dependencies and priorities into consideration."

[1266] Information gathering

[1267] The user enters a request for information gathering from their device. The device sends the information gathering request to the server. The server receives the request, and the AI ​​collects information from specific data sources. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report. For example, if a user enters a request for market research, the AI ​​model collects the latest statistical data and trending articles and provides a clearly summarized report.

[1268] Example prompt: "Collect data and trend articles for market research and generate a summarized report."

[1269] Support for reverse planning to achieve self-realization

[1270] The user enters a long-term goal from their device. The device sends the entered long-term goal to the server. The server receives the long-term goal and uses a generating AI model to set annual goals. Furthermore, it breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is sent to the device for the user to review and execute. For example, if the user sets "I will become independent and start my own business in 10 years," the AI ​​model will work backward to determine the necessary steps such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[1271] Example prompt: "Please create a schedule outlining the steps and plan necessary to start your own business in 10 years."

[1272] This system leverages the power of generative AI to support users in efficiently performing their tasks and achieving long-term goals. HTTP POST is used for communication between the server and the terminal, and data is exchanged in JSON format. Generative AI models play a crucial role in each function, analyzing user input data and providing optimal suggestions to improve productivity.

[1273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1274] Schedule management

[1275] Step 1:

[1276] The user enters their schedule using a terminal. The entered data is generated in JSON format via the keyboard or touchscreen.

[1277] Step 2:

[1278] The terminal sends the entered schedule data to the server. Specifically, it sends the schedule data in JSON format using an HTTP POST request.

[1279] Step 3:

[1280] The server analyzes the received schedule data. A generative AI model is used for the analysis, performing pattern recognition to eliminate duplication and waste from the data.

[1281] Step 4:

[1282] The server generates an optimized schedule based on the analyzed data. The generated schedule is also converted to JSON format.

[1283] Step 5:

[1284] The server sends an optimized schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1285] Step 6:

[1286] Users can view the optimized schedule on their device and make adjustments as needed. The adjustment data is also saved in JSON format.

[1287] Email Processing

[1288] Step 1:

[1289] The user receives emails using their device. Emails are received via a standard email application.

[1290] Step 2:

[1291] The device sends the received email data to the server. The transmission format is JSON, and it uses an HTTP POST request.

[1292] Step 3:

[1293] The server analyzes the content of the email. A generative AI model is used for the analysis, including determining importance and filtering spam.

[1294] Step 4:

[1295] The server generates an email summary and a draft reply. The generated summary and draft reply are converted into JSON format.

[1296] Step 5:

[1297] The server sends the generated summary and proposed reply to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1298] Step 6:

[1299] The user reviews the summary and proposed reply on their device and makes revisions as needed. The revised reply is then sent via email.

[1300] Task management

[1301] Step 1:

[1302] The user enters a new task using a terminal. The entered data is generated in JSON format.

[1303] Step 2:

[1304] The terminal sends the entered task data to the server. Specifically, it sends the task data in JSON format using an HTTP POST request.

[1305] Step 3:

[1306] The server analyzes the received task data. A generative AI model is used for the analysis to determine task priorities and dependencies.

[1307] Step 4:

[1308] The server generates the optimal task order and timeline based on the analysis results. The generated task schedule is converted to JSON format.

[1309] Step 5:

[1310] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1311] Step 6:

[1312] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[1313] Information gathering

[1314] Step 1:

[1315] The user enters a data collection request using their device. The entered data is generated in JSON format.

[1316] Step 2:

[1317] The device sends an information collection request to the server. The transmission format is JSON, and it uses an HTTP POST request.

[1318] Step 3:

[1319] The server receives a request and uses a generative AI model to collect information from a specific data source. The collected information is obtained from databases or the internet.

[1320] Step 4:

[1321] The server summarizes the collected information and generates a report. The generated report is converted to JSON format.

[1322] Step 5:

[1323] The server sends the generated report to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1324] Step 6:

[1325] The user views the report on their device. The data in the report is modified as needed.

[1326] Support for reverse planning to achieve self-realization

[1327] Step 1:

[1328] The user enters their long-term goals using a device. The entered data is generated in JSON format.

[1329] Step 2:

[1330] The terminal sends the entered long-term goals to the server. The transmission format is JSON, and it uses an HTTP POST request.

[1331] Step 3:

[1332] The server receives the long-term goals and uses a generative AI model to set annual goals. The set goals are then converted into JSON format.

[1333] Step 4:

[1334] The server breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is then converted into JSON format.

[1335] Step 5:

[1336] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1337] Step 6:

[1338] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[1339] This allows the system to perform specific data processing and calculations for each function, providing optimized data and thereby improving user productivity.

[1340] (Application Example 1)

[1341] 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."

[1342] In traditional virtual store operations, managing staff schedules, handling customer inquiries via email, and managing tasks were often done manually, resulting in inefficiencies. Furthermore, there was a lack of tools to streamline operations, such as optimizing schedules, promptly addressing important emails, and prioritizing tasks. As a result, operational efficiency declined, placing a burden on store management.

[1343] 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.

[1344] In this invention, the server includes means for the user to input a schedule, means for the terminal to transmit the user's input data to the server, means for the server to analyze the received schedule data, means for optimizing the analyzed schedule data, means for transmitting the optimized schedule to the terminal, means for the user to confirm and modify the optimized schedule, means for optimizing staff schedules in a virtual store, and means for generating prompt statements when optimizing the schedule using a generative AI model. This enables efficient management of staff schedules in a virtual store.

[1345] A "user" is an individual or legal entity that uses the system or terminals to operate and manage a virtual store.

[1346] A "schedule" is a plan of the date, time, and content of events and tasks that the user enters.

[1347] A "device" refers to an input and display device such as a smartphone, tablet, or personal computer used by a user.

[1348] A "server" is a computer system that receives, analyzes, and optimizes data sent by users, and then returns the results to the terminal.

[1349] "Schedule data" refers to information about the schedule entered by the user.

[1350] "Analysis" refers to the process of analyzing schedule data and email data received by a server to extract and evaluate appropriate information.

[1351] "Optimization" refers to the efficient and effective organization and adjustment of schedules and task data.

[1352] A "virtual store" is an online store that provides goods and services via the internet.

[1353] "Staff" refers to the personnel who support the operation of the virtual store.

[1354] A "generative AI model" refers to an artificial intelligence algorithm trained to perform a specific task.

[1355] A "prompt statement" is an instruction given to a generative AI model, containing instructions for obtaining a specific result.

[1356] "Email" refers to messages sent and received electronically, and is used for customer inquiries and internal company communications.

[1357] A "task" refers to the work or tasks that a user is supposed to perform.

[1358] "Priority" refers to the order in which tasks and schedules are arranged based on their importance and urgency.

[1359] "Dependency" refers to a relationship where one task or schedule depends on another task or event.

[1360] A "summary" refers to a concise compilation of key information.

[1361] A "suggested reply" is a proposed response to a message, such as an email.

[1362] This invention is a system that utilizes a generative AI model to streamline daily operations in virtual stores and improve user productivity. This system primarily provides three main functions: schedule management, email processing, and task management. The implementation methods for each function are described below.

[1363] Schedule management

[1364] The user enters the staff schedule for the virtual store using a terminal. This schedule data is sent from the terminal to the server. The server analyzes the received schedule data, eliminating duplication and inefficiencies to optimize it. The optimized schedule is sent back to the terminal for the user to review and modify. At this time, a generation AI model is used to generate prompts for schedule optimization, and the AI ​​is instructed to perform the optimization work.

[1365] Email Processing

[1366] Emails received by the user are received on the device, and the data is sent to the server. The server analyzes the content of the emails, determines their importance, and performs spam filtering. Based on the analyzed content of the emails, AI generates summaries and suggested replies. The generated summaries and suggested replies are sent to the device, where the user reviews and modifies them, and sends them as needed.

[1367] Task management

[1368] When a user enters a new task from their device, the task data is sent to the server. The server analyzes the task data and uses a generative AI model to determine priorities and dependencies, generating an optimal task sequence and timeline. This enables efficient task management. The generated task schedule is sent to the device, where the user can review and execute it.

[1369] Hardware and software used

[1370] Hardware: Servers (e.g., AWS EC2 instances), user devices (smartphones, tablets, PCs)

[1371] Software: Django framework (server-side program), generative AI model (e.g., OpenAI GPT-3)

[1372] Examples of specific cases and prompt statements

[1373] Specific example

[1374] For example, consider a scenario where a store manager inputs staff shift schedules. If different shifts overlap, the server uses a generated AI model to optimize the schedule and suggest the best shift arrangement. Furthermore, when a large volume of customer inquiry emails arrive, the AI ​​generates summaries and suggested replies to support a quick response.

[1375] Example of a prompt

[1376] For schedule optimization: "Optimize this schedule: {'Mon': ['StaffA', 'StaffB'], 'Tue': ['StaffC', 'StaffD'], 'Wed': ['StaffA', 'StaffE']}"

[1377] For email processing: "Summarize and create a reply draft for this email: 'Dear Store, We have an urgent issue regarding our recent order...'"

[1378] Based on the above, the system of the present invention provides a concrete means to streamline daily operations in virtual store management and reduce the workload of users.

[1379] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1380] Step 1:

[1381] The user enters their schedule into the terminal. The terminal receives the entered schedule data and sends it to the server. The input data includes the date and time, event details, and information about the staff in charge. The output is the schedule data sent to the server.

[1382] Step 2:

[1383] The server analyzes the received schedule data. The analysis verifies data integrity and checks for duplication and unnecessary information. The input is the schedule data, and the output is the analysis results.

[1384] Step 3:

[1385] The server optimizes the analyzed schedule data. A generative AI model is used to generate prompts for optimization. These prompts are input to the AI ​​model to obtain the optimal schedule. The input consists of the analysis results and prompts, and the output is the optimized schedule data.

[1386] Step 4:

[1387] The server sends optimized schedule data to the terminal. The terminal displays the received data and prompts the user for confirmation and correction. The input is the optimized schedule data, and the output is the schedule displayed on the terminal.

[1388] Step 5:

[1389] The system reviews the schedule received by the user and makes corrections as needed. The corrected schedule data is then sent back to the server. The input is the user's corrected data, and the output is the corrected schedule data.

[1390] Step 6:

[1391] The user receives an email on their device. The device then sends the received email data to the server. The input is the email data, and the output is the email data sent to the server.

[1392] Step 7:

[1393] The server analyzes received email data, performs importance assessment, and filters out spam. Based on the analysis results, an AI model is used to generate summaries and suggested replies. The input is email data, and the output is summaries and suggested replies.

[1394] Step 8:

[1395] The server sends the generated summary and draft reply to the terminal. The terminal displays it to the user, who then reviews and makes corrections. The input is the summary and draft reply, and the output is the data displayed to the user.

[1396] Step 9:

[1397] The user reviews and corrects the summary and draft reply, then resends them to the server for final delivery. The input is the corrected summary and draft reply, and the output is the sent email.

[1398] Step 10:

[1399] The user enters a new task into the terminal. The terminal sends the entered task data to the server. The input is the task data, and the output is the task data sent to the server.

[1400] Step 11:

[1401] The server analyzes the received task data to determine priorities and dependencies. Based on the analysis results, a generative AI model is used to generate the optimal task order and timeline. The input is task data, and the output is the optimized task order and timeline.

[1402] Step 12:

[1403] The server sends the generated task schedule to the terminal. The terminal displays it to the user, who then reviews and executes the task schedule. The input is the optimized task schedule, and the output is the data displayed to the user.

[1404] Through the steps described above, the present invention provides concrete means for streamlining users' daily operations and supporting virtual store management.

[1405] 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.

[1406] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[1407] Schedule management

[1408] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotions and optimizes the schedule based on those emotions. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the device, and the user can review and modify it.

[1409] Specific example:

[1410] When a user schedules a meeting or client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[1411] Email Processing

[1412] The user receives an email from their device. The device sends the received email data to the server. The server analyzes the email content, and the sentiment engine recognizes the user's emotions to determine importance and perform spam filtering. The AI ​​also generates an email summary and suggested replies, adjusting them based on the user's emotions. For example, if the user is fatigued, a simple reply suggestion might be made. The summary and suggested replies are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[1413] Specific example:

[1414] When a user receives an important email while feeling fatigued, the emotion engine generates a simple and quick response suggestion to reduce the user's burden.

[1415] Task management

[1416] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[1417] Specific example:

[1418] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[1419] Information gathering

[1420] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[1421] Specific example:

[1422] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[1423] Support for reverse planning to achieve self-realization

[1424] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[1425] Specific example:

[1426] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[1427] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[1428] The following describes the processing flow.

[1429] Schedule management processing steps

[1430] Step 1:

[1431] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[1432] Step 2:

[1433] The terminal sends user input data to the server. The data is often sent in formats such as JSON or XML.

[1434] Step 3:

[1435] The server analyzes the received schedule data. It checks the data format and performs checks for any discrepancies if necessary.

[1436] Step 4:

[1437] The server uses an emotion engine to recognize the user's current emotions. Specifically, it refers to emotion data previously recorded by the user or real-time emotion input.

[1438] Step 5:

[1439] The server optimizes the schedule data. For example, if a user is feeling stressed, it might add breaks to slow down the pace or adjust the order of important tasks.

[1440] Step 6:

[1441] The server sends an optimized schedule to the terminal.

[1442] Step 7:

[1443] The device notifies the user of an optimized schedule. The user can then review and modify the schedule based on this information.

[1444] Email Processing Steps

[1445] Step 1:

[1446] The user receives an email from their device. A notification appears as a pop-up or alert.

[1447] Step 2:

[1448] The device sends received email data to the server. This data includes information such as the email body, sender, and date / time.

[1449] Step 3:

[1450] The server analyzes the received emails, checking their content and determining their importance or whether they are spam.

[1451] Step 4:

[1452] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's fatigue level and stress level.

[1453] Step 5:

[1454] The server generates email summaries and suggested replies. For example, if the user is tired, it will generate a concise suggested reply.

[1455] Step 6:

[1456] The server sends a summary and a draft reply to the terminal.

[1457] Step 7:

[1458] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[1459] Task management processing steps

[1460] Step 1:

[1461] The user enters the task from their device. They fill in the project name and specific task details.

[1462] Step 2:

[1463] The terminal sends the entered task data to the server. The data format used is typically JSON or XML.

[1464] Step 3:

[1465] The server analyzes the received task data. It checks the data format and determines priorities and dependencies.

[1466] Step 4:

[1467] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's energy level and mood.

[1468] Step 5:

[1469] The server generates the optimal order and timeline for tasks, making adjustments based on emotions, such as scheduling important tasks during times of high concentration.

[1470] Step 6:

[1471] The server sends the generated task schedule to the terminal.

[1472] Step 7:

[1473] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[1474] Information gathering processing steps

[1475] Step 1:

[1476] The user enters an information gathering request from their device. They enter the topic, keywords, and purpose they want to investigate.

[1477] Step 2:

[1478] The device sends an information collection request to the server.

[1479] Step 3:

[1480] The server receives the request and uses an emotion engine to recognize the user's emotions.

[1481] Step 4:

[1482] The server collects information from specific data sources. It retrieves necessary information from sources such as news websites and academic journal databases.

[1483] Step 5:

[1484] The server summarizes the collected information and adjusts the report based on the user's emotions. For example, if the user is easily fatigued, a concise summary is generated.

[1485] Step 6:

[1486] The server sends the generated report to the terminal.

[1487] Step 7:

[1488] The device notifies the user of the report it has received. The user reviews the report and takes the necessary action.

[1489] Processing steps for supporting reverse engineering for self-realization

[1490] Step 1:

[1491] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[1492] Step 2:

[1493] The device sends long-term goal data to the server.

[1494] Step 3:

[1495] The server receives the long-term goals and uses an emotion engine to recognize the user's emotions.

[1496] Step 4:

[1497] The server uses AI to work backward and set annual goals. It defines specific steps and milestones.

[1498] Step 5:

[1499] The server breaks down annual goals into monthly and weekly units and converts them into tasks. It also makes adjustments based on emotions.

[1500] Step 6:

[1501] The server sends the generated task schedule to the terminal.

[1502] Step 7:

[1503] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[1504] (Example 2)

[1505] 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."

[1506] Traditional scheduling, email processing, task management, and information gathering systems often fail to consider user emotions, leading to stress and decreased work efficiency. This frequently resulted in users being unable to achieve their full productivity. To address this problem, dynamic adjustments based on user emotional states are required.

[1507] 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.

[1508] In this invention, the server includes means for an emotion engine to recognize the user's emotions, means for optimizing the schedule based on analysis and emotion recognition, and means for adjusting the generated summaries and response suggestions based on the emotions. This enables improved user productivity and reduced stress by making optimal adjustments according to the user's emotional state.

[1509] A "user" refers to a person who uses this system to manage their schedule, process emails, manage tasks, and gather information.

[1510] "Device" refers to electronic devices used by users, such as personal computers, smartphones, and tablets.

[1511] A "server" refers to a computer system that receives data sent from a terminal and performs analysis and optimization.

[1512] An "emotion engine" refers to software or hardware that recognizes a user's emotions and optimizes data based on those recognition results.

[1513] "Schedule data" refers to information about appointments and plans entered by the user.

[1514] "Analysis" refers to the process by which a server processes received data to understand and interpret its content, importance, dependencies, and other relevant information.

[1515] "Optimization" refers to adjusting schedules, task sequences, email summaries, and response drafts more effectively and efficiently based on analyzed data and user sentiment recognition results.

[1516] "Email data" refers to the content of emails received by a user and any accompanying information.

[1517] A "summary" refers to information that has been extracted and concisely compiled from the most important parts of an email or other information gathering results.

[1518] A "draft reply" refers to a suggested text that will be generated as a response to an email.

[1519] "Task data" refers to information about jobs and tasks entered by the user.

[1520] "Priority" refers to the criteria used to determine the order in which tasks and appointments entered by the user are executed, based on factors such as importance and urgency.

[1521] A "dependency" refers to a relationship where one task presupposes the completion of another task.

[1522] A "timeline" refers to a chronological arrangement of tasks and appointments that need to be completed within a specific period.

[1523] "Information gathering" refers to the process of obtaining necessary data from specific sources based on user instructions.

[1524] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[1525] Schedule management

[1526] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotions and optimizes the schedule based on those emotions. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the device, and the user can review and modify it.

[1527] Specific example:

[1528] When a user schedules a meeting or client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[1529] Example of a prompt:

[1530] "I'm entering this week's schedule. There are two important meetings and one client visit. Please adjust the schedule considering the stress level."

[1531] Email Processing

[1532] The user receives an email from their device. The device sends the received email data to the server. The server analyzes the email content, and the sentiment engine recognizes the user's emotions to determine importance and perform spam filtering. The AI ​​also generates an email summary and suggested replies, adjusting them based on the user's emotions. For example, if the user is fatigued, a simple reply suggestion might be made. The summary and suggested replies are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[1533] Specific example:

[1534] When a user receives an important email while feeling fatigued, the emotion engine generates a simple and quick response suggestion to reduce the user's burden.

[1535] Example of a prompt:

[1536] "Please provide a summary of the important email I received today and a draft reply. I am very tired right now, so a brief reply would be appreciated."

[1537] Task management

[1538] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[1539] Specific example:

[1540] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[1541] Example of a prompt:

[1542] "I'll enter today's tasks. These include meeting preparation, report writing, and presentation practice. Please create a schedule in the optimal order, taking my energy level into consideration."

[1543] Information gathering

[1544] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[1545] Specific example:

[1546] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[1547] Example of a prompt:

[1548] "Please gather information on recent market trends. I'm currently exhausted, so I'd prefer a concise summary report."

[1549] Support for reverse planning to achieve self-realization

[1550] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[1551] Specific example:

[1552] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[1553] Example of a prompt:

[1554] "My goal is to become independent and start my own business in 10 years. Please create annual, monthly, and weekly plans to achieve this goal, and adjust them to take my stress levels into consideration."

[1555] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[1556] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1557] Schedule management

[1558] Step 1:

[1559] The user enters their schedule from their device. For example, the user enters appointments for meetings or client visits into their device. This input data includes the date, time, and content of the appointment.

[1560] Step 2:

[1561] The terminal sends the entered schedule data to the server. The entered data is transferred to the server using an HTTP request. This operation constitutes data communication from the terminal to the server.

[1562] Step 3:

[1563] The server analyzes the received schedule data. A natural language processing engine (e.g., spaCy) is used to analyze the data's content. Here, the schedule's content, importance, and deadline are determined. The results of this analysis become the input data for the next processing step.

[1564] Step 4:

[1565] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., IBM Watson Tone Analyzer) is used to evaluate the user's stress level. Past user response data and temporary emotion data are used as input data.

[1566] Step 5:

[1567] The server optimizes the schedule based on analysis and sentiment recognition. An AI model (e.g., GPT-4) is used to make adjustments such as postponing or easing important tasks and inserting relaxation time. The data generated during this optimization process is output as optimized schedule data.

[1568] Step 6:

[1569] The optimized schedule is sent to the device. The final generated optimized schedule data is sent to the device as an HTTP response.

[1570] Step 7:

[1571] Users can review and modify their optimized schedules. Users can check their schedules on their devices and make additional changes or modifications as needed.

[1572] ---

[1573] Email Processing

[1574] Step 1:

[1575] The user receives an email on their device. The user receives a new email through an email client (e.g., Outlook or Gmail).

[1576] Step 2:

[1577] The device sends the received email data to the server. The received email data is sent to the server via an HTTP request.

[1578] Step 3:

[1579] The server analyzes the content of the email. Using a natural language processing engine (e.g., NLTK or spaCy), it analyzes the email content and evaluates the importance of the body and attachments. This result is stored on the server and used as input data for the next processing step.

[1580] Step 4:

[1581] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., TextBlob) is used to determine the user's emotional state (e.g., fatigue level, stress). The user's past behavior and emotional data are used as input data.

[1582] Step 5:

[1583] The server determines the importance and whether an email is spam. A spam detection algorithm (e.g., Naive Bayes) is used to determine importance and filter out spam. The determination result is used as input data for the next processing step.

[1584] Step 6:

[1585] AI generates and adjusts email summaries and response drafts based on sentiment. Using an AI model (e.g., GPT-4), it generates summary texts and response drafts, and adjusts the wording to match the user's sentiment.

[1586] Step 7:

[1587] The summary and proposed reply are sent to the terminal. The final generated summary and proposed reply are sent to the terminal as an HTTP response.

[1588] Step 8:

[1589] The user reviews the summary and draft reply, makes revisions as needed, and sends it. The user reviews the summary and draft reply on their device, makes revisions as needed, and sends the final email.

[1590] ---

[1591] Task management

[1592] Step 1:

[1593] The user enters tasks from the terminal. The user enters tasks such as "report creation" or "data analysis" into the terminal.

[1594] Step 2:

[1595] The terminal sends the entered task data to the server. The entered task data is sent to the server using an HTTP request.

[1596] Step 3:

[1597] The server analyzes the task data. Using a natural language processing engine (e.g., SpaCy), it analyzes the task content, importance, dependencies, etc. The analysis results become input data for the next processing step.

[1598] Step 4:

[1599] The emotion engine recognizes the user's emotions. It uses an emotion analysis library (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Past user response data and temporary emotion data are used as input data.

[1600] Step 5:

[1601] The server determines priorities and dependencies. Based on the analysis results and sentiment recognition results, it determines the priority and dependencies of tasks. This determination becomes the input data for the next processing step.

[1602] Step 6:

[1603] The AI ​​generates and adjusts the optimal task order and timeline based on emotions. Using an AI model (e.g., GPT-4), it generates the optimal task order and timeline and adjusts it to match the user's emotions.

[1604] Step 7:

[1605] The generated task schedule is sent to the terminal. The final task schedule data is sent to the terminal as an HTTP response.

[1606] Step 8:

[1607] The user reviews and executes the task schedule. The user reviews the task schedule generated on their device, makes any necessary modifications, and then proceeds with execution.

[1608] ---

[1609] Information gathering

[1610] Step 1:

[1611] The user enters a request for information gathering from their device. For example, the user enters a request to find out about "recent market trends" into their device.

[1612] Step 2:

[1613] The device sends an information collection request to the server. The information collection request data is sent to the server using an HTTP request.

[1614] Step 3:

[1615] The server receives and analyzes the request. Using a natural language processing engine, it analyzes the request content and identifies the data necessary for information gathering.

[1616] Step 4:

[1617] The emotion engine recognizes the user's emotions. It uses an emotion analysis library to recognize the user's emotional state. Input data includes information related to the user's stress and fatigue levels.

[1618] Step 5:

[1619] The server collects information. It uses web scraping techniques (e.g., Beautiful Soup) to collect the necessary information from the specified data source.

[1620] Step 6:

[1621] The AI ​​summarizes and reframes the collected information based on sentiment. Using an AI model (e.g., GPT-4), it summarizes the collected information and presents it in a format that aligns with the user's emotions.

[1622] Step 7:

[1623] The generated report is sent to the terminal. The final report data is sent to the terminal as an HTTP response.

[1624] Step 8:

[1625] The user reviews the report. The user reviews the report generated on their device and provides feedback as needed.

[1626] ---

[1627] Support for reverse planning to achieve self-realization

[1628] Step 1:

[1629] The user enters their long-term goal from their device. For example, the user might enter the goal "I will become independent and start my own business in 10 years" into their device.

[1630] Step 2:

[1631] The device sends long-term goal data to the server. The long-term goal data is sent to the server using an HTTP request.

[1632] Step 3:

[1633] The server receives and analyzes the data. A natural language processing engine is used to analyze the content of the input long-term goals. The analysis results obtained here are used as input data for the next processing step.

[1634] Step 4:

[1635] The emotion engine recognizes the user's emotions. An emotion analysis library is used to recognize the user's emotional state. Here, the user's stress level and motivation are used as input data.

[1636] Step 5:

[1637] The AI ​​works backward to set annual targets. Using an AI model (e.g., GPT-4), it sets the annual targets necessary to achieve the long-term goal. This backward calculation result is used as input data for the next processing step.

[1638] Step 6:

[1639] The AI ​​breaks down annual goals into monthly and weekly tasks. These generated tasks are then converted into monthly and weekly goals based on the annual plan.

[1640] Step 7:

[1641] The server optimizes generated task schedules based on emotions. It considers the user's emotional state and optimizes the task schedule accordingly. For example, it reduces the workload during periods of high stress.

[1642] Step 8:

[1643] A task schedule optimized for the device is sent. The optimized task schedule is sent to the device as an HTTP response.

[1644] Step 9:

[1645] The user reviews and executes the task schedule. The user reviews the generated task schedule, makes any necessary corrections or adjustments, and then proceeds with execution.

[1646] ---

[1647] This allows users to efficiently manage schedules, tasks, and emails, and gather information. Furthermore, by utilizing an emotion engine, appropriate adjustments are made based on the user's emotional state, resulting in increased productivity and reduced stress.

[1648] (Application Example 2)

[1649] 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."

[1650] Traditional food delivery systems have a problem in that they do not consider the user's emotional state when suggesting dishes or restaurants, thus failing to reduce user stress and improve satisfaction. Furthermore, the ordering process lacks consideration for reducing the user's psychological burden, resulting in an unoptimized user experience. To solve these problems, a system is needed that provides optimal suggestions based on the user's emotional state.

[1651] 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. In this invention, the server includes means for analyzing user input data and optimally adjusting schedules and suggestions using a generative AI and an emotion engine, means for making suggestions and optimizations regarding food delivery based on the user's emotional state, and means for transmitting the suggested and optimized data to a terminal for the user to confirm and modify. This enables optimal food delivery suggestions based on the user's emotional state and an ordering process that reduces psychological burden.

[1652] A "schedule" is a planner that allows users to manage their daily activities and appointments hour by hour.

[1653] A "terminal" refers to an electronic device that a user can operate and use to input and receive information.

[1654] A "server" is a central computer system that processes and manages data over a network.

[1655] "Analysis" is the process of meticulously examining data to find specific information or patterns within it.

[1656] "Generative AI" refers to artificial intelligence that automatically generates new data and information based on user input.

[1657] An "emotion engine" is a technology that recognizes the user's emotional state and provides appropriate responses and suggestions based on those emotions.

[1658] "Optimization" is the process of adjusting to the most effective state or conditions for a specific purpose.

[1659] "Food delivery" is a service where users order food and have it delivered to a specified location.

[1660] "Email" refers to electronic messages sent and received via the internet.

[1661] A "task" is a specific task or activity that needs to be performed in order to achieve a particular goal.

[1662] A "summary" is a short, concise piece of text or content that captures the main points of a long piece of information.

[1663] A "suggested reply" is a proposed or suggested response to a received message.

[1664] This invention provides a food delivery system for realizing the described invention. This system consists of a terminal operated by the user and a server that centrally processes and manages data.

[1665] First, when a user enters their schedule from a device such as a smartphone, the device sends the user's input data to the server. The server analyzes the received schedule data and optimizes it using generative AI and an emotion engine. In particular, it recognizes the user's emotional state and fine-tunes the schedule based on that. For example, if the user is feeling stressed, adjustments such as adding relaxation time are made according to that emotional state. The optimized schedule is sent back to the device, where the user can review and modify it.

[1666] Next, if the user's emotional state is affected, the system optimizes the food delivery suggestions. Based on the user's emotional state, for example, states such as "fatigue" or "stress" are recognized, and appropriate meals (e.g., healthy dishes or refreshing desserts) are suggested. These suggestions are optimized for easy selection by the user and are displayed on the device.

[1667] When a user inputs a specific emotion or state, the server uses an emotion engine to analyze that state and suggest the most suitable dishes or restaurants. For example, if a user inputs "I'm tired today," the server uses the emotion engine to recognize "fatigue" and suggests healthy dishes. This process reduces the user's psychological burden and provides an optimal service experience.

[1668] The system requires hardware such as smartphones, and software such as the EmotionEngine and FoodDeliveryAPI. Through these components, user emotion recognition, data analysis, suggestion generation, and the ordering process are integrated.

[1669] For example, if a user enters "I'm tired today," the emotion engine recognizes "fatigue," and the food delivery API suggests three healthy dishes. For instance, "green salad," "chicken soup," and "fruit bowl" might be displayed. The user then reviews and modifies their selections, and the order is finalized.

[1670] Examples of prompt statements for input to a generative AI model include the following:

[1671] "I'm feeling stressed and tired right now. Could you recommend some dishes?"

[1672] In this way, it becomes possible to provide optimal food delivery suggestions based on the user's emotional state.

[1673] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1674] Step 1:

[1675] Users input their schedules and emotional states from a smartphone or other device. Specifically, users input their emotional state in text format, such as "I'm tired today." This data is temporarily stored on the device.

[1676] Step 2:

[1677] The device sends user input data (schedule and emotional state) to the server. This transmission process involves sending data to the server via an API. The server receives the entered emotional state data.

[1678] Step 3:

[1679] The server analyzes the received data. Here, the EmotionEngine is used to analyze emotions from text data. For example, it extracts the emotional state "fatigue" from the input "tired." The analysis results are stored on the server.

[1680] Step 4:

[1681] The server uses generative AI to suggest the most suitable dishes and restaurants based on the user's emotional state. It calls a food delivery API to retrieve data on dishes appropriate for that emotional state. For example, for the emotion of "fatigue," it might suggest healthy dishes such as "green salad," "chicken soup," and "fruit bowl." This information is temporarily stored on the server.

[1682] Step 5:

[1683] The server sends suggestion data to the device. The API then forwards dish suggestions, tailored to the user's emotional state, to the device. The device displays the received data and shows the suggestions to the user.

[1684] Step 6:

[1685] The user reviews, selects, and modifies the suggested dishes. From the dish options displayed on the device, the user selects their desired dish. The information about the user's selected dish is temporarily saved on the device.

[1686] Step 7:

[1687] The device sends user selection data to the server. Information about the selected dish is sent to the server via API. The transmitted data is received by the server.

[1688] Step 8:

[1689] The server generates the final order and sends it to the food delivery service. Order information is generated and sent to the delivery service via the food delivery API along with the user's delivery address information. A final order confirmation message is sent to the user's device and displayed on it.

[1690] 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.

[1691] 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.

[1692] 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.

[1693] [Fourth Embodiment]

[1694] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1695] 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.

[1696] 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).

[1697] 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.

[1698] 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.

[1699] 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).

[1700] 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.

[1701] 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.

[1702] 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.

[1703] 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.

[1704] 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.

[1705] 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.

[1706] 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".

[1707] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering. It also provides support for achieving long-term goals for self-realization.

[1708] Schedule management

[1709] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, optimizing it by eliminating duplicates and unnecessary information. The optimized schedule is sent to the device, where the user can review and modify it.

[1710] Specific example:

[1711] When a user registers their schedule for the following week, the AI ​​detects any overlapping meeting times and suggests moving them to a different, more suitable time.

[1712] Email Processing

[1713] The user receives an email on their device. The device sends the received email data to the server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The summary and suggested reply are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[1714] Specific example:

[1715] When a user receives a large volume of emails, the AI ​​prioritizes important emails and provides templates to make replying easier.

[1716] Task management

[1717] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, and sends the generated task schedule to the device. The user confirms and executes the tasks.

[1718] Specific example:

[1719] When a user enters tasks for a new project, the AI ​​considers the dependencies between tasks and suggests a natural order and estimated time for each.

[1720] Information gathering

[1721] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the AI ​​collects information from the specified data source. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report.

[1722] Specific example:

[1723] When a user submits a market research request, the AI ​​gathers the latest statistical data and trending articles and provides a clearly summarized report.

[1724] Support for reverse planning to achieve self-realization

[1725] The user inputs their long-term goal from their device. The server receives the long-term goal, and the AI ​​works backward to set annual goals. Furthermore, the annual goals are broken down into monthly and weekly tasks. The generated task schedule is sent to the device, which the user reviews and executes.

[1726] Specific example:

[1727] If a user sets a goal like "I will become independent and start my own business in 10 years," the AI ​​will work backward to determine the necessary steps, such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[1728] These features enable users to streamline their daily tasks and work towards achieving long-term goals. This system leverages the power of generative AI to effectively support user productivity and self-realization.

[1729] The following describes the processing flow.

[1730] Schedule management

[1731] Step 1:

[1732] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[1733] Step 2:

[1734] The device sends user input data to the server. For example, it might send data in the format "2023-10-01: Meeting, 2023-10-02: Client visit".

[1735] Step 3:

[1736] The server analyzes the schedule data it receives. It checks the format and content of the input data to ensure there are no errors or missing information.

[1737] Step 4:

[1738] The server uses AI to optimize schedule data. Specifically, it adjusts overlapping appointments, prioritizes them based on importance, and reduces unnecessary travel time.

[1739] Step 5:

[1740] The server sends an optimized schedule to the terminal. It is then sent again in JSON format, etc.

[1741] Step 6:

[1742] The device notifies the user of the optimized schedule it has received. The user then uses this information to review and modify their schedule.

[1743] Email Processing

[1744] Step 1:

[1745] The user receives an email on their device. A notification is sent indicating that a new email is available.

[1746] Step 2:

[1747] The device sends received email data to the server. This data includes information such as the email content and sender.

[1748] Step 3:

[1749] The server analyzes the emails it receives. AI determines the importance of the emails and filters them to determine if they are spam.

[1750] Step 4:

[1751] The AI ​​on the server generates email summaries and suggested replies. For example, in response to an email requesting meeting confirmation, it can generate a suggested reply such as "I can attend."

[1752] Step 5:

[1753] The server sends a summary and a draft reply to the terminal. Data containing the summary and draft reply is sent.

[1754] Step 6:

[1755] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[1756] Task management

[1757] Step 1:

[1758] The user enters the task from their device. They fill in the project name and specific task details.

[1759] Step 2:

[1760] The terminal sends the entered task data to the server. The data is sent in JSON format, among others.

[1761] Step 3:

[1762] The server analyzes the received task data. The AI ​​determines the task priorities and dependencies.

[1763] Step 4:

[1764] The AI ​​on the server generates the optimal task order and timeline. For example, it determines the task order based on the project's progress.

[1765] Step 5:

[1766] The server sends the generated task schedule to the terminal. Data containing the detailed schedule is sent.

[1767] Step 6:

[1768] The device notifies the user of the task schedule it has received. The user reviews the schedule and proceeds with execution.

[1769] Information gathering

[1770] Step 1:

[1771] The user enters an information gathering request from their device. They enter the topic or keywords they want to investigate.

[1772] Step 2:

[1773] The device sends an information collection request to the server.

[1774] Step 3:

[1775] The server receives the request, and the AI ​​collects information from specific data sources. It gathers necessary information from sources such as news websites and databases.

[1776] Step 4:

[1777] The AI ​​on the server summarizes the collected information and generates a report. It extracts the most important parts from the collected data.

[1778] Step 5:

[1779] The server sends the generated report to the terminal. Data containing a summary report is sent.

[1780] Step 6:

[1781] The device notifies the user of the reports it has received. The user reviews the reports and takes the necessary actions.

[1782] Support for reverse planning to achieve self-realization

[1783] Step 1:

[1784] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[1785] Step 2:

[1786] The device sends long-term goal data to the server.

[1787] Step 3:

[1788] The server receives the long-term goal, and the AI ​​works backward to set annual goals. Specific goals are defined for each year.

[1789] Step 4:

[1790] The AI ​​on the server breaks down the annual goals into monthly and weekly units and converts them into tasks.

[1791] Step 5:

[1792] The server sends the generated task schedule to the terminal. Detailed schedule data is sent.

[1793] Step 6:

[1794] The device notifies the user of the task schedule it has received. The user reviews the information and takes the necessary actions.

[1795] (Example 1)

[1796] 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".

[1797] We provide a system that efficiently supports users' daily work and self-realization by utilizing generative AI. Conventional systems lacked sufficient integration of schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization, making it difficult to improve user productivity. Furthermore, they lacked features to eliminate duplication and waste and optimize processes, resulting in cumbersome manual management.

[1798] 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.

[1799] In this invention, the server includes means for analyzing received data, means for optimizing the analyzed data, and means for transmitting the generated data to a terminal. This enables schedule optimization, email processing with importance assessment and spam filtering, task management considering priorities and dependencies, information gathering that collects and summarizes information from specific data sources, and self-actualization support that converts long-term goals into concrete tasks by working backward.

[1800] A "schedule" refers to a plan based on time and date, including the user's appointments.

[1801] "Terminal" refers to electronic devices used by users, such as smartphones and computers.

[1802] A "server" refers to a computer system that receives data sent by users and performs analysis and processing on it.

[1803] "Data analysis" refers to the process of processing received data and extracting meaningful information.

[1804] "Optimization" refers to adjustments made to eliminate redundancy and waste, resulting in an efficient state.

[1805] "Email" refers to electronic mail, including digital messages sent and received over the internet.

[1806] A "task" refers to any work or action that needs to be performed in order to achieve a specific goal.

[1807] "Information gathering" refers to the process of collecting data and knowledge necessary for a specific purpose.

[1808] "Long-term goals" refer to major objectives that are planned to be achieved over a long period of time.

[1809] A "generative AI model" refers to a model that uses artificial intelligence technology to generate output based on user input data and requests.

[1810] A "prompt statement" refers to an instruction given as input to an AI model.

[1811] This invention is a system that utilizes generative AI to support users' daily work and self-realization. This system primarily provides five functions: schedule management, email processing, task management, information gathering, and reverse engineering support for self-realization. The details are described below.

[1812] Schedule management

[1813] The user enters their schedule from their device. The device sends the entered schedule data to the server. The server uses a "generative AI model" to analyze the received schedule data, optimizing it by eliminating duplication and waste. The optimized schedule is sent to the device, which the user can then review and modify. For example, if a user registers their schedule for the following week, the "generative AI model" might detect a meeting time conflict and suggest moving it to a different, more appropriate time.

[1814] Example prompt message: "I have entered the schedule for next week. Please check for duplicates and inefficiencies and optimize it."

[1815] Email Processing

[1816] The user receives an email on their device. The device sends the received email data to a server. The server analyzes the email content, determining its importance and performing spam filtering. Next, the AI ​​generates an email summary and a suggested reply. The generated summary and reply are sent to the device, where the user reviews and modifies them as needed before sending. For example, when a user receives a large number of emails, the AI ​​model on the server prioritizes important emails and provides templates to facilitate replies.

[1817] Example prompt: "Summarize the received email and generate a draft reply."

[1818] Task management

[1819] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data to determine priorities and dependencies. A generative AI model generates the optimal task order and timeline, and sends the generated task schedule to the device. The user reviews and executes the tasks. For example, when a user enters tasks for a new project, the AI ​​model considers the task dependencies and suggests a natural order and estimated time for each task.

[1820] Example prompt: "I have entered the tasks for this project. Please generate the optimal task order and schedule, taking dependencies and priorities into consideration."

[1821] Information gathering

[1822] The user enters a request for information gathering from their device. The device sends the information gathering request to the server. The server receives the request, and the AI ​​collects information from specific data sources. The collected information is summarized, a report is generated, and sent to the device. The user reviews the report. For example, if a user enters a request for market research, the AI ​​model collects the latest statistical data and trending articles and provides a clearly summarized report.

[1823] Example prompt: "Collect data and trend articles for market research and generate a summarized report."

[1824] Support for reverse planning to achieve self-realization

[1825] The user enters a long-term goal from their device. The device sends the entered long-term goal to the server. The server receives the long-term goal and uses a generating AI model to set annual goals. Furthermore, it breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is sent to the device for the user to review and execute. For example, if the user sets "I will become independent and start my own business in 10 years," the AI ​​model will work backward to determine the necessary steps such as obtaining qualifications, sales activities, and fundraising, and propose a schedule of specific annual, monthly, and weekly tasks.

[1826] Example prompt: "Please create a schedule outlining the steps and plan necessary to start your own business in 10 years."

[1827] This system leverages the power of generative AI to support users in efficiently performing their tasks and achieving long-term goals. HTTP POST is used for communication between the server and the terminal, and data is exchanged in JSON format. Generative AI models play a crucial role in each function, analyzing user input data and providing optimal suggestions to improve productivity.

[1828] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1829] Schedule management

[1830] Step 1:

[1831] The user enters their schedule using a terminal. The entered data is generated in JSON format via the keyboard or touchscreen.

[1832] Step 2:

[1833] The terminal sends the entered schedule data to the server. Specifically, it sends the schedule data in JSON format using an HTTP POST request.

[1834] Step 3:

[1835] The server analyzes the received schedule data. A generative AI model is used for the analysis, performing pattern recognition to eliminate duplication and waste from the data.

[1836] Step 4:

[1837] The server generates an optimized schedule based on the analyzed data. The generated schedule is also converted to JSON format.

[1838] Step 5:

[1839] The server sends an optimized schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1840] Step 6:

[1841] Users can view the optimized schedule on their device and make adjustments as needed. The adjustment data is also saved in JSON format.

[1842] Email Processing

[1843] Step 1:

[1844] The user receives emails using their device. Emails are received via a standard email application.

[1845] Step 2:

[1846] The device sends the received email data to the server. The transmission format is JSON, and it uses an HTTP POST request.

[1847] Step 3:

[1848] The server analyzes the content of the email. A generative AI model is used for the analysis, including determining importance and filtering spam.

[1849] Step 4:

[1850] The server generates an email summary and a draft reply. The generated summary and draft reply are converted into JSON format.

[1851] Step 5:

[1852] The server sends the generated summary and proposed reply to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1853] Step 6:

[1854] The user reviews the summary and proposed reply on their device and makes revisions as needed. The revised reply is then sent via email.

[1855] Task management

[1856] Step 1:

[1857] The user enters a new task using a terminal. The entered data is generated in JSON format.

[1858] Step 2:

[1859] The terminal sends the entered task data to the server. Specifically, it sends the task data in JSON format using an HTTP POST request.

[1860] Step 3:

[1861] The server analyzes the received task data. A generative AI model is used for the analysis to determine task priorities and dependencies.

[1862] Step 4:

[1863] The server generates the optimal task order and timeline based on the analysis results. The generated task schedule is converted to JSON format.

[1864] Step 5:

[1865] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1866] Step 6:

[1867] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[1868] Information gathering

[1869] Step 1:

[1870] The user enters a data collection request using their device. The entered data is generated in JSON format.

[1871] Step 2:

[1872] The device sends an information collection request to the server. The transmission format is JSON, and it uses an HTTP POST request.

[1873] Step 3:

[1874] The server receives a request and uses a generative AI model to collect information from a specific data source. The collected information is obtained from databases or the internet.

[1875] Step 4:

[1876] The server summarizes the collected information and generates a report. The generated report is converted to JSON format.

[1877] Step 5:

[1878] The server sends the generated report to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1879] Step 6:

[1880] The user views the report on their device. The data in the report is modified as needed.

[1881] Support for reverse planning to achieve self-realization

[1882] Step 1:

[1883] The user enters their long-term goals using a device. The entered data is generated in JSON format.

[1884] Step 2:

[1885] The terminal sends the entered long-term goals to the server. The transmission format is JSON, and it uses an HTTP POST request.

[1886] Step 3:

[1887] The server receives the long-term goals and uses a generative AI model to set annual goals. The set goals are then converted into JSON format.

[1888] Step 4:

[1889] The server breaks down the annual goals into monthly and weekly units and converts them into specific tasks. The generated task schedule is then converted into JSON format.

[1890] Step 5:

[1891] The server sends the generated task schedule to the terminal. This also uses an HTTP POST request, and the data is sent in JSON format.

[1892] Step 6:

[1893] Users can check their task schedule on their device and make corrections as needed. The corrected data is also saved in JSON format.

[1894] This allows the system to perform specific data processing and calculations for each function, providing optimized data and thereby improving user productivity.

[1895] (Application Example 1)

[1896] 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".

[1897] In traditional virtual store operations, managing staff schedules, handling customer inquiries via email, and managing tasks were often done manually, resulting in inefficiencies. Furthermore, there was a lack of tools to streamline operations, such as optimizing schedules, promptly addressing important emails, and prioritizing tasks. As a result, operational efficiency declined, placing a burden on store management.

[1898] 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.

[1899] In this invention, the server includes means for the user to input a schedule, means for the terminal to transmit the user's input data to the server, means for the server to analyze the received schedule data, means for optimizing the analyzed schedule data, means for transmitting the optimized schedule to the terminal, means for the user to confirm and modify the optimized schedule, means for optimizing staff schedules in a virtual store, and means for generating prompt statements when optimizing the schedule using a generative AI model. This enables efficient management of staff schedules in a virtual store.

[1900] A "user" is an individual or legal entity that uses the system or terminals to operate and manage a virtual store.

[1901] A "schedule" is a plan of the date, time, and content of events and tasks that the user enters.

[1902] A "device" refers to an input and display device such as a smartphone, tablet, or personal computer used by a user.

[1903] A "server" is a computer system that receives, analyzes, and optimizes data sent by users, and then returns the results to the terminal.

[1904] "Schedule data" refers to information about the schedule entered by the user.

[1905] "Analysis" refers to the process of analyzing schedule data and email data received by a server to extract and evaluate appropriate information.

[1906] "Optimization" refers to the efficient and effective organization and adjustment of schedules and task data.

[1907] A "virtual store" is an online store that provides goods and services via the internet.

[1908] "Staff" refers to the personnel who support the operation of the virtual store.

[1909] A "generative AI model" refers to an artificial intelligence algorithm trained to perform a specific task.

[1910] A "prompt statement" is an instruction given to a generative AI model, containing instructions for obtaining a specific result.

[1911] "Email" refers to messages sent and received electronically, and is used for customer inquiries and internal company communications.

[1912] A "task" refers to the work or tasks that a user is supposed to perform.

[1913] "Priority" refers to the order in which tasks and schedules are arranged based on their importance and urgency.

[1914] "Dependency" refers to a relationship where one task or schedule depends on another task or event.

[1915] A "summary" refers to a concise compilation of key information.

[1916] A "suggested reply" is a proposed response to a message, such as an email.

[1917] This invention is a system that utilizes a generative AI model to streamline daily operations in virtual stores and improve user productivity. This system primarily provides three main functions: schedule management, email processing, and task management. The implementation methods for each function are described below.

[1918] Schedule management

[1919] The user enters the staff schedule for the virtual store using a terminal. This schedule data is sent from the terminal to the server. The server analyzes the received schedule data, eliminating duplication and inefficiencies to optimize it. The optimized schedule is sent back to the terminal for the user to review and modify. At this time, a generation AI model is used to generate prompts for schedule optimization, and the AI ​​is instructed to perform the optimization work.

[1920] Email Processing

[1921] Emails received by the user are received on the device, and the data is sent to the server. The server analyzes the content of the emails, determines their importance, and performs spam filtering. Based on the analyzed content of the emails, AI generates summaries and suggested replies. The generated summaries and suggested replies are sent to the device, where the user reviews and modifies them, and sends them as needed.

[1922] Task management

[1923] When a user enters a new task from their device, the task data is sent to the server. The server analyzes the task data and uses a generative AI model to determine priorities and dependencies, generating an optimal task sequence and timeline. This enables efficient task management. The generated task schedule is sent to the device, where the user can review and execute it.

[1924] Hardware and software used

[1925] Hardware: Servers (e.g., AWS EC2 instances), user devices (smartphones, tablets, PCs)

[1926] Software: Django framework (server-side program), generative AI model (e.g., OpenAI GPT-3)

[1927] Examples of specific cases and prompt statements

[1928] Specific example

[1929] For example, consider a scenario where a store manager inputs staff shift schedules. If different shifts overlap, the server uses a generated AI model to optimize the schedule and suggest the best shift arrangement. Furthermore, when a large volume of customer inquiry emails arrive, the AI ​​generates summaries and suggested replies to support a quick response.

[1930] Example of a prompt

[1931] For schedule optimization: "Optimize this schedule: {'Mon': ['StaffA', 'StaffB'], 'Tue': ['StaffC', 'StaffD'], 'Wed': ['StaffA', 'StaffE']}"

[1932] For email processing: "Summarize and create a reply draft for this email: 'Dear Store, We have an urgent issue regarding our recent order...'"

[1933] Based on the above, the system of the present invention provides a concrete means to streamline daily operations in virtual store management and reduce the workload of users.

[1934] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1935] Step 1:

[1936] The user enters their schedule into the terminal. The terminal receives the entered schedule data and sends it to the server. The input data includes the date and time, event details, and information about the staff in charge. The output is the schedule data sent to the server.

[1937] Step 2:

[1938] The server analyzes the received schedule data. The analysis verifies data integrity and checks for duplication and unnecessary information. The input is the schedule data, and the output is the analysis results.

[1939] Step 3:

[1940] The server optimizes the analyzed schedule data. A generative AI model is used to generate prompts for optimization. These prompts are input to the AI ​​model to obtain the optimal schedule. The input consists of the analysis results and prompts, and the output is the optimized schedule data.

[1941] Step 4:

[1942] The server sends optimized schedule data to the terminal. The terminal displays the received data and prompts the user for confirmation and correction. The input is the optimized schedule data, and the output is the schedule displayed on the terminal.

[1943] Step 5:

[1944] The system reviews the schedule received by the user and makes corrections as needed. The corrected schedule data is then sent back to the server. The input is the user's corrected data, and the output is the corrected schedule data.

[1945] Step 6:

[1946] The user receives an email on their device. The device then sends the received email data to the server. The input is the email data, and the output is the email data sent to the server.

[1947] Step 7:

[1948] The server analyzes received email data, performs importance assessment, and filters out spam. Based on the analysis results, an AI model is used to generate summaries and suggested replies. The input is email data, and the output is summaries and suggested replies.

[1949] Step 8:

[1950] The server sends the generated summary and draft reply to the terminal. The terminal displays it to the user, who then reviews and makes corrections. The input is the summary and draft reply, and the output is the data displayed to the user.

[1951] Step 9:

[1952] The user reviews and corrects the summary and draft reply, then resends them to the server for final delivery. The input is the corrected summary and draft reply, and the output is the sent email.

[1953] Step 10:

[1954] The user enters a new task into the terminal. The terminal sends the entered task data to the server. The input is the task data, and the output is the task data sent to the server.

[1955] Step 11:

[1956] The server analyzes the received task data to determine priorities and dependencies. Based on the analysis results, a generative AI model is used to generate the optimal task order and timeline. The input is task data, and the output is the optimized task order and timeline.

[1957] Step 12:

[1958] The server sends the generated task schedule to the terminal. The terminal displays it to the user, who then reviews and executes the task schedule. The input is the optimized task schedule, and the output is the data displayed to the user.

[1959] Through the steps described above, the present invention provides concrete means for streamlining users' daily operations and supporting virtual store management.

[1960] 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.

[1961] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[1962] Schedule management

[1963] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotions and optimizes the schedule based on those emotions. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the device, and the user can review and modify it.

[1964] Specific example:

[1965] When a user schedules a meeting or client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[1966] Email Processing

[1967] The user receives an email from their device. The device sends the received email data to the server. The server analyzes the email content, and the sentiment engine recognizes the user's emotions to determine importance and perform spam filtering. The AI ​​also generates an email summary and suggested replies, adjusting them based on the user's emotions. For example, if the user is fatigued, a simple reply suggestion might be made. The summary and suggested replies are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[1968] Specific example:

[1969] When a user receives an important email while feeling fatigued, the emotion engine generates a simple and quick response suggestion to reduce the user's burden.

[1970] Task management

[1971] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[1972] Specific example:

[1973] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[1974] Information gathering

[1975] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[1976] Specific example:

[1977] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[1978] Support for reverse planning to achieve self-realization

[1979] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[1980] Specific example:

[1981] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[1982] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[1983] The following describes the processing flow.

[1984] Schedule management processing steps

[1985] Step 1:

[1986] The user enters their schedule from their device. Specifically, they fill in the date, time, and details of the appointment in an input form.

[1987] Step 2:

[1988] The terminal sends user input data to the server. The data is often sent in formats such as JSON or XML.

[1989] Step 3:

[1990] The server analyzes the received schedule data. It checks the data format and performs checks for any discrepancies if necessary.

[1991] Step 4:

[1992] The server uses an emotion engine to recognize the user's current emotions. Specifically, it refers to emotion data previously recorded by the user or real-time emotion input.

[1993] Step 5:

[1994] The server optimizes the schedule data. For example, if a user is feeling stressed, it might add breaks to slow down the pace or adjust the order of important tasks.

[1995] Step 6:

[1996] The server sends an optimized schedule to the terminal.

[1997] Step 7:

[1998] The device notifies the user of an optimized schedule. The user can then review and modify the schedule based on this information.

[1999] Email Processing Steps

[2000] Step 1:

[2001] The user receives an email from their device. A notification appears as a pop-up or alert.

[2002] Step 2:

[2003] The device sends received email data to the server. This data includes information such as the email body, sender, and date / time.

[2004] Step 3:

[2005] The server analyzes the received emails, checking their content and determining their importance or whether they are spam.

[2006] Step 4:

[2007] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's fatigue level and stress level.

[2008] Step 5:

[2009] The server generates email summaries and suggested replies. For example, if the user is tired, it will generate a concise suggested reply.

[2010] Step 6:

[2011] The server sends a summary and a draft reply to the terminal.

[2012] Step 7:

[2013] The device notifies the user of the summary and proposed reply received. The user reviews and modifies the content and sends it as needed.

[2014] Task management processing steps

[2015] Step 1:

[2016] The user enters the task from their device. They fill in the project name and specific task details.

[2017] Step 2:

[2018] The terminal sends the entered task data to the server. The data format used is typically JSON or XML.

[2019] Step 3:

[2020] The server analyzes the received task data. It checks the data format and determines priorities and dependencies.

[2021] Step 4:

[2022] The server uses an emotion engine to recognize the user's emotions. This allows the server to understand the user's energy level and mood.

[2023] Step 5:

[2024] The server generates the optimal order and timeline for tasks, making adjustments based on emotions, such as scheduling important tasks during times of high concentration.

[2025] Step 6:

[2026] The server sends the generated task schedule to the terminal.

[2027] Step 7:

[2028] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[2029] Information gathering processing steps

[2030] Step 1:

[2031] The user enters an information gathering request from their device. They enter the topic, keywords, and purpose they want to investigate.

[2032] Step 2:

[2033] The device sends an information collection request to the server.

[2034] Step 3:

[2035] The server receives the request and uses an emotion engine to recognize the user's emotions.

[2036] Step 4:

[2037] The server collects information from specific data sources. It retrieves necessary information from sources such as news websites and academic journal databases.

[2038] Step 5:

[2039] The server summarizes the collected information and adjusts the report based on the user's emotions. For example, if the user is easily fatigued, a concise summary is generated.

[2040] Step 6:

[2041] The server sends the generated report to the terminal.

[2042] Step 7:

[2043] The device notifies the user of the report it has received. The user reviews the report and takes the necessary action.

[2044] Processing steps for supporting reverse engineering for self-realization

[2045] Step 1:

[2046] The user enters their long-term goals from their device. They enter the goals they want to achieve and the timeframe they have set.

[2047] Step 2:

[2048] The device sends long-term goal data to the server.

[2049] Step 3:

[2050] The server receives the long-term goals and uses an emotion engine to recognize the user's emotions.

[2051] Step 4:

[2052] The server uses AI to work backward and set annual goals. It defines specific steps and milestones.

[2053] Step 5:

[2054] The server breaks down annual goals into monthly and weekly units and converts them into tasks. It also makes adjustments based on emotions.

[2055] Step 6:

[2056] The server sends the generated task schedule to the terminal.

[2057] Step 7:

[2058] The terminal notifies the user of the task schedule it has received. The user reviews the details and then executes the task.

[2059] (Example 2)

[2060] 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".

[2061] Traditional scheduling, email processing, task management, and information gathering systems often fail to consider user emotions, leading to stress and decreased work efficiency. This frequently resulted in users being unable to achieve their full productivity. To address this problem, dynamic adjustments based on user emotional states are required.

[2062] 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.

[2063] In this invention, the server includes means for an emotion engine to recognize the user's emotions, means for optimizing the schedule based on analysis and emotion recognition, and means for adjusting the generated summaries and response suggestions based on the emotions. This enables improved user productivity and reduced stress by making optimal adjustments according to the user's emotional state.

[2064] A "user" refers to a person who uses this system to manage their schedule, process emails, manage tasks, and gather information.

[2065] "Device" refers to electronic devices used by users, such as personal computers, smartphones, and tablets.

[2066] A "server" refers to a computer system that receives data sent from a terminal and performs analysis and optimization.

[2067] An "emotion engine" refers to software or hardware that recognizes a user's emotions and optimizes data based on those recognition results.

[2068] "Schedule data" refers to information about appointments and plans entered by the user.

[2069] "Analysis" refers to the process by which a server processes received data to understand and interpret its content, importance, dependencies, and other relevant information.

[2070] "Optimization" refers to adjusting schedules, task sequences, email summaries, and response drafts more effectively and efficiently based on analyzed data and user sentiment recognition results.

[2071] "Email data" refers to the content of emails received by a user and any accompanying information.

[2072] A "summary" refers to information that has been extracted and concisely compiled from the most important parts of an email or other information gathering results.

[2073] A "draft reply" refers to a suggested text that will be generated as a response to an email.

[2074] "Task data" refers to information about jobs and tasks entered by the user.

[2075] "Priority" refers to the criteria used to determine the order in which tasks and appointments entered by the user are executed, based on factors such as importance and urgency.

[2076] A "dependency" refers to a relationship where one task presupposes the completion of another task.

[2077] A "timeline" refers to a chronological arrangement of tasks and appointments that need to be completed within a specific period.

[2078] "Information gathering" refers to the process of obtaining necessary data from specific sources based on user instructions.

[2079] This invention is a system that combines generative AI and an emotion engine to support users' daily work and self-actualization. This system primarily provides four functions: schedule management, email processing, task management, and information gathering, and further optimizes these functions by recognizing the user's emotions.

[2080] Schedule management

[2081] The user enters their schedule from their device. The device sends the user's input data to the server. The server analyzes the received schedule data, and the emotion engine recognizes the user's current emotions and optimizes the schedule based on those emotions. For example, if the user is feeling stressed, adjustments such as postponing important tasks are made. The optimized schedule is sent to the device, and the user can review and modify it.

[2082] Specific example:

[2083] When a user schedules a meeting or client visit, the emotion engine recognizes the user's stress level and adds relaxation time to the schedule as needed.

[2084] Example of a prompt:

[2085] "I'm entering this week's schedule. There are two important meetings and one client visit. Please adjust the schedule considering the stress level."

[2086] Email Processing

[2087] The user receives an email from their device. The device sends the received email data to the server. The server analyzes the email content, and the sentiment engine recognizes the user's emotions to determine importance and perform spam filtering. The AI ​​also generates an email summary and suggested replies, adjusting them based on the user's emotions. For example, if the user is fatigued, a simple reply suggestion might be made. The summary and suggested replies are sent to the device, where the user reviews and modifies them, and sends them if necessary.

[2088] Specific example:

[2089] When a user receives an important email while feeling fatigued, the emotion engine generates a simple and quick response suggestion to reduce the user's burden.

[2090] Example of a prompt:

[2091] "Please provide a summary of the important email I received today and a draft reply. I am very tired right now, so a brief reply would be appreciated."

[2092] Task management

[2093] The user enters tasks from their device. The device sends the entered task data to the server. The server analyzes the received task data, and the emotion engine recognizes the user's emotions to determine priorities and dependencies. The AI ​​generates the optimal task order and timeline, making adjustments based on the emotions. The generated task schedule is sent to the device for the user to review and execute.

[2094] Specific example:

[2095] When a user enters multiple tasks, the emotion engine assesses the user's current energy level and places more difficult tasks during times when their energy level is highest.

[2096] Example of a prompt:

[2097] "I'll enter today's tasks. These include meeting preparation, report writing, and presentation practice. Please create a schedule in the optimal order, taking my energy level into consideration."

[2098] Information gathering

[2099] The user enters a request for information collection from their device. The device sends the information collection request to the server. The server receives the request, and the emotion engine recognizes the user's emotions and collects information from specific data sources. The AI ​​summarizes the collected information and adjusts the report format based on the user's emotions. The generated report is sent to the device for the user to review.

[2100] Specific example:

[2101] When a user submits a market research request, the emotion engine recognizes the user's fatigue level and provides a concise report in a summarized format when gathering information.

[2102] Example of a prompt:

[2103] "Please gather information on recent market trends. I'm currently exhausted, so I'd prefer a concise summary report."

[2104] Support for reverse planning to achieve self-realization

[2105] The user enters their long-term goal from their device. The server receives the long-term goal, and the emotion engine recognizes the user's emotions. The AI ​​then works backward to set annual goals. The annual goals are also broken down into monthly and weekly units and converted into tasks. The generated task schedule is adjusted based on the user's emotions and sent to the device. The user then reviews and executes the tasks.

[2106] Specific example:

[2107] If a user sets a goal of "starting their own business in 10 years," the emotional engine will take their stress level into consideration and suggest a schedule with some leeway.

[2108] Example of a prompt:

[2109] "My goal is to become independent and start my own business in 10 years. Please create annual, monthly, and weekly plans to achieve this goal, and adjust them to take my stress levels into consideration."

[2110] These features allow users to efficiently manage schedules, process emails, manage tasks, and gather information. Furthermore, the introduction of an emotion engine improves user productivity and reduces stress by taking into account the user's emotional state and making optimal adjustments. This system utilizes generative AI and an emotion engine to provide support optimized for individual situations.

[2111] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2112] Schedule management

[2113] Step 1:

[2114] The user enters their schedule from their device. For example, the user enters appointments for meetings or client visits into their device. This input data includes the date, time, and content of the appointment.

[2115] Step 2:

[2116] The terminal sends the entered schedule data to the server. The entered data is transferred to the server using an HTTP request. This operation constitutes data communication from the terminal to the server.

[2117] Step 3:

[2118] The server analyzes the received schedule data. A natural language processing engine (e.g., spaCy) is used to analyze the data's content. Here, the schedule's content, importance, and deadline are determined. The results of this analysis become the input data for the next processing step.

[2119] Step 4:

[2120] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., IBM Watson Tone Analyzer) is used to evaluate the user's stress level. Past user response data and temporary emotion data are used as input data.

[2121] Step 5:

[2122] The server optimizes the schedule based on analysis and sentiment recognition. An AI model (e.g., GPT-4) is used to make adjustments such as postponing or easing important tasks and inserting relaxation time. The data generated during this optimization process is output as optimized schedule data.

[2123] Step 6:

[2124] The optimized schedule is sent to the device. The final generated optimized schedule data is sent to the device as an HTTP response.

[2125] Step 7:

[2126] Users can review and modify their optimized schedules. Users can check their schedules on their devices and make additional changes or modifications as needed.

[2127] ---

[2128] Email Processing

[2129] Step 1:

[2130] The user receives an email on their device. The user receives a new email through an email client (e.g., Outlook or Gmail).

[2131] Step 2:

[2132] The device sends the received email data to the server. The received email data is sent to the server via an HTTP request.

[2133] Step 3:

[2134] The server analyzes the content of the email. Using a natural language processing engine (e.g., NLTK or spaCy), it analyzes the email content and evaluates the importance of the body and attachments. This result is stored on the server and used as input data for the next processing step.

[2135] Step 4:

[2136] The emotion engine recognizes the user's emotions. An emotion analysis library (e.g., TextBlob) is used to determine the user's emotional state (e.g., fatigue level, stress). The user's past behavior and emotional data are used as input data.

[2137] Step 5:

[2138] The server determines the importance and whether an email is spam. A spam detection algorithm (e.g., Naive Bayes) is used to determine importance and filter out spam. The determination result is used as input data for the next processing step.

[2139] Step 6:

[2140] AI generates and adjusts email summaries and response drafts based on sentiment. Using an AI model (e.g., GPT-4), it generates summary texts and response drafts, and adjusts the wording to match the user's sentiment.

[2141] Step 7:

[2142] The summary and proposed reply are sent to the terminal. The final generated summary and proposed reply are sent to the terminal as an HTTP response.

[2143] Step 8:

[2144] The user reviews the summary and draft reply, makes revisions as needed, and sends it. The user reviews the summary and draft reply on their device, makes revisions as needed, and sends the final email.

[2145] ---

[2146] Task management

[2147] Step 1:

[2148] The user enters tasks from the terminal. The user enters tasks such as "report creation" or "data analysis" into the terminal.

[2149] Step 2:

[2150] The terminal sends the entered task data to the server. The entered task data is sent to the server using an HTTP request.

[2151] Step 3:

[2152] The server analyzes the task data. Using a natural language processing engine (e.g., SpaCy), it analyzes the task content, importance, dependencies, etc. The analysis results become input data for the next processing step.

[2153] Step 4:

[2154] The emotion engine recognizes the user's emotions. It uses an emotion analysis library (e.g., IBM Watson Tone Analyzer) to recognize the user's emotions. Past user response data and temporary emotion data are used as input data.

[2155] Step 5:

[2156] The server determines priorities and dependencies. Based on the analysis results and sentiment recognition results, it determines the priority and dependencies of tasks. This determination becomes the input data for the next processing step.

[2157] Step 6:

[2158] The AI ​​generates and adjusts the optimal task order and timeline based on emotions. Using an AI model (e.g., GPT-4), it generates the optimal task order and timeline and adjusts it to match the user's emotions.

[2159] Step 7:

[2160] The generated task schedule is sent to the terminal. The final task schedule data is sent to the terminal as an HTTP response.

[2161] Step 8:

[2162] The user reviews and executes the task schedule. The user reviews the task schedule generated on their device, makes any necessary modifications, and then proceeds with execution.

[2163] ---

[2164] Information gathering

[2165] Step 1:

[2166] The user enters a request for information gathering from their device. For example, the user enters a request to find out about "recent market trends" into their device.

[2167] Step 2:

[2168] The device sends an information collection request to the server. The information collection request data is sent to the server using an HTTP request.

[2169] Step 3:

[2170] The server receives and analyzes the request. Using a natural language processing engine, it analyzes the request content and identifies the data necessary for information gathering.

[2171] Step 4:

[2172] The emotion engine recognizes the user's emotions. It uses an emotion analysis library to recognize the user's emotional state. Input data includes information related to the user's stress and fatigue levels.

[2173] Step 5:

[2174] The server collects information. It uses web scraping techniques (e.g., Beautiful Soup) to collect the necessary information from the specified data source.

[2175] Step 6:

[2176] The AI ​​summarizes and reframes the collected information based on sentiment. Using an AI model (e.g., GPT-4), it summarizes the collected information and presents it in a format that aligns with the user's emotions.

[2177] Step 7:

[2178] The generated report is sent to the terminal. The final report data is sent to the terminal as an HTTP response.

[2179] Step 8:

[2180] The user reviews the report. The user reviews the report generated on their device and provides feedback as needed.

[2181] ---

[2182] Support for reverse planning to achieve self-realization

[2183] Step 1:

[2184] The user enters their long-term goal from their device. For example, the user might enter the goal "I will become independent and start my own business in 10 years" into their device.

[2185] Step 2:

[2186] The device sends long-term goal data to the server. The long-term goal data is sent to the server using an HTTP request.

[2187] Step 3:

[2188] The server receives and analyzes the data. A natural language processing engine is used to analyze the content of the input long-term goals. The analysis results obtained here are used as input data for the next processing step.

[2189] Step 4:

[2190] The emotion engine recognizes the user's emotions. An emotion analysis library is used to recognize the user's emotional state. Here, the user's stress level and motivation are used as input data.

[2191] Step 5:

[2192] The AI ​​works backward to set annual targets. Using an AI model (e.g., GPT-4), it sets the annual targets necessary to achieve the long-term goal. This backward calculation result is used as input data for the next processing step.

[2193] Step 6:

[2194] The AI ​​breaks down annual goals into monthly and weekly tasks. These generated tasks are then converted into monthly and weekly goals based on the annual plan.

[2195] Step 7:

[2196] The server optimizes generated task schedules based on emotions. It considers the user's emotional state and optimizes the task schedule accordingly. For example, it reduces the workload during periods of high stress.

[2197] Step 8:

[2198] A task schedule optimized for the device is sent. The optimized task schedule is sent to the device as an HTTP response.

[2199] Step 9:

[2200] The user reviews and executes the task schedule. The user reviews the generated task schedule, makes any necessary corrections or adjustments, and then proceeds with execution.

[2201] ---

[2202] This allows users to efficiently manage schedules, tasks, and emails, and gather information. Furthermore, by utilizing an emotion engine, appropriate adjustments are made based on the user's emotional state, resulting in increased productivity and reduced stress.

[2203] (Application Example 2)

[2204] 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".

[2205] Traditional food delivery systems have a problem in that they do not consider the user's emotional state when suggesting dishes or restaurants, thus failing to reduce user stress and improve satisfaction. Furthermore, the ordering process lacks consideration for reducing the user's psychological burden, resulting in an unoptimized user experience. To solve these problems, a system is needed that provides optimal suggestions based on the user's emotional state.

[2206] 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. In this invention, the server includes means for analyzing user input data and optimally adjusting schedules and suggestions using a generative AI and an emotion engine, means for making suggestions and optimizations regarding food delivery based on the user's emotional state, and means for transmitting the suggested and optimized data to a terminal for the user to confirm and modify. This enables optimal food delivery suggestions based on the user's emotional state and an ordering process that reduces psychological burden.

[2207] A "schedule" is a planner that allows users to manage their daily activities and appointments hour by hour.

[2208] A "terminal" refers to an electronic device that a user can operate and use to input and receive information.

[2209] A "server" is a central computer system that processes and manages data over a network.

[2210] "Analysis" is the process of meticulously examining data to find specific information or patterns within it.

[2211] "Generative AI" refers to artificial intelligence that automatically generates new data and information based on user input.

[2212] An "emotion engine" is a technology that recognizes the user's emotional state and provides appropriate responses and suggestions based on those emotions.

[2213] "Optimization" is the process of adjusting to the most effective state or conditions for a specific purpose.

[2214] "Food delivery" is a service where users order food ...

Claims

1. A means for users to input their schedules, A means by which the terminal sends user input data to the server, A means for analyzing the schedule data received by the server, A means for optimizing the analyzed schedule data, A means of sending an optimized schedule to the terminal, A system that includes means for users to review and modify their optimized schedules.

2. The means by which users receive emails, A means of sending email data received by the terminal to the server, The server's means of determining the importance of an email or whether it is spam, A means of generating email summaries and draft replies, A means of sending the generated summary and proposed reply to the terminal, The system according to claim 1, including means for the user to review, revise, and submit a summary or a draft reply.

3. A means for the user to input tasks, A means for the terminal to send the entered task data to the server, A means by which the server analyzes task data and determines priorities and dependencies, A means of generating the optimal task order and timeline, A means of sending the generated task schedule to the terminal, The system according to claim 1, comprising means for the user to check and execute a task schedule.

4. A means for users to input information gathering requests, A means by which a terminal sends a request for information collection to a server, A server is a means of collecting and summarizing information from a specific data source, A means of generating a report of the collected information, A means of sending the generated report to the terminal, The system according to claim 1, comprising means for the user to review the report.

5. A means for users to input long-term goals, A server receives long-term goals and sets annual goals by working backward from them. Methods for breaking down annual goals into monthly and weekly units and converting them into tasks, Send the generated task schedule to the terminal. The system according to claim 1, including means for the user to confirm and perform actions.

Images