System

Abstract

A system is provided.SOLUTION: An information processing apparatus comprising: means for receiving a request content; means for analyzing the received request content using a generation model and extracting a task content; means for automatically setting a priority based on the task content; and means for cooperating with a schedule management apparatus and proposing an execution time of a task based on the priority.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The purpose of this invention is to reduce the complexity of task management for corporate employees and freelance workers and improve their productivity. In Japan in particular, the constant stream of work requests makes it difficult to prioritize and schedule tasks, leading to a decline in productivity. Given this background, there is a demand for a system that can quickly and accurately analyze request content, automatically prioritize tasks, and optimize schedules. [Means for solving the problem]

[0005] The present invention provides a system including a means for receiving request content, a means for analyzing the received request content using a generative model and extracting task content, a means for automatically setting priorities based on the task content, and a means for proposing task execution times based on the priorities in cooperation with a schedule management device. The system further includes a means for automatically modifying the execution schedule to optimize task execution times in cooperation with the schedule management device, and a means for automatically generating and sending questions to the requester when there are inconsistencies or unclear points in the request content, thereby making task management more efficient and improving user productivity.

[0006] An "information processing device" is a device that collects, processes, analyzes, and outputs data, and is used to efficiently perform a specific task.

[0007] The "means for receiving request content" is a means having an interface and communication function for receiving request information from a user in the form of text, image, sound, video, or the like.

[0008] A "generative model" is a model that uses a pre-trained machine learning algorithm to analyze the content of input data and generate results for a specific purpose.

[0009] The "means for analyzing and extracting task content" is a means for analyzing the received request content using a generative model and extracting the necessary task information.

[0010] The "means for automatically setting priority" is a means for evaluating the importance and urgency of each task based on the extracted task information, and automatically determining the execution order.

[0011] A "schedule management device" is a device or system for managing a user's schedule and tasks, and adjusting and recording the execution time of each task.

[0012] The "means for proposing task execution times" is a means for proposing optimal task execution times based on priority.

[0013] The "means for automatically correcting the execution schedule" is a means for automatically readjusting and updating the existing schedule in response to changes or the addition of new tasks, in cooperation with a schedule management device.

[0014] The "means for generating and sending questions" refers to a means for automatically generating additional questions and sending them to the requester when there are unclear points or contradictions in the request content. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention relates to a task management system used by corporate employees and freelancers to improve work efficiency. This system simplifies complex task management by quickly and accurately analyzing requests, automatically prioritizing tasks, and proposing optimal execution times.

[0037] Program Description

[0038] This system starts when the user inputs the request details into the terminal. The user can input the request information in the form of text, images, audio, video, etc. This data is sent to the server.

[0039] The server passes the received data to the generative model and requests it to analyze it. The generative model analyzes the received data and extracts the necessary task information. The analysis results may include detailed task content and additional questions. In this case, the server notifies the user who made the request of the generated questions.

[0040] After obtaining the task information, the server automatically prioritizes the task based on this information. Priority is determined by the task's importance and deadline. Next, the server uses the Google Calendar API to retrieve the user's current schedule. This allows it to suggest the best time to execute the new task while coordinating with existing schedules.

[0041] The proposed schedule is added to the user's Google Calendar and can be viewed on the user's device. The user can review the proposed schedule and make adjustments as necessary. The user then carries out each task according to the confirmed schedule.

[0042] Specific examples

[0043] As an example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to input the request as text, attach any relevant image files, and send it to the server. The server passes this request to a generative model, which analyzes the task content. The analysis results include the task's importance and the necessary materials.

[0044] Based on this information, the server sets the task priority to "high." It then checks the user's schedule using the Google Calendar API and suggests that the task be performed the following morning. The suggested schedule is automatically added to Google Calendar, and the user can view it on their smartphone.

[0045] The user checks the schedule and accepts it if there are no problems. If adjustments are needed, the user manually edits the schedule. Once the schedule is confirmed, the user executes the tasks according to the schedule.

[0046] This system allows users to reduce the time spent on prioritizing tasks and adjusting schedules, allowing them to focus on their core work. By integrating the generative model with the Google Calendar API, task management is automated, significantly improving work efficiency.

[0047] The above is a specific embodiment for carrying out the present invention. By using this system, the productivity of companies and freelance workers can be increased.

[0048] The processing flow will be explained below.

[0049] Step 1:

[0050] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[0051] Step 2:

[0052] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[0053] Step 3:

[0054] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[0055] Step 4:

[0056] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[0057] Step 5:

[0058] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[0059] Step 6:

[0060] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[0061] Step 7:

[0062] Based on the schedule and priorities obtained by the server, the optimal execution time for each task is proposed, and the proposed task execution time is automatically added to the user's schedule.

[0063] Step 8:

[0064] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[0065] Step 9:

[0066] The server monitors the confirmed schedule and has the function of sending reminders when the task execution time approaches, so that users do not forget to execute the task.

[0067] Step 10:

[0068] Tasks are executed according to a schedule determined by the user. Once the task is completed, the user can notify the server of the task completion from their terminal.

[0069] Through these processing steps, users can efficiently manage the entire process from receiving to executing tasks. The automated integration of the generative model and the Google Calendar API enables quick task prioritization and scheduling, improving productivity.

[0070] Example 1

[0071] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0072] In conventional task management systems, task prioritization and schedule adjustments are often done manually, resulting in problems that reduce worker efficiency. Furthermore, when there are unclear points about a request, there is a lack of a way to quickly and accurately address them. This leads to the complexity of task management, waste of time, and hinders work efficiency.

[0073] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0074] In this invention, the server includes: a means for a user to input request details and send them from a terminal; a means for the server to receive the request details, analyze them using a generative AI model, and extract task details; a means for the server to automatically set priorities based on the task details; a means for the server to acquire the user's schedule via a schedule management device and propose task execution times; and a means for reflecting the proposed execution times in the schedule management device so that the user can confirm and adjust them. This automates task priority setting and schedule adjustment, improving work efficiency and reducing the complexity of task management.

[0075] "User" refers to a general user who uses the system to input and manage task requests.

[0076] "Terminal" refers to the device used by the user to input task requests and send them to the server. Examples include smartphones and personal computers.

[0077] "Server" refers to a central computer system that receives and analyzes requests, prioritizes tasks, and manages schedules.

[0078] "Generative AI model" refers to an artificial intelligence model used to analyze received requests and extract task content.

[0079] "Task content" refers to the specific work items extracted from the request content analyzed by the generative AI model.

[0080] "Priority" refers to the execution priority set based on the importance and deadline of a task.

[0081] "Execution time" refers to the specific date, time, and time period when a task should be executed.

[0082] A "schedule management device" refers to a system or application for managing a user's schedule, such as a general calendar application.

[0083] "Request content" refers to the task content and requirements that the user inputs into the system.

[0084] "Question" refers to the content that the generative AI model automatically generates when there is an unclear point in the request content and asks the user for confirmation.

[0085] "Analysis" refers to the process in which the generative AI model deciphers the request received and extracts the necessary task content.

[0086] "Reflecting" refers to the process in which the server adds the proposed execution time to the schedule management device and has the user confirm it.

[0087] This invention relates to a task management system that workers can use to improve their work efficiency. This system simplifies complex task management by quickly and accurately analyzing task requests, automatically setting priorities, and proposing optimal execution times.

[0088] System configuration

[0089] This system is composed of a combination of terminals, a server, and a schedule management device. Terminals are devices used by users to input task requests, and include smartphones and PCs. The server is a central computer system that analyzes the request content, sets task priorities, and manages schedules. The schedule management device is a system or application for managing users' schedules, such as a general calendar application.

[0090] Data Processing Procedures

[0091] The process of this system is as follows.

[0092] A user uses a device to input task requests and transmit the data. The requests can be in the form of text, images, audio, or video. For example, a user may input details about a new marketing project and attach images of related materials. After input, the data is transmitted from the device to the server.

[0093] The server receives the data sent by the user and then has the generative AI model analyze the request. The generative AI model analyzes the received request and extracts the task details. Based on the analysis results, the server automatically sets the priority of the task. At this time, the priority is set to "high," "medium," or "low" based on the importance and deadline of the task.

[0094] The server also obtains the user's current schedule through the schedule management device, allowing it to suggest the best time to execute a new task. For example, the server may check the user's schedule using the Google Calendar API and suggest executing the task in the morning of the following day.

[0095] The proposed schedule is automatically added to the schedule management device and can be viewed by the user through their terminal. The user can check the schedule and make adjustments as necessary. Once the schedule is confirmed, the user can carry out tasks according to the schedule.

[0096] Specific examples

[0097] A specific scenario is shown below.

[0098] During a meeting, a user is verbally requested to complete a new marketing task. The user then uses their smartphone to type the request into text, attaching any related image files, and submitting it to the server.

[0099] The server receives the request and sends a prompt to the generative AI model, such as, "Your task is to create a marketing strategy for a new product. The image below contains detailed information." The generative AI model then responds with an analysis result, such as, "The key points are based on the graphs in the document. Additional materials are also required."

[0100] Based on the analysis results, the server sets the task priority to "high" and checks the user's schedule using the Google Calendar API. The optimal execution time is suggested as the morning of the following day. The suggested schedule is automatically added to Google Calendar for the user to view.

[0101] The user checks the schedule and accepts it if there are no problems, or manually adjusts it if there are any overlapping schedules. Once the schedule is confirmed, the user executes the task according to the specified time.

[0102] This system significantly reduces the time required for setting task priorities and adjusting schedules, thereby improving work efficiency. In addition, by linking the generative AI model with the schedule management device, task management is automated, allowing users to focus on their primary work.

[0103] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0104] Step 1:

[0105] The user inputs the request details.

[0106] Specific operation: The user operates a device (smartphone or PC) to input the task request details. The input format can be text, images, audio, video, etc.

[0107] Input: Marketing project request details and image files of related materials.

[0108] Output: The input request data.

[0109] Step 2:

[0110] The terminal sends the request to the server.

[0111] Specific operation: When the user presses the input completion button, the terminal sends the request content data to the server.

[0112] Input: The requested data entered.

[0113] Output: The request data sent to the server.

[0114] Step 3:

[0115] The server receives the request and asks the generative AI model to analyze it.

[0116] Specific operation: The server processes the request content data received from the terminal, creates a prompt sentence for analyzing the request content, and sends it to the generative AI model.

[0117] Input: The request data sent to the server.

[0118] Output: A prompt to the generative AI model to analyze.

[0119] Step 4:

[0120] The generative AI model analyzes the request and extracts the task content.

[0121] Specific operation: The generative AI model receives the prompt, analyzes the input request, and extracts the necessary task information.

[0122] Input: A prompt to request the generative AI model to analyze.

[0123] Output: Analysis results including task content (e.g., task details and follow-up questions).

[0124] Step 5:

[0125] The server sets the priority of the tasks based on the analysis results.

[0126] Specific operation: Based on the analysis results obtained from the generative AI model, the server sets priorities based on task importance and deadlines.

[0127] Input: Analysis results of the generative AI model.

[0128] Output: The priority of the task (e.g. "High", "Medium", "Low").

[0129] Step 6:

[0130] The server obtains the user's current schedule from the schedule management device.

[0131] Specific operation: The server uses a schedule management API (e.g., Google Calendar API) to obtain the user's current schedule information.

[0132] Input: User authentication information and schedule management device API.

[0133] Output: The user's current schedule data.

[0134] Step 7:

[0135] The server suggests the best time to execute the task.

[0136] Specific operation: The server calculates and proposes the optimal task execution time based on the acquired schedule data and task priority.

[0137] Input: Task priority and user schedule data.

[0138] Output: Proposed task execution time.

[0139] Step 8:

[0140] The proposed execution time is reflected in the schedule management device.

[0141] Specific operation: The server adds the proposed task execution time to the schedule management device.

[0142] Input: Proposed task execution time.

[0143] Output: New scheduled tasks added to the scheduler.

[0144] Step 9:

[0145] The user reviews the schedule and adjusts it as needed.

[0146] Specific operation: The user checks the task execution time proposed by the schedule management device through the terminal and manually adjusts the time if necessary.

[0147] Input: A new scheduled task added to the schedule management device.

[0148] Output: The confirmed task execution time, or the task execution time adjusted by the user.

[0149] Step 10:

[0150] Execute tasks according to a schedule established by the user.

[0151] Specific Action: The user starts and executes a task at a specified time based on a fixed schedule.

[0152] Input: The confirmed task execution time.

[0153] Output: Completed tasks and their progress reports.

[0154] This concludes the detailed explanation of each processing step in the program for this system. This system allows users to significantly reduce the time it takes to set task priorities and adjust schedules, thereby improving work efficiency.

[0155] (Application example 1)

[0156] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0157] In today's factories, multiple processes are carried out simultaneously, making scheduling and prioritization complicated and difficult to manage efficiently. Furthermore, if factory equipment is not operated at the appropriate time, unnecessary waiting time and process delays occur, resulting in reduced production efficiency and increased operating costs.

[0158] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0159] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for linking with a schedule management device and proposing task execution times based on the priorities, and means for optimizing the schedule of work processes in the factory and controlling the operation of factory work equipment, thereby enabling automatic adjustment of schedules and efficient task management in the factory production process.

[0160] The "means for receiving the request content" is a device or function that takes in the request information such as text, images, audio, and video received from the user.

[0161] A "generative model" is a type of artificial intelligence algorithm used to analyze input data and extract specific information.

[0162] The "means for extracting task content" is a device or function that uses a generative model to identify a specific task and its details from the received request content.

[0163] The "means for automatically setting priorities" is a device or function that evaluates the importance and deadlines based on the extracted task contents and automatically determines the priority of the work.

[0164] A "schedule management device" is a device or system that manages the start and end times of tasks and appropriately adjusts a user's schedule.

[0165] "Means for optimizing the schedule of work processes in a factory and controlling the operation of factory work equipment" refers to a device or function that automatically controls the operation of factory work equipment to optimize the timing of each work process in a factory and efficiently carry out work.

[0166] To implement the present invention, an information processing system is required to efficiently manage factory work processes and their schedules. This system receives requests, analyzes them using a generative model, sets priorities based on the analysis, and works in conjunction with a schedule management device to optimize the operation of factory work equipment.

[0167] First, the user inputs the request details from their device. This request is input in the form of text, images, audio, video, etc., and sent to the server. The server then passes the received request details to the generative AI model and requests that it be analyzed. The generative AI model analyzes the request details and extracts the task details. The extracted task details include the task priority and required operation information.

[0168] Next, the server automatically sets priorities based on the extracted task content. These priorities are determined by the task's importance and deadline. Furthermore, the server works with a schedule management device to suggest optimal execution times. In this process, the server uses existing schedule management software, such as the Google Calendar API, to obtain the user's current schedule and adjust the optimal execution time for the new task.

[0169] The proposed schedule is added to the user's schedule management device and can be viewed by the user via a terminal. The user can review the proposed schedule and make adjustments as necessary. Factory equipment is automatically operated at the specified times according to the confirmed schedule. This operation is used, for example, for parts assembly and inspection work on a factory line.

[0170] As a concrete example, consider a scenario in which a factory worker is requested to perform a new task. The worker uses a tablet device to enter the request details as text, attach any relevant image files, and send it to the server. The server then uses a generative AI model to analyze the request and extract the task's importance and required materials. Based on the extracted information, the server sets the task's priority to "high," checks the worker's schedule using the Google Calendar API, and proposes that the task be completed the following morning. The proposed schedule is automatically added to Google Calendar and can be viewed by the worker on their tablet.

[0171] This system allows the factory's work processes to proceed smoothly and significantly reduces the time required for task prioritization and schedule management. An example of a prompt that a user might use when inputting their request into the system would be, "I'm requesting assembly work for a new part. I've attached a related image. It's of high importance." In this way, it is possible to significantly improve the factory's production efficiency.

[0172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0173] Step 1:

[0174] The user uses a terminal to input the request content. The request content can be input in the form of text, image, audio, video, etc. The input data is formatted appropriately according to the format and sent to the server. Input: Request content (text, image, audio, video) Output: Formatted request data

[0175] Specific operation: For example, the user inputs text and an image from a tablet device, such as "I would like to request assembly work for a new part. I have attached a related image." Then, the user presses the send button to send the data to the server.

[0176] Step 2:

[0177] The server sends the received request to the generative AI model and requests it to analyze it. The generative AI model analyzes the data and extracts the necessary task information. Input: Formatted request data Output: Detailed task information (e.g., task content, priority)

[0178] How it works: The server sends the formatted request data to the analysis API endpoint, and the generative AI model analyzes it. For example, it can obtain an analysis result such as "This image shows the assembly work of part A."

[0179] Step 3:

[0180] The server automatically sets task priorities based on detailed task information obtained from the generated AI model. Input: Detailed task information Output: Prioritized task data

[0181] Specific operation: The server evaluates the analysis results and sets priorities based on the importance and urgency of the tasks. For example, tasks that are judged to be of high importance are set to "High."

[0182] Step 4:

[0183] The server works with a schedule management device (e.g., Google Calendar API) to obtain the user's current schedule and propose new task execution times. Input: prioritized task data, user's current schedule. Output: proposed execution schedule.

[0184] Specific operation: The server uses the Google Calendar API to obtain the user's current schedule. Then, based on the priority, it selects an available time slot and suggests a time to execute the task. For example, it suggests executing the task in the morning of the following day.

[0185] Step 5:

[0186] The server adds the proposed schedule to the user's schedule management device, allowing the user to view it through their device. Input: Proposed execution schedule Output: Schedule added to the user's Google Calendar

[0187] Specific operation: The server sends an API request to add the proposed task schedule to Google Calendar. The schedule is displayed on the calendar in a format that the user can view on a tablet or other device.

[0188] Step 6:

[0189] The user confirms the proposed schedule. If necessary, the user can adjust the schedule. Input: Schedule added to Google Calendar Output: Schedule confirmed by the user

[0190] What happens: The user opens Google Calendar on their device, reviews the proposed task schedule, and, if necessary, changes or adjusts the schedule and finally confirms it.

[0191] Step 7:

[0192] Factory equipment is automatically operated at the specified time according to the confirmed schedule. Input: Confirmed schedule Output: Work execution status

[0193] Specific operation: Factory equipment automatically starts work based on the confirmed schedule. For example, assembly work for part A starts and finishes at the specified time.

[0194] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0195] This invention relates to a task management system that helps corporate employees and freelancers improve their work efficiency. In particular, it is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[0196] Program Description

[0197] This system starts with the user inputting the request details from the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is then sent from the terminal to the server.

[0198] The server temporarily stores the received data and sends it to the generative model for analysis. The generative model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[0199] The server then utilizes an emotion engine to recognize the user's emotional state. The emotion engine identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[0200] The server then uses the Google Calendar API to retrieve the user's current schedule, and, taking into account the priority and the user's emotional state, suggests the optimal time to execute the task and automatically adds it to the Google Calendar.

[0201] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[0202] Specific examples

[0203] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to type the request as text, attach any relevant image files, and send it to a server. The server then passes the request to a generative model, which analyzes the task. The user's emotional state (e.g., stress, anxiety, etc.) is also analyzed along with the analysis results.

[0204] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[0205] The proposed schedule is automatically added to Google Calendar and can be viewed by the user on their smartphone. The user can review the schedule and accept it if there are no problems, or manually adjust it if necessary. Once the schedule is confirmed, the user can carry out the tasks according to the schedule.

[0206] In this way, by combining the emotion engine, task management that takes into account the user's emotional state becomes possible, realizing more efficient and user-friendly task management. By linking the generative model with the Google Calendar API, task prioritization and schedule adjustment can be performed quickly, improving productivity.

[0207] The processing flow will be explained below.

[0208] Step 1:

[0209] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[0210] Step 2:

[0211] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[0212] Step 3:

[0213] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[0214] Step 4:

[0215] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[0216] Step 5:

[0217] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[0218] Step 6:

[0219] The server analyzes the user's emotional state using an emotion engine, which analyzes the user's input data and real-time feedback to identify the user's emotions.

[0220] Step 7:

[0221] The server adjusts task priorities and suggested execution times as needed based on the user's emotional state. For example, if the user is feeling stressed, the schedule is adjusted to avoid those times.

[0222] Step 8:

[0223] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[0224] Step 9:

[0225] The server takes into account the user's schedule, priorities, and emotional state to suggest the optimal execution time for each task. The suggested execution times are automatically added to the user's Google Calendar.

[0226] Step 10:

[0227] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[0228] Step 11:

[0229] The server monitors the schedule and sends reminders when the task is about to be performed, helping users remember to perform the task.

[0230] Step 12:

[0231] Tasks are executed according to a schedule determined by the user. When a task is completed, the user can notify the server of the completion of the task from the terminal.

[0232] In this way, taking into account the user's emotional state enables more adaptive and efficient task management. By combining a generative model, an emotion engine, and the Google Calendar API, this system can improve the user's overall work efficiency.

[0233] Example 2

[0234] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0235] In conventional task management systems, task prioritization and schedule adjustments are performed without taking the user's emotional state into consideration, which often leads to problems such as stress and reduced efficiency. Furthermore, there is no automated response when the request content is unclear, which increases the burden on the user.

[0236] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0237] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for analyzing the user's emotional state using an emotion recognition engine, means for adjusting task priorities and execution times based on the user's emotional state, and means for working in conjunction with a schedule management device to suggest task execution times based on the priorities and emotional state. This allows task prioritization and schedule adjustment to be performed automatically and optimally while taking the user's emotional state into consideration, thereby improving work efficiency and reducing stress.

[0238] "Request content" refers to input data that includes specific information and instructions that a user needs to perform a job or task.

[0239] A "generative model" is an algorithm or system that uses artificial intelligence technology to analyze received requests and extract task content.

[0240] "Task content" refers to the specific work or processing items that the user must perform, extracted from the request content.

[0241] "Priority" is an evaluation criterion that determines the order and importance of execution based on the importance and urgency of the task content.

[0242] An "emotion recognition engine" is a system or algorithm that analyzes a user's emotional state from input data and real-time feedback.

[0243] "User's emotional state" refers to the user's psychological state and emotions analyzed by the emotion recognition engine.

[0244] A "schedule management device" is an external system or application for managing task execution times and schedules.

[0245] A "task execution time" is a specific time period allotted to a user to perform a particular task.

[0246] This invention relates to a task management system for improving the work efficiency of corporate employees and freelance workers. It is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[0247] The program for this system starts with the user inputting the request details on the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is sent from the terminal to the server.

[0248] The server temporarily stores the received data and sends it to the generative AI model for analysis. The generative AI model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[0249] The server then utilizes an emotion recognition engine to recognize the user's emotional state, which identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[0250] The server then uses the schedule management device's API to obtain the user's current schedule, and, taking into account the priority and the user's emotional state, proposes optimal task execution times and automatically adds them to the schedule management device.

[0251] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[0252] Specific examples

[0253] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. Using their smartphone, the user types the request as text and attaches any relevant image files, sending it to a server. The server then passes the request to a generative AI model, which analyzes the task. The user's emotional state (e.g., stress or anxiety) is also analyzed along with the analysis results.

[0254] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[0255] The proposed schedule is automatically added to the schedule management device and becomes available for the user to view on their smartphone. The user reviews the schedule and, if there are no particular problems, accepts it as is, making manual adjustments as necessary. Once the schedule is finalized, the user carries out tasks according to the schedule. In this way, combining an emotion recognition engine enables task management that takes the user's emotional state into account, resulting in even more efficient and user-friendly task management.

[0256] An example prompt is:

[0257] "User entered text:

[0258] I want to schedule a meeting for new project X next Monday at 3 PM. Please review the relevant materials and set the priority to high. Also, analyze the user's emotional state and adjust the schedule if necessary."

[0259] The above system utilizes a generative AI model and an emotion recognition engine to not only improve the efficiency of task management for users but also reduce emotional burden, thereby increasing work productivity.

[0260] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0261] Step 1:

[0262] The user enters the request details

[0263] Specific operation: The user uses their device (smartphone, tablet, PC) to input the details of a new task request. Input formats include text, audio, images, and video. Specifically, the user enters text such as "Create materials for Project X" and attaches the relevant PDF file.

[0264] Input: Request details entered by the user (text, audio, images, videos, etc.) and attachments

[0265] Output: The requested data and attached files are sent from the device to the server.

[0266] Step 2:

[0267] The device sends data to the server, and the server stores the data.

[0268] Specific operation: The terminal sends the input request and attached file to the server. The server receives this data and temporarily stores it in a database.

[0269] Input: Request content and attachments sent from the device

[0270] Output: The request details and attachments are saved in the database.

[0271] Step 3:

[0272] The server requests the generated AI model to analyze the data.

[0273] Specific operation: The server passes the saved request content and attachments to the generative AI model and requests text analysis. The generative AI model analyzes the request text and attachments and extracts specific task information.

[0274] Input: Saved request and attachments

[0275] Output: Parsed task content

[0276] Step 4:

[0277] The server sets the priority of the task

[0278] Specific operation: The server sets the priority of tasks based on the analysis results from the generative AI model. In doing so, it considers the urgency, importance, deadline, etc. of the task and determines it as "high priority."

[0279] Input: Analysis results from a generative AI model

[0280] Output: Prioritized task information

[0281] Step 5:

[0282] The server uses an emotion recognition engine to analyze the user's emotional state.

[0283] Specific operation: The server analyzes the user's latest input data and real-time feedback using an emotion recognition engine. For example, using the text entered by the user and real-time facial expression images, the emotion recognition engine determines that the user is feeling stressed.

[0284] Input: Latest user input data and real-time feedback

[0285] Output: Parsed user's emotional state

[0286] Step 6:

[0287] The server adjusts task priorities and execution times

[0288] Specific operation: The server receives the results of the emotion recognition engine, considers the user's stress level, and adjusts the task priority and execution time. Specifically, it suggests execution times that avoid high-stress times.

[0289] Input: Emotion recognition engine results, prioritized task information

[0290] Output: Adjusted task priorities and execution times

[0291] Step 7:

[0292] The server automatically adds a schedule using the schedule management device's API.

[0293] Specific operation: The server uses the schedule management device's API to obtain the user's current schedule. Based on the obtained schedule, the server automatically adds the optimal time slot to the schedule management device, taking into account task priority and emotional state.

[0294] Input: User's current schedule, adjusted task priority and execution time

[0295] Output: The proposed task execution times are automatically added to the scheduler.

[0296] Step 8:

[0297] User reviews proposed schedule and adjusts as needed

[0298] Specific operation: The user checks the proposed schedule on the device. For example, they open a schedule management app on their smartphone and see that "Create materials for Project X" has been added. They can manually adjust the time as needed.

[0299] Input: Schedule information provided by the server

[0300] Output: Schedule approved and adjusted by user

[0301] Step 9:

[0302] The server sends the reminder

[0303] Specific operation: The server sends a reminder to the user when the task execution time approaches. Specifically, a push notification is displayed on the smartphone saying, "Please start creating materials for Project X."

[0304] Input: Confirmed schedule information

[0305] Output: Reminder notification sent to user

[0306] Step 10:

[0307] A user performs a task

[0308] Specific behavior: After receiving the reminder, the user starts and completes the task according to the confirmed schedule. For example, according to the schedule management app, the user starts preparing documents and completes the task at the specified time.

[0309] Input: Reminder sent

[0310] Output: Completed tasks

[0311] (Application example 2)

[0312] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0313] Conventional factory task management relies on manual work and human judgment, making it difficult to efficiently prioritize tasks and optimize execution schedules. Furthermore, task management does not take into account the emotional state of workers, resulting in increased worker fatigue and stress and reduced productivity. The purpose of this invention is to solve these problems and provide a more effective and user-friendly task management system.

[0314] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for recognizing emotional states and managing tasks based on that information, and means for working with a schedule management device to propose task execution times based on the priorities and emotional states. This improves work efficiency in factories and enables flexible task management that takes into account the emotional states of workers.

[0315] The "request content" is information that requests or instructs the execution of a task, and is provided in the form of text, audio, images, video, or the like.

[0316] A "generative model" is a model that uses machine learning and artificial intelligence techniques to analyze data and extract useful information.

[0317] "Task content" refers to the details and necessary information of a specific task or process extracted from the analysis results of the request content.

[0318] "Priority" is a criterion for determining the execution priority of a task relative to other tasks based on the importance and urgency of the task.

[0319] "Emotional state" refers to the user's psychological or physiological emotional state, including stress, fatigue, and the like.

[0320] "Task management" refers to activities that support the effective execution of tasks, such as planning, prioritizing, scheduling, and progress management of tasks.

[0321] A "schedule management device" is a device or system for recording, adjusting, and managing task execution times.

[0322] In order to put this invention into practice, it is first necessary to build a system in which a server, a terminal, and a user work in cooperation with each other.

[0323] The server includes the following means:

[0324] 1. Method of receiving request content: The user inputs the task request content from a device such as a smartphone, smart glasses, or head-mounted display. The input format can be a variety of formats, including text, audio, images, and video. The request content is sent from the device to the server.

[0325] 2. Generative model analysis: The server temporarily stores the received request and sends it to the generative model (machine learning model) for analysis. Here, the task content and necessary information are extracted, and the next step is taken based on the results.

[0326] 3. Priority setting method: Priorities are automatically set based on the importance and urgency of tasks. This priority setting is performed using an evaluation algorithm that runs on the server.

[0327] 4. Emotional state recognition: The emotion engine recognizes the user's emotional state by analyzing the user's input data and real-time feedback. If the user is in a stressful state, the priority is adjusted.

[0328] 5. Schedule suggestion method: Works with schedule management devices (such as Google Calendar API) to suggest optimal task execution times. Schedules based on priorities and emotional state are automatically added to the calendar.

[0329] The terminal has the following features:

[0330] 1. Task input interface: Provides an interface for users to input task requests. This can be a smartphone, smart glasses, or a head-mounted display.

[0331] 2. Schedule Review Interface: Includes an interface that allows the user to review the proposed schedule and manually adjust it if necessary.

[0332] The user does the following:

[0333] 1. Task request: The user inputs the task request details using the terminal, which are then sent to the server.

[0334] 2. Providing feedback: Providing feedback on the execution of schedules and tasks generated by the server.

[0335] As a concrete example, consider a scenario in which a factory worker is asked to perform "maintenance work on a new machine" using smart glasses. In this case, the worker inputs the task details by voice through the smart glasses. The voice data is sent to the server, and the task details are analyzed by a generative model. Next, an emotion engine checks the worker's emotional state, and if the worker is feeling stressed, the priority is adjusted based on that information. Finally, the optimal execution time is suggested using the Google Calendar API and displayed on the smart glasses.

[0336] Example prompt sentence:

[0337] "I've been asked to carry out maintenance work on a new machine. The details are to check the inspection list and related manuals."

[0338] In this way, combining a generative AI model with an emotion engine enables more efficient and flexible task management than conventional task management systems.

[0339] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0340] Step 1:

[0341] The user uses a device to input the task request. The input can be text, voice, image, or video. For example, a user can use smart glasses to input voice input such as "Request maintenance work on a new machine." This request is then sent from the device to the server.

[0342] Step 2:

[0343] The server temporarily stores the received request (voice data). It then sends the request to the generative AI model, requesting it to analyze the task content. The generative AI model analyzes the voice data, extracts the necessary information, and returns it to the server as the task content. Input: Request content (voice data), Output: Task content (analysis results)

[0344] Step 3:

[0345] The server evaluates the importance and urgency of the tasks based on the task content obtained from the generative AI model, and automatically sets priorities. Priority is set using an algorithm that takes into account the importance and urgency of the task content, resource usage, etc. Input: Task content (analysis results), Output: Priority

[0346] Step 4:

[0347] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's emotional state (stress, etc.) from the voice data and returns the results to the server. Input: Request content (voice data), Output: Emotional state (analysis results)

[0348] Step 5:

[0349] The server works with a schedule management device (such as Google Calendar API) based on the priority and emotional state to propose the optimal task execution time. Here, a time period with high priority and when the user is not feeling stressed is selected and added to the Google Calendar as a schedule. Input: Priority, emotional state, Output: Proposed execution time (schedule)

[0350] Step 6:

[0351] The user uses the device to check the proposed schedule. The schedule is displayed through the smart glasses, and the user manually adjusts it as needed. Once the user approves the schedule, the server confirms it and begins monitoring. Input: Proposed execution time (schedule), Output: Confirmed schedule

[0352] Step 7:

[0353] The server monitors the confirmed schedule and sends reminders when the task execution time approaches. The reminders are sent to the terminal, and the user executes the task according to the confirmed schedule. Input: Confirmed schedule, Output: Reminder notification

[0354] In this way, the entire process from inputting the request details to finalizing the schedule and executing the task becomes clear at each step. This improves work efficiency in the factory and enables flexible task management that takes into account the emotional state of the user.

[0355] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0356] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0357] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0358] [Second embodiment]

[0359] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0360] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0361] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0362] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0363] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0364] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0365] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0366] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0367] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0368] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0369] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0370] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0371] This invention relates to a task management system used by corporate employees and freelancers to improve work efficiency. This system simplifies complex task management by quickly and accurately analyzing requests, automatically prioritizing tasks, and proposing optimal execution times.

[0372] Program Description

[0373] This system starts when the user inputs the request details into the terminal. The user can input the request information in the form of text, images, audio, video, etc. This data is sent to the server.

[0374] The server passes the received data to the generative model and requests it to analyze it. The generative model analyzes the received data and extracts the necessary task information. The analysis results may include detailed task content and additional questions. In this case, the server notifies the user who made the request of the generated questions.

[0375] After obtaining the task information, the server automatically prioritizes the task based on this information. Priority is determined by the task's importance and deadline. Next, the server uses the Google Calendar API to retrieve the user's current schedule. This allows it to suggest the best time to execute the new task while coordinating with existing schedules.

[0376] The proposed schedule is added to the user's Google Calendar and can be viewed on the user's device. The user can review the proposed schedule and make adjustments as necessary. The user then carries out each task according to the confirmed schedule.

[0377] Specific examples

[0378] As an example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to input the request as text, attach any relevant image files, and send it to the server. The server passes this request to a generative model, which analyzes the task content. The analysis results include the task's importance and the necessary materials.

[0379] Based on this information, the server sets the task priority to "high." It then checks the user's schedule using the Google Calendar API and suggests that the task be performed the following morning. The suggested schedule is automatically added to Google Calendar, and the user can view it on their smartphone.

[0380] The user checks the schedule and accepts it if there are no problems. If adjustments are needed, the user manually edits the schedule. Once the schedule is confirmed, the user executes the tasks according to the schedule.

[0381] This system allows users to reduce the time spent on prioritizing tasks and adjusting schedules, allowing them to focus on their core work. By integrating the generative model with the Google Calendar API, task management is automated, significantly improving work efficiency.

[0382] The above is a specific embodiment for carrying out the present invention. By using this system, the productivity of companies and freelance workers can be increased.

[0383] The processing flow will be explained below.

[0384] Step 1:

[0385] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[0386] Step 2:

[0387] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[0388] Step 3:

[0389] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[0390] Step 4:

[0391] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[0392] Step 5:

[0393] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[0394] Step 6:

[0395] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[0396] Step 7:

[0397] Based on the schedule and priorities obtained by the server, the optimal execution time for each task is proposed, and the proposed task execution time is automatically added to the user's schedule.

[0398] Step 8:

[0399] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[0400] Step 9:

[0401] The server monitors the confirmed schedule and has the function of sending reminders when the task execution time approaches, so that users do not forget to execute the task.

[0402] Step 10:

[0403] Tasks are executed according to a schedule determined by the user. Once the task is completed, the user can notify the server of the task completion from their terminal.

[0404] Through these processing steps, users can efficiently manage the entire process from receiving to executing tasks. The automated integration of the generative model and the Google Calendar API enables quick task prioritization and scheduling, improving productivity.

[0405] Example 1

[0406] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0407] In conventional task management systems, task prioritization and schedule adjustments are often done manually, resulting in problems that reduce worker efficiency. Furthermore, when there are unclear points about a request, there is a lack of a way to quickly and accurately address them. This leads to the complexity of task management, waste of time, and hinders work efficiency.

[0408] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0409] In this invention, the server includes: a means for a user to input request details and send them from a terminal; a means for the server to receive the request details, analyze them using a generative AI model, and extract task details; a means for the server to automatically set priorities based on the task details; a means for the server to acquire the user's schedule via a schedule management device and propose task execution times; and a means for reflecting the proposed execution times in the schedule management device so that the user can confirm and adjust them. This automates task priority setting and schedule adjustment, improving work efficiency and reducing the complexity of task management.

[0410] "User" refers to a general user who uses the system to input and manage task requests.

[0411] "Terminal" refers to the device used by the user to input task requests and send them to the server. Examples include smartphones and personal computers.

[0412] "Server" refers to a central computer system that receives and analyzes requests, prioritizes tasks, and manages schedules.

[0413] "Generative AI model" refers to an artificial intelligence model used to analyze received requests and extract task content.

[0414] "Task content" refers to the specific work items extracted from the request content analyzed by the generative AI model.

[0415] "Priority" refers to the execution priority set based on the importance and deadline of a task.

[0416] "Execution time" refers to the specific date, time, and time period when a task should be executed.

[0417] A "schedule management device" refers to a system or application for managing a user's schedule, such as a general calendar application.

[0418] "Request content" refers to the task content and requirements that the user inputs into the system.

[0419] "Question" refers to the content that the generative AI model automatically generates when there is an unclear point in the request content and asks the user for confirmation.

[0420] "Analysis" refers to the process in which the generative AI model deciphers the request received and extracts the necessary task content.

[0421] "Reflecting" refers to the process in which the server adds the proposed execution time to the schedule management device and has the user confirm it.

[0422] This invention relates to a task management system that workers can use to improve their work efficiency. This system simplifies complex task management by quickly and accurately analyzing task requests, automatically setting priorities, and proposing optimal execution times.

[0423] System configuration

[0424] This system is composed of a combination of terminals, a server, and a schedule management device. Terminals are devices used by users to input task requests, and include smartphones and PCs. The server is a central computer system that analyzes the request content, sets task priorities, and manages schedules. The schedule management device is a system or application for managing users' schedules, such as a general calendar application.

[0425] Data Processing Procedures

[0426] The process of this system is as follows.

[0427] A user uses a device to input task requests and transmit the data. The requests can be in the form of text, images, audio, or video. For example, a user may input details about a new marketing project and attach images of related materials. After input, the data is transmitted from the device to the server.

[0428] The server receives the data sent by the user and then has the generative AI model analyze the request. The generative AI model analyzes the received request and extracts the task details. Based on the analysis results, the server automatically sets the priority of the task. At this time, the priority is set to "high," "medium," or "low" based on the importance and deadline of the task.

[0429] The server also obtains the user's current schedule through the schedule management device, allowing it to suggest the best time to execute a new task. For example, the server may check the user's schedule using the Google Calendar API and suggest executing the task in the morning of the following day.

[0430] The proposed schedule is automatically added to the schedule management device and can be viewed by the user through their terminal. The user can check the schedule and make adjustments as necessary. Once the schedule is confirmed, the user can carry out tasks according to the schedule.

[0431] Specific examples

[0432] A specific scenario is shown below.

[0433] During a meeting, a user is verbally requested to complete a new marketing task. The user then uses their smartphone to type the request into text, attaching any related image files, and submitting it to the server.

[0434] The server receives the request and sends a prompt to the generative AI model, such as, "Your task is to create a marketing strategy for a new product. The image below contains detailed information." The generative AI model then responds with an analysis result, such as, "The key points are based on the graphs in the document. Additional materials are also required."

[0435] Based on the analysis results, the server sets the task priority to "high" and checks the user's schedule using the Google Calendar API. The optimal execution time is suggested as the morning of the following day. The suggested schedule is automatically added to Google Calendar for the user to view.

[0436] The user checks the schedule and accepts it if there are no problems, or manually adjusts it if there are any overlapping schedules. Once the schedule is confirmed, the user executes the task according to the specified time.

[0437] This system significantly reduces the time required for setting task priorities and adjusting schedules, thereby improving work efficiency. In addition, by linking the generative AI model with the schedule management device, task management is automated, allowing users to focus on their primary work.

[0438] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0439] Step 1:

[0440] The user inputs the request details.

[0441] Specific operation: The user operates a device (smartphone or PC) to input the task request details. The input format can be text, images, audio, video, etc.

[0442] Input: Marketing project request details and image files of related materials.

[0443] Output: The input request data.

[0444] Step 2:

[0445] The terminal sends the request to the server.

[0446] Specific operation: When the user presses the input completion button, the terminal sends the request content data to the server.

[0447] Input: The requested data entered.

[0448] Output: The request data sent to the server.

[0449] Step 3:

[0450] The server receives the request and asks the generative AI model to analyze it.

[0451] Specific operation: The server processes the request content data received from the terminal, creates a prompt sentence for analyzing the request content, and sends it to the generative AI model.

[0452] Input: The request data sent to the server.

[0453] Output: A prompt to the generative AI model to analyze.

[0454] Step 4:

[0455] The generative AI model analyzes the request and extracts the task content.

[0456] Specific operation: The generative AI model receives the prompt, analyzes the input request, and extracts the necessary task information.

[0457] Input: A prompt to request the generative AI model to analyze.

[0458] Output: Analysis results including task content (e.g., task details and follow-up questions).

[0459] Step 5:

[0460] The server sets the priority of the tasks based on the analysis results.

[0461] Specific operation: Based on the analysis results obtained from the generative AI model, the server sets priorities based on task importance and deadlines.

[0462] Input: Analysis results of the generative AI model.

[0463] Output: The priority of the task (e.g. "High", "Medium", "Low").

[0464] Step 6:

[0465] The server obtains the user's current schedule from the schedule management device.

[0466] Specific operation: The server uses a schedule management API (e.g., Google Calendar API) to obtain the user's current schedule information.

[0467] Input: User authentication information and schedule management device API.

[0468] Output: The user's current schedule data.

[0469] Step 7:

[0470] The server suggests the best time to execute the task.

[0471] Specific operation: The server calculates and proposes the optimal task execution time based on the acquired schedule data and task priority.

[0472] Input: Task priority and user schedule data.

[0473] Output: Proposed task execution time.

[0474] Step 8:

[0475] The proposed execution time is reflected in the schedule management device.

[0476] Specific operation: The server adds the proposed task execution time to the schedule management device.

[0477] Input: Proposed task execution time.

[0478] Output: New scheduled tasks added to the scheduler.

[0479] Step 9:

[0480] The user reviews the schedule and adjusts it as needed.

[0481] Specific operation: The user checks the task execution time proposed by the schedule management device through the terminal and manually adjusts the time if necessary.

[0482] Input: A new scheduled task added to the schedule management device.

[0483] Output: The confirmed task execution time, or the task execution time adjusted by the user.

[0484] Step 10:

[0485] Execute tasks according to a schedule established by the user.

[0486] Specific Action: The user starts and executes a task at a specified time based on a fixed schedule.

[0487] Input: The confirmed task execution time.

[0488] Output: Completed tasks and their progress reports.

[0489] This concludes the detailed explanation of each processing step in the program for this system. This system allows users to significantly reduce the time it takes to set task priorities and adjust schedules, thereby improving work efficiency.

[0490] (Application example 1)

[0491] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0492] In today's factories, multiple processes are carried out simultaneously, making scheduling and prioritization complicated and difficult to manage efficiently. Furthermore, if factory equipment is not operated at the appropriate time, unnecessary waiting time and process delays occur, resulting in reduced production efficiency and increased operating costs.

[0493] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0494] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for linking with a schedule management device and proposing task execution times based on the priorities, and means for optimizing the schedule of work processes in the factory and controlling the operation of factory work equipment, thereby enabling automatic adjustment of schedules and efficient task management in the factory production process.

[0495] The "means for receiving the request content" is a device or function that takes in the request information such as text, images, audio, and video received from the user.

[0496] A "generative model" is a type of artificial intelligence algorithm used to analyze input data and extract specific information.

[0497] The "means for extracting task content" is a device or function that uses a generative model to identify a specific task and its details from the received request content.

[0498] The "means for automatically setting priorities" is a device or function that evaluates the importance and deadlines based on the extracted task contents and automatically determines the priority of the work.

[0499] A "schedule management device" is a device or system that manages the start and end times of tasks and appropriately adjusts a user's schedule.

[0500] "Means for optimizing the schedule of work processes in a factory and controlling the operation of factory work equipment" refers to a device or function that automatically controls the operation of factory work equipment to optimize the timing of each work process in a factory and efficiently carry out work.

[0501] To implement the present invention, an information processing system is required to efficiently manage factory work processes and their schedules. This system receives requests, analyzes them using a generative model, sets priorities based on the analysis, and works in conjunction with a schedule management device to optimize the operation of factory work equipment.

[0502] First, the user inputs the request details from their device. This request is input in the form of text, images, audio, video, etc., and sent to the server. The server then passes the received request details to the generative AI model and requests that it be analyzed. The generative AI model analyzes the request details and extracts the task details. The extracted task details include the task priority and required operation information.

[0503] Next, the server automatically sets priorities based on the extracted task content. These priorities are determined by the task's importance and deadline. Furthermore, the server works with a schedule management device to suggest optimal execution times. In this process, the server uses existing schedule management software, such as the Google Calendar API, to obtain the user's current schedule and adjust the optimal execution time for the new task.

[0504] The proposed schedule is added to the user's schedule management device and can be viewed by the user via a terminal. The user can review the proposed schedule and make adjustments as necessary. Factory equipment is automatically operated at the specified times according to the confirmed schedule. This operation is used, for example, for parts assembly and inspection work on a factory line.

[0505] As a concrete example, consider a scenario in which a factory worker is requested to perform a new task. The worker uses a tablet device to enter the request details as text, attach any relevant image files, and send it to the server. The server then uses a generative AI model to analyze the request and extract the task's importance and required materials. Based on the extracted information, the server sets the task's priority to "high," checks the worker's schedule using the Google Calendar API, and proposes that the task be completed the following morning. The proposed schedule is automatically added to Google Calendar and can be viewed by the worker on their tablet.

[0506] This system allows the factory's work processes to proceed smoothly and significantly reduces the time required for task prioritization and schedule management. An example of a prompt that a user might use when inputting their request into the system would be, "I'm requesting assembly work for a new part. I've attached a related image. It's of high importance." In this way, it is possible to significantly improve the factory's production efficiency.

[0507] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0508] Step 1:

[0509] The user uses a terminal to input the request content. The request content can be input in the form of text, image, audio, video, etc. The input data is formatted appropriately according to the format and sent to the server. Input: Request content (text, image, audio, video) Output: Formatted request data

[0510] Specific operation: For example, the user inputs text and an image from a tablet device, such as "I would like to request assembly work for a new part. I have attached a related image." Then, the user presses the send button to send the data to the server.

[0511] Step 2:

[0512] The server sends the received request to the generative AI model and requests it to analyze it. The generative AI model analyzes the data and extracts the necessary task information. Input: Formatted request data Output: Detailed task information (e.g., task content, priority)

[0513] How it works: The server sends the formatted request data to the analysis API endpoint, and the generative AI model analyzes it. For example, it can obtain an analysis result such as "This image shows the assembly work of part A."

[0514] Step 3:

[0515] The server automatically sets task priorities based on detailed task information obtained from the generated AI model. Input: Detailed task information Output: Prioritized task data

[0516] Specific operation: The server evaluates the analysis results and sets priorities based on the importance and urgency of the tasks. For example, tasks that are judged to be of high importance are set to "High."

[0517] Step 4:

[0518] The server works with a schedule management device (e.g., Google Calendar API) to obtain the user's current schedule and propose new task execution times. Input: prioritized task data, user's current schedule. Output: proposed execution schedule.

[0519] Specific operation: The server uses the Google Calendar API to obtain the user's current schedule. Then, based on the priority, it selects an available time slot and suggests a time to execute the task. For example, it suggests executing the task in the morning of the following day.

[0520] Step 5:

[0521] The server adds the proposed schedule to the user's schedule management device, allowing the user to view it through their device. Input: Proposed execution schedule Output: Schedule added to the user's Google Calendar

[0522] Specific operation: The server sends an API request to add the proposed task schedule to Google Calendar. The schedule is displayed on the calendar in a format that the user can view on a tablet or other device.

[0523] Step 6:

[0524] The user confirms the proposed schedule. If necessary, the user can adjust the schedule. Input: Schedule added to Google Calendar Output: Schedule confirmed by the user

[0525] What happens: The user opens Google Calendar on their device, reviews the proposed task schedule, and, if necessary, changes or adjusts the schedule and finally confirms it.

[0526] Step 7:

[0527] Factory equipment is automatically operated at the specified time according to the confirmed schedule. Input: Confirmed schedule Output: Work execution status

[0528] Specific operation: Factory equipment automatically starts work based on the confirmed schedule. For example, assembly work for part A starts and finishes at the specified time.

[0529] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0530] This invention relates to a task management system that helps corporate employees and freelancers improve their work efficiency. In particular, it is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[0531] Program Description

[0532] This system starts with the user inputting the request details from the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is then sent from the terminal to the server.

[0533] The server temporarily stores the received data and sends it to the generative model for analysis. The generative model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[0534] The server then utilizes an emotion engine to recognize the user's emotional state. The emotion engine identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[0535] The server then uses the Google Calendar API to retrieve the user's current schedule, and, taking into account the priority and the user's emotional state, suggests the optimal time to execute the task and automatically adds it to the Google Calendar.

[0536] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[0537] Specific examples

[0538] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to type the request as text, attach any relevant image files, and send it to a server. The server then passes the request to a generative model, which analyzes the task. The user's emotional state (e.g., stress, anxiety, etc.) is also analyzed along with the analysis results.

[0539] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[0540] The proposed schedule is automatically added to Google Calendar and can be viewed by the user on their smartphone. The user can review the schedule and accept it if there are no problems, or manually adjust it if necessary. Once the schedule is confirmed, the user can carry out the tasks according to the schedule.

[0541] In this way, by combining the emotion engine, task management that takes into account the user's emotional state becomes possible, realizing more efficient and user-friendly task management. By linking the generative model with the Google Calendar API, task prioritization and schedule adjustment can be performed quickly, improving productivity.

[0542] The processing flow will be explained below.

[0543] Step 1:

[0544] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[0545] Step 2:

[0546] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[0547] Step 3:

[0548] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[0549] Step 4:

[0550] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[0551] Step 5:

[0552] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[0553] Step 6:

[0554] The server analyzes the user's emotional state using an emotion engine, which analyzes the user's input data and real-time feedback to identify the user's emotions.

[0555] Step 7:

[0556] The server adjusts task priorities and suggested execution times as needed based on the user's emotional state. For example, if the user is feeling stressed, the schedule is adjusted to avoid those times.

[0557] Step 8:

[0558] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[0559] Step 9:

[0560] The server takes into account the user's schedule, priorities, and emotional state to suggest the optimal execution time for each task. The suggested execution times are automatically added to the user's Google Calendar.

[0561] Step 10:

[0562] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[0563] Step 11:

[0564] The server monitors the schedule and sends reminders when the task is about to be performed, helping users remember to perform the task.

[0565] Step 12:

[0566] Tasks are executed according to a schedule determined by the user. When a task is completed, the user can notify the server of the completion of the task from the terminal.

[0567] In this way, taking into account the user's emotional state enables more adaptive and efficient task management. By combining a generative model, an emotion engine, and the Google Calendar API, this system can improve the user's overall work efficiency.

[0568] Example 2

[0569] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0570] In conventional task management systems, task prioritization and schedule adjustments are performed without taking the user's emotional state into consideration, which often leads to problems such as stress and reduced efficiency. Furthermore, there is no automated response when the request content is unclear, which increases the burden on the user.

[0571] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0572] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for analyzing the user's emotional state using an emotion recognition engine, means for adjusting task priorities and execution times based on the user's emotional state, and means for working in conjunction with a schedule management device to suggest task execution times based on the priorities and emotional state. This allows task prioritization and schedule adjustment to be performed automatically and optimally while taking the user's emotional state into consideration, thereby improving work efficiency and reducing stress.

[0573] "Request content" refers to input data that includes specific information and instructions that a user needs to perform a job or task.

[0574] A "generative model" is an algorithm or system that uses artificial intelligence technology to analyze received requests and extract task content.

[0575] "Task content" refers to the specific work or processing items that the user must perform, extracted from the request content.

[0576] "Priority" is an evaluation criterion that determines the order and importance of execution based on the importance and urgency of the task content.

[0577] An "emotion recognition engine" is a system or algorithm that analyzes a user's emotional state from input data and real-time feedback.

[0578] "User's emotional state" refers to the user's psychological state and emotions analyzed by the emotion recognition engine.

[0579] A "schedule management device" is an external system or application for managing task execution times and schedules.

[0580] A "task execution time" is a specific time period allotted to a user to perform a particular task.

[0581] This invention relates to a task management system for improving the work efficiency of corporate employees and freelance workers. It is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[0582] The program for this system starts with the user inputting the request details on the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is sent from the terminal to the server.

[0583] The server temporarily stores the received data and sends it to the generative AI model for analysis. The generative AI model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[0584] The server then utilizes an emotion recognition engine to recognize the user's emotional state, which identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[0585] The server then uses the schedule management device's API to obtain the user's current schedule, and, taking into account the priority and the user's emotional state, proposes optimal task execution times and automatically adds them to the schedule management device.

[0586] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[0587] Specific examples

[0588] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. Using their smartphone, the user types the request as text and attaches any relevant image files, sending it to a server. The server then passes the request to a generative AI model, which analyzes the task. The user's emotional state (e.g., stress or anxiety) is also analyzed along with the analysis results.

[0589] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[0590] The proposed schedule is automatically added to the schedule management device and becomes available for the user to view on their smartphone. The user reviews the schedule and, if there are no particular problems, accepts it as is, making manual adjustments as necessary. Once the schedule is finalized, the user carries out tasks according to the schedule. In this way, combining an emotion recognition engine enables task management that takes the user's emotional state into account, resulting in even more efficient and user-friendly task management.

[0591] An example prompt is:

[0592] "User entered text:

[0593] I want to schedule a meeting for new project X next Monday at 3 PM. Please review the relevant materials and set the priority to high. Also, analyze the user's emotional state and adjust the schedule if necessary."

[0594] The above system utilizes a generative AI model and an emotion recognition engine to not only improve the efficiency of task management for users but also reduce emotional burden, thereby increasing work productivity.

[0595] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0596] Step 1:

[0597] The user enters the request details

[0598] Specific operation: The user uses their device (smartphone, tablet, PC) to input the details of a new task request. Input formats include text, audio, images, and video. Specifically, the user enters text such as "Create materials for Project X" and attaches the relevant PDF file.

[0599] Input: Request details entered by the user (text, audio, images, videos, etc.) and attachments

[0600] Output: The requested data and attached files are sent from the device to the server.

[0601] Step 2:

[0602] The device sends data to the server, and the server stores the data.

[0603] Specific operation: The terminal sends the input request and attached file to the server. The server receives this data and temporarily stores it in a database.

[0604] Input: Request content and attachments sent from the device

[0605] Output: The request details and attachments are saved in the database.

[0606] Step 3:

[0607] The server requests the generated AI model to analyze the data.

[0608] Specific operation: The server passes the saved request content and attachments to the generative AI model and requests text analysis. The generative AI model analyzes the request text and attachments and extracts specific task information.

[0609] Input: Saved request and attachments

[0610] Output: Parsed task content

[0611] Step 4:

[0612] The server sets the priority of the task

[0613] Specific operation: The server sets the priority of tasks based on the analysis results from the generative AI model. In doing so, it considers the urgency, importance, deadline, etc. of the task and determines it as "high priority."

[0614] Input: Analysis results from a generative AI model

[0615] Output: Prioritized task information

[0616] Step 5:

[0617] The server uses an emotion recognition engine to analyze the user's emotional state.

[0618] Specific operation: The server analyzes the user's latest input data and real-time feedback using an emotion recognition engine. For example, using the text entered by the user and real-time facial expression images, the emotion recognition engine determines that the user is feeling stressed.

[0619] Input: Latest user input data and real-time feedback

[0620] Output: Parsed user's emotional state

[0621] Step 6:

[0622] The server adjusts task priorities and execution times

[0623] Specific operation: The server receives the results of the emotion recognition engine, considers the user's stress level, and adjusts the task priority and execution time. Specifically, it suggests execution times that avoid high-stress times.

[0624] Input: Emotion recognition engine results, prioritized task information

[0625] Output: Adjusted task priorities and execution times

[0626] Step 7:

[0627] The server automatically adds a schedule using the schedule management device's API.

[0628] Specific operation: The server uses the schedule management device's API to obtain the user's current schedule. Based on the obtained schedule, the server automatically adds the optimal time slot to the schedule management device, taking into account task priority and emotional state.

[0629] Input: User's current schedule, adjusted task priority and execution time

[0630] Output: The proposed task execution times are automatically added to the scheduler.

[0631] Step 8:

[0632] User reviews proposed schedule and adjusts as needed

[0633] Specific operation: The user checks the proposed schedule on the device. For example, they open a schedule management app on their smartphone and see that "Create materials for Project X" has been added. They can manually adjust the time as needed.

[0634] Input: Schedule information provided by the server

[0635] Output: Schedule approved and adjusted by user

[0636] Step 9:

[0637] The server sends the reminder

[0638] Specific operation: The server sends a reminder to the user when the task execution time approaches. Specifically, a push notification is displayed on the smartphone saying, "Please start creating materials for Project X."

[0639] Input: Confirmed schedule information

[0640] Output: Reminder notification sent to user

[0641] Step 10:

[0642] A user performs a task

[0643] Specific behavior: After receiving the reminder, the user starts and completes the task according to the confirmed schedule. For example, according to the schedule management app, the user starts preparing documents and completes the task at the specified time.

[0644] Input: Reminder sent

[0645] Output: Completed tasks

[0646] (Application example 2)

[0647] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0648] Conventional factory task management relies on manual work and human judgment, making it difficult to efficiently prioritize tasks and optimize execution schedules. Furthermore, task management does not take into account the emotional state of workers, resulting in increased worker fatigue and stress and reduced productivity. The purpose of this invention is to solve these problems and provide a more effective and user-friendly task management system.

[0649] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for recognizing emotional states and managing tasks based on that information, and means for working with a schedule management device to propose task execution times based on the priorities and emotional states. This improves work efficiency in factories and enables flexible task management that takes into account the emotional states of workers.

[0650] The "request content" is information that requests or instructs the execution of a task, and is provided in the form of text, audio, images, video, or the like.

[0651] A "generative model" is a model that uses machine learning and artificial intelligence techniques to analyze data and extract useful information.

[0652] "Task content" refers to the details and necessary information of a specific task or process extracted from the analysis results of the request content.

[0653] "Priority" is a criterion for determining the execution priority of a task relative to other tasks based on the importance and urgency of the task.

[0654] "Emotional state" refers to the user's psychological or physiological emotional state, including stress, fatigue, and the like.

[0655] "Task management" refers to activities that support the effective execution of tasks, such as planning, prioritizing, scheduling, and progress management of tasks.

[0656] A "schedule management device" is a device or system for recording, adjusting, and managing task execution times.

[0657] In order to put this invention into practice, it is first necessary to build a system in which a server, a terminal, and a user work in cooperation with each other.

[0658] The server includes the following means:

[0659] 1. Method of receiving request content: The user inputs the task request content from a device such as a smartphone, smart glasses, or head-mounted display. The input format can be a variety of formats, including text, audio, images, and video. The request content is sent from the device to the server.

[0660] 2. Generative model analysis: The server temporarily stores the received request and sends it to the generative model (machine learning model) for analysis. Here, the task content and necessary information are extracted, and the next step is taken based on the results.

[0661] 3. Priority setting method: Priorities are automatically set based on the importance and urgency of tasks. This priority setting is performed using an evaluation algorithm that runs on the server.

[0662] 4. Emotional state recognition: The emotion engine recognizes the user's emotional state by analyzing the user's input data and real-time feedback. If the user is in a stressful state, the priority is adjusted.

[0663] 5. Schedule suggestion method: Works with schedule management devices (such as Google Calendar API) to suggest optimal task execution times. Schedules based on priorities and emotional state are automatically added to the calendar.

[0664] The terminal has the following features:

[0665] 1. Task input interface: Provides an interface for users to input task requests. This can be a smartphone, smart glasses, or a head-mounted display.

[0666] 2. Schedule Review Interface: Includes an interface that allows the user to review the proposed schedule and manually adjust it if necessary.

[0667] The user does the following:

[0668] 1. Task request: The user inputs the task request details using the terminal, which are then sent to the server.

[0669] 2. Providing feedback: Providing feedback on the execution of schedules and tasks generated by the server.

[0670] As a concrete example, consider a scenario in which a factory worker is asked to perform "maintenance work on a new machine" using smart glasses. In this case, the worker inputs the task details by voice through the smart glasses. The voice data is sent to the server, and the task details are analyzed by a generative model. Next, an emotion engine checks the worker's emotional state, and if the worker is feeling stressed, the priority is adjusted based on that information. Finally, the optimal execution time is suggested using the Google Calendar API and displayed on the smart glasses.

[0671] Example prompt sentence:

[0672] "I've been asked to carry out maintenance work on a new machine. The details are to check the inspection list and related manuals."

[0673] In this way, combining a generative AI model with an emotion engine enables more efficient and flexible task management than conventional task management systems.

[0674] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0675] Step 1:

[0676] The user uses a device to input the task request. The input can be text, voice, image, or video. For example, a user can use smart glasses to input voice input such as "Request maintenance work on a new machine." This request is then sent from the device to the server.

[0677] Step 2:

[0678] The server temporarily stores the received request (voice data). It then sends the request to the generative AI model, requesting it to analyze the task content. The generative AI model analyzes the voice data, extracts the necessary information, and returns it to the server as the task content. Input: Request content (voice data), Output: Task content (analysis results)

[0679] Step 3:

[0680] The server evaluates the importance and urgency of the tasks based on the task content obtained from the generative AI model, and automatically sets priorities. Priority is set using an algorithm that takes into account the importance and urgency of the task content, resource usage, etc. Input: Task content (analysis results), Output: Priority

[0681] Step 4:

[0682] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's emotional state (stress, etc.) from the voice data and returns the results to the server. Input: Request content (voice data), Output: Emotional state (analysis results)

[0683] Step 5:

[0684] The server works with a schedule management device (such as Google Calendar API) based on the priority and emotional state to propose the optimal task execution time. Here, a time period with high priority and when the user is not feeling stressed is selected and added to the Google Calendar as a schedule. Input: Priority, emotional state, Output: Proposed execution time (schedule)

[0685] Step 6:

[0686] The user uses the device to check the proposed schedule. The schedule is displayed through the smart glasses, and the user manually adjusts it as needed. Once the user approves the schedule, the server confirms it and begins monitoring. Input: Proposed execution time (schedule), Output: Confirmed schedule

[0687] Step 7:

[0688] The server monitors the confirmed schedule and sends reminders when the task execution time approaches. The reminders are sent to the terminal, and the user executes the task according to the confirmed schedule. Input: Confirmed schedule, Output: Reminder notification

[0689] In this way, the entire process from inputting the request details to finalizing the schedule and executing the task becomes clear at each step. This improves work efficiency in the factory and enables flexible task management that takes into account the emotional state of the user.

[0690] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0691] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0692] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0693] [Third embodiment]

[0694] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0695] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0696] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0697] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0698] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0699] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0700] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0701] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0702] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0703] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0704] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0705] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0706] This invention relates to a task management system used by corporate employees and freelancers to improve work efficiency. This system simplifies complex task management by quickly and accurately analyzing requests, automatically prioritizing tasks, and proposing optimal execution times.

[0707] Program Description

[0708] This system starts when the user inputs the request details into the terminal. The user can input the request information in the form of text, images, audio, video, etc. This data is sent to the server.

[0709] The server passes the received data to the generative model and requests it to analyze it. The generative model analyzes the received data and extracts the necessary task information. The analysis results may include detailed task content and additional questions. In this case, the server notifies the user who made the request of the generated questions.

[0710] After obtaining the task information, the server automatically prioritizes the task based on this information. Priority is determined by the task's importance and deadline. Next, the server uses the Google Calendar API to retrieve the user's current schedule. This allows it to suggest the best time to execute the new task while coordinating with existing schedules.

[0711] The proposed schedule is added to the user's Google Calendar and can be viewed on the user's device. The user can review the proposed schedule and make adjustments as necessary. The user then carries out each task according to the confirmed schedule.

[0712] Specific examples

[0713] As an example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to input the request as text, attach any relevant image files, and send it to the server. The server passes this request to a generative model, which analyzes the task content. The analysis results include the task's importance and the necessary materials.

[0714] Based on this information, the server sets the task priority to "high." It then checks the user's schedule using the Google Calendar API and suggests that the task be performed the following morning. The suggested schedule is automatically added to Google Calendar, and the user can view it on their smartphone.

[0715] The user checks the schedule and accepts it if there are no problems. If adjustments are needed, the user manually edits the schedule. Once the schedule is confirmed, the user executes the tasks according to the schedule.

[0716] This system allows users to reduce the time spent on prioritizing tasks and adjusting schedules, allowing them to focus on their core work. By integrating the generative model with the Google Calendar API, task management is automated, significantly improving work efficiency.

[0717] The above is a specific embodiment for carrying out the present invention. By using this system, the productivity of companies and freelance workers can be increased.

[0718] The processing flow will be explained below.

[0719] Step 1:

[0720] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[0721] Step 2:

[0722] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[0723] Step 3:

[0724] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[0725] Step 4:

[0726] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[0727] Step 5:

[0728] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[0729] Step 6:

[0730] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[0731] Step 7:

[0732] Based on the schedule and priorities obtained by the server, the optimal execution time for each task is proposed, and the proposed task execution time is automatically added to the user's schedule.

[0733] Step 8:

[0734] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[0735] Step 9:

[0736] The server monitors the confirmed schedule and has the function of sending reminders when the task execution time approaches, so that users do not forget to execute the task.

[0737] Step 10:

[0738] Tasks are executed according to a schedule determined by the user. Once the task is completed, the user can notify the server of the task completion from their terminal.

[0739] Through these processing steps, users can efficiently manage the entire process from receiving to executing tasks. The automated integration of the generative model and the Google Calendar API enables quick task prioritization and scheduling, improving productivity.

[0740] Example 1

[0741] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0742] In conventional task management systems, task prioritization and schedule adjustments are often done manually, resulting in problems that reduce worker efficiency. Furthermore, when there are unclear points about a request, there is a lack of a way to quickly and accurately address them. This leads to the complexity of task management, waste of time, and hinders work efficiency.

[0743] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0744] In this invention, the server includes: a means for a user to input request details and send them from a terminal; a means for the server to receive the request details, analyze them using a generative AI model, and extract task details; a means for the server to automatically set priorities based on the task details; a means for the server to acquire the user's schedule via a schedule management device and propose task execution times; and a means for reflecting the proposed execution times in the schedule management device so that the user can confirm and adjust them. This automates task priority setting and schedule adjustment, improving work efficiency and reducing the complexity of task management.

[0745] "User" refers to a general user who uses the system to input and manage task requests.

[0746] "Terminal" refers to the device used by the user to input task requests and send them to the server. Examples include smartphones and personal computers.

[0747] "Server" refers to a central computer system that receives and analyzes requests, prioritizes tasks, and manages schedules.

[0748] "Generative AI model" refers to an artificial intelligence model used to analyze received requests and extract task content.

[0749] "Task content" refers to the specific work items extracted from the request content analyzed by the generative AI model.

[0750] "Priority" refers to the execution priority set based on the importance and deadline of a task.

[0751] "Execution time" refers to the specific date, time, and time period when a task should be executed.

[0752] A "schedule management device" refers to a system or application for managing a user's schedule, such as a general calendar application.

[0753] "Request content" refers to the task content and requirements that the user inputs into the system.

[0754] "Question" refers to the content that the generative AI model automatically generates when there is an unclear point in the request content and asks the user for confirmation.

[0755] "Analysis" refers to the process in which the generative AI model deciphers the request received and extracts the necessary task content.

[0756] "Reflecting" refers to the process in which the server adds the proposed execution time to the schedule management device and has the user confirm it.

[0757] This invention relates to a task management system that workers can use to improve their work efficiency. This system simplifies complex task management by quickly and accurately analyzing task requests, automatically setting priorities, and proposing optimal execution times.

[0758] System configuration

[0759] This system is composed of a combination of terminals, a server, and a schedule management device. Terminals are devices used by users to input task requests, and include smartphones and PCs. The server is a central computer system that analyzes the request content, sets task priorities, and manages schedules. The schedule management device is a system or application for managing users' schedules, such as a general calendar application.

[0760] Data Processing Procedures

[0761] The process of this system is as follows.

[0762] A user uses a device to input task requests and transmit the data. The requests can be in the form of text, images, audio, or video. For example, a user may input details about a new marketing project and attach images of related materials. After input, the data is transmitted from the device to the server.

[0763] The server receives the data sent by the user and then has the generative AI model analyze the request. The generative AI model analyzes the received request and extracts the task details. Based on the analysis results, the server automatically sets the priority of the task. At this time, the priority is set to "high," "medium," or "low" based on the importance and deadline of the task.

[0764] The server also obtains the user's current schedule through the schedule management device, allowing it to suggest the best time to execute a new task. For example, the server may check the user's schedule using the Google Calendar API and suggest executing the task in the morning of the following day.

[0765] The proposed schedule is automatically added to the schedule management device and can be viewed by the user through their terminal. The user can check the schedule and make adjustments as necessary. Once the schedule is confirmed, the user can carry out tasks according to the schedule.

[0766] Specific examples

[0767] A specific scenario is shown below.

[0768] During a meeting, a user is verbally requested to complete a new marketing task. The user then uses their smartphone to type the request into text, attaching any related image files, and submitting it to the server.

[0769] The server receives the request and sends a prompt to the generative AI model, such as, "Your task is to create a marketing strategy for a new product. The image below contains detailed information." The generative AI model then responds with an analysis result, such as, "The key points are based on the graphs in the document. Additional materials are also required."

[0770] Based on the analysis results, the server sets the task priority to "high" and checks the user's schedule using the Google Calendar API. The optimal execution time is suggested as the morning of the following day. The suggested schedule is automatically added to Google Calendar for the user to view.

[0771] The user checks the schedule and accepts it if there are no problems, or manually adjusts it if there are any overlapping schedules. Once the schedule is confirmed, the user executes the task according to the specified time.

[0772] This system significantly reduces the time required for setting task priorities and adjusting schedules, thereby improving work efficiency. In addition, by linking the generative AI model with the schedule management device, task management is automated, allowing users to focus on their primary work.

[0773] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0774] Step 1:

[0775] The user inputs the request details.

[0776] Specific operation: The user operates a device (smartphone or PC) to input the task request details. The input format can be text, images, audio, video, etc.

[0777] Input: Marketing project request details and image files of related materials.

[0778] Output: The input request data.

[0779] Step 2:

[0780] The terminal sends the request to the server.

[0781] Specific operation: When the user presses the input completion button, the terminal sends the request content data to the server.

[0782] Input: The requested data entered.

[0783] Output: The request data sent to the server.

[0784] Step 3:

[0785] The server receives the request and asks the generative AI model to analyze it.

[0786] Specific operation: The server processes the request content data received from the terminal, creates a prompt sentence for analyzing the request content, and sends it to the generative AI model.

[0787] Input: The request data sent to the server.

[0788] Output: A prompt to the generative AI model to analyze.

[0789] Step 4:

[0790] The generative AI model analyzes the request and extracts the task content.

[0791] Specific operation: The generative AI model receives the prompt, analyzes the input request, and extracts the necessary task information.

[0792] Input: A prompt to request the generative AI model to analyze.

[0793] Output: Analysis results including task content (e.g., task details and follow-up questions).

[0794] Step 5:

[0795] The server sets the priority of the tasks based on the analysis results.

[0796] Specific operation: Based on the analysis results obtained from the generative AI model, the server sets priorities based on task importance and deadlines.

[0797] Input: Analysis results of the generative AI model.

[0798] Output: The priority of the task (e.g. "High", "Medium", "Low").

[0799] Step 6:

[0800] The server obtains the user's current schedule from the schedule management device.

[0801] Specific operation: The server uses a schedule management API (e.g., Google Calendar API) to obtain the user's current schedule information.

[0802] Input: User authentication information and schedule management device API.

[0803] Output: The user's current schedule data.

[0804] Step 7:

[0805] The server suggests the best time to execute the task.

[0806] Specific operation: The server calculates and proposes the optimal task execution time based on the acquired schedule data and task priority.

[0807] Input: Task priority and user schedule data.

[0808] Output: Proposed task execution time.

[0809] Step 8:

[0810] The proposed execution time is reflected in the schedule management device.

[0811] Specific operation: The server adds the proposed task execution time to the schedule management device.

[0812] Input: Proposed task execution time.

[0813] Output: New scheduled tasks added to the scheduler.

[0814] Step 9:

[0815] The user reviews the schedule and adjusts it as needed.

[0816] Specific operation: The user checks the task execution time proposed by the schedule management device through the terminal and manually adjusts the time if necessary.

[0817] Input: A new scheduled task added to the schedule management device.

[0818] Output: The confirmed task execution time, or the task execution time adjusted by the user.

[0819] Step 10:

[0820] Execute tasks according to a schedule established by the user.

[0821] Specific Action: The user starts and executes a task at a specified time based on a fixed schedule.

[0822] Input: The confirmed task execution time.

[0823] Output: Completed tasks and their progress reports.

[0824] This concludes the detailed explanation of each processing step in the program for this system. This system allows users to significantly reduce the time it takes to set task priorities and adjust schedules, thereby improving work efficiency.

[0825] (Application example 1)

[0826] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0827] In today's factories, multiple processes are carried out simultaneously, making scheduling and prioritization complicated and difficult to manage efficiently. Furthermore, if factory equipment is not operated at the appropriate time, unnecessary waiting time and process delays occur, resulting in reduced production efficiency and increased operating costs.

[0828] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0829] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for linking with a schedule management device and proposing task execution times based on the priorities, and means for optimizing the schedule of work processes in the factory and controlling the operation of factory work equipment, thereby enabling automatic adjustment of schedules and efficient task management in the factory production process.

[0830] The "means for receiving the request content" is a device or function that takes in the request information such as text, images, audio, and video received from the user.

[0831] A "generative model" is a type of artificial intelligence algorithm used to analyze input data and extract specific information.

[0832] The "means for extracting task content" is a device or function that uses a generative model to identify a specific task and its details from the received request content.

[0833] The "means for automatically setting priorities" is a device or function that evaluates the importance and deadlines based on the extracted task contents and automatically determines the priority of the work.

[0834] A "schedule management device" is a device or system that manages the start and end times of tasks and appropriately adjusts a user's schedule.

[0835] "Means for optimizing the schedule of work processes in a factory and controlling the operation of factory work equipment" refers to a device or function that automatically controls the operation of factory work equipment to optimize the timing of each work process in a factory and efficiently carry out work.

[0836] To implement the present invention, an information processing system is required to efficiently manage factory work processes and their schedules. This system receives requests, analyzes them using a generative model, sets priorities based on the analysis, and works in conjunction with a schedule management device to optimize the operation of factory work equipment.

[0837] First, the user inputs the request details from their device. This request is input in the form of text, images, audio, video, etc., and sent to the server. The server then passes the received request details to the generative AI model and requests that it be analyzed. The generative AI model analyzes the request details and extracts the task details. The extracted task details include the task priority and required operation information.

[0838] Next, the server automatically sets priorities based on the extracted task content. These priorities are determined by the task's importance and deadline. Furthermore, the server works with a schedule management device to suggest optimal execution times. In this process, the server uses existing schedule management software, such as the Google Calendar API, to obtain the user's current schedule and adjust the optimal execution time for the new task.

[0839] The proposed schedule is added to the user's schedule management device and can be viewed by the user via a terminal. The user can review the proposed schedule and make adjustments as necessary. Factory equipment is automatically operated at the specified times according to the confirmed schedule. This operation is used, for example, for parts assembly and inspection work on a factory line.

[0840] As a concrete example, consider a scenario in which a factory worker is requested to perform a new task. The worker uses a tablet device to enter the request details as text, attach any relevant image files, and send it to the server. The server then uses a generative AI model to analyze the request and extract the task's importance and required materials. Based on the extracted information, the server sets the task's priority to "high," checks the worker's schedule using the Google Calendar API, and proposes that the task be completed the following morning. The proposed schedule is automatically added to Google Calendar and can be viewed by the worker on their tablet.

[0841] This system allows the factory's work processes to proceed smoothly and significantly reduces the time required for task prioritization and schedule management. An example of a prompt that a user might use when inputting their request into the system would be, "I'm requesting assembly work for a new part. I've attached a related image. It's of high importance." In this way, it is possible to significantly improve the factory's production efficiency.

[0842] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0843] Step 1:

[0844] The user uses a terminal to input the request content. The request content can be input in the form of text, image, audio, video, etc. The input data is formatted appropriately according to the format and sent to the server. Input: Request content (text, image, audio, video) Output: Formatted request data

[0845] Specific operation: For example, the user inputs text and an image from a tablet device, such as "I would like to request assembly work for a new part. I have attached a related image." Then, the user presses the send button to send the data to the server.

[0846] Step 2:

[0847] The server sends the received request to the generative AI model and requests it to analyze it. The generative AI model analyzes the data and extracts the necessary task information. Input: Formatted request data Output: Detailed task information (e.g., task content, priority)

[0848] How it works: The server sends the formatted request data to the analysis API endpoint, and the generative AI model analyzes it. For example, it can obtain an analysis result such as "This image shows the assembly work of part A."

[0849] Step 3:

[0850] The server automatically sets task priorities based on detailed task information obtained from the generated AI model. Input: Detailed task information Output: Prioritized task data

[0851] Specific operation: The server evaluates the analysis results and sets priorities based on the importance and urgency of the tasks. For example, tasks that are judged to be of high importance are set to "High."

[0852] Step 4:

[0853] The server works with a schedule management device (e.g., Google Calendar API) to obtain the user's current schedule and propose new task execution times. Input: prioritized task data, user's current schedule. Output: proposed execution schedule.

[0854] Specific operation: The server uses the Google Calendar API to obtain the user's current schedule. Then, based on the priority, it selects an available time slot and suggests a time to execute the task. For example, it suggests executing the task in the morning of the following day.

[0855] Step 5:

[0856] The server adds the proposed schedule to the user's schedule management device, allowing the user to view it through their device. Input: Proposed execution schedule Output: Schedule added to the user's Google Calendar

[0857] Specific operation: The server sends an API request to add the proposed task schedule to Google Calendar. The schedule is displayed on the calendar in a format that the user can view on a tablet or other device.

[0858] Step 6:

[0859] The user confirms the proposed schedule. If necessary, the user can adjust the schedule. Input: Schedule added to Google Calendar Output: Schedule confirmed by the user

[0860] What happens: The user opens Google Calendar on their device, reviews the proposed task schedule, and, if necessary, changes or adjusts the schedule and finally confirms it.

[0861] Step 7:

[0862] Factory equipment is automatically operated at the specified time according to the confirmed schedule. Input: Confirmed schedule Output: Work execution status

[0863] Specific operation: Factory equipment automatically starts work based on the confirmed schedule. For example, assembly work for part A starts and finishes at the specified time.

[0864] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0865] This invention relates to a task management system that helps corporate employees and freelancers improve their work efficiency. In particular, it is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[0866] Program Description

[0867] This system starts with the user inputting the request details from the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is then sent from the terminal to the server.

[0868] The server temporarily stores the received data and sends it to the generative model for analysis. The generative model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[0869] The server then utilizes an emotion engine to recognize the user's emotional state. The emotion engine identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[0870] The server then uses the Google Calendar API to retrieve the user's current schedule, and, taking into account the priority and the user's emotional state, suggests the optimal time to execute the task and automatically adds it to the Google Calendar.

[0871] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[0872] Specific examples

[0873] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to type the request as text, attach any relevant image files, and send it to a server. The server then passes the request to a generative model, which analyzes the task. The user's emotional state (e.g., stress, anxiety, etc.) is also analyzed along with the analysis results.

[0874] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[0875] The proposed schedule is automatically added to Google Calendar and can be viewed by the user on their smartphone. The user can review the schedule and accept it if there are no problems, or manually adjust it if necessary. Once the schedule is confirmed, the user can carry out the tasks according to the schedule.

[0876] In this way, by combining the emotion engine, task management that takes into account the user's emotional state becomes possible, realizing more efficient and user-friendly task management. By linking the generative model with the Google Calendar API, task prioritization and schedule adjustment can be performed quickly, improving productivity.

[0877] The processing flow will be explained below.

[0878] Step 1:

[0879] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[0880] Step 2:

[0881] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[0882] Step 3:

[0883] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[0884] Step 4:

[0885] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[0886] Step 5:

[0887] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[0888] Step 6:

[0889] The server analyzes the user's emotional state using an emotion engine, which analyzes the user's input data and real-time feedback to identify the user's emotions.

[0890] Step 7:

[0891] The server adjusts task priorities and suggested execution times as needed based on the user's emotional state. For example, if the user is feeling stressed, the schedule is adjusted to avoid those times.

[0892] Step 8:

[0893] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[0894] Step 9:

[0895] The server takes into account the user's schedule, priorities, and emotional state to suggest the optimal execution time for each task. The suggested execution times are automatically added to the user's Google Calendar.

[0896] Step 10:

[0897] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[0898] Step 11:

[0899] The server monitors the schedule and sends reminders when the task is about to be performed, helping users remember to perform the task.

[0900] Step 12:

[0901] Tasks are executed according to a schedule determined by the user. When a task is completed, the user can notify the server of the completion of the task from the terminal.

[0902] In this way, taking into account the user's emotional state enables more adaptive and efficient task management. By combining a generative model, an emotion engine, and the Google Calendar API, this system can improve the user's overall work efficiency.

[0903] Example 2

[0904] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0905] In conventional task management systems, task prioritization and schedule adjustments are performed without taking the user's emotional state into consideration, which often leads to problems such as stress and reduced efficiency. Furthermore, there is no automated response when the request content is unclear, which increases the burden on the user.

[0906] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0907] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for analyzing the user's emotional state using an emotion recognition engine, means for adjusting task priorities and execution times based on the user's emotional state, and means for working in conjunction with a schedule management device to suggest task execution times based on the priorities and emotional state. This allows task prioritization and schedule adjustment to be performed automatically and optimally while taking the user's emotional state into consideration, thereby improving work efficiency and reducing stress.

[0908] "Request content" refers to input data that includes specific information and instructions that a user needs to perform a job or task.

[0909] A "generative model" is an algorithm or system that uses artificial intelligence technology to analyze received requests and extract task content.

[0910] "Task content" refers to the specific work or processing items that the user must perform, extracted from the request content.

[0911] "Priority" is an evaluation criterion that determines the order and importance of execution based on the importance and urgency of the task content.

[0912] An "emotion recognition engine" is a system or algorithm that analyzes a user's emotional state from input data and real-time feedback.

[0913] "User's emotional state" refers to the user's psychological state and emotions analyzed by the emotion recognition engine.

[0914] A "schedule management device" is an external system or application for managing task execution times and schedules.

[0915] A "task execution time" is a specific time period allotted to a user to perform a particular task.

[0916] This invention relates to a task management system for improving the work efficiency of corporate employees and freelance workers. It is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[0917] The program for this system starts with the user inputting the request details on the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is sent from the terminal to the server.

[0918] The server temporarily stores the received data and sends it to the generative AI model for analysis. The generative AI model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[0919] The server then utilizes an emotion recognition engine to recognize the user's emotional state, which identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[0920] The server then uses the schedule management device's API to obtain the user's current schedule, and, taking into account the priority and the user's emotional state, proposes optimal task execution times and automatically adds them to the schedule management device.

[0921] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[0922] Specific examples

[0923] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. Using their smartphone, the user types the request as text and attaches any relevant image files, sending it to a server. The server then passes the request to a generative AI model, which analyzes the task. The user's emotional state (e.g., stress or anxiety) is also analyzed along with the analysis results.

[0924] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[0925] The proposed schedule is automatically added to the schedule management device and becomes available for the user to view on their smartphone. The user reviews the schedule and, if there are no particular problems, accepts it as is, making manual adjustments as necessary. Once the schedule is finalized, the user carries out tasks according to the schedule. In this way, combining an emotion recognition engine enables task management that takes the user's emotional state into account, resulting in even more efficient and user-friendly task management.

[0926] An example prompt is:

[0927] "User entered text:

[0928] I want to schedule a meeting for new project X next Monday at 3 PM. Please review the relevant materials and set the priority to high. Also, analyze the user's emotional state and adjust the schedule if necessary."

[0929] The above system utilizes a generative AI model and an emotion recognition engine to not only improve the efficiency of task management for users but also reduce emotional burden, thereby increasing work productivity.

[0930] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0931] Step 1:

[0932] The user enters the request details

[0933] Specific operation: The user uses their device (smartphone, tablet, PC) to input the details of a new task request. Input formats include text, audio, images, and video. Specifically, the user enters text such as "Create materials for Project X" and attaches the relevant PDF file.

[0934] Input: Request details entered by the user (text, audio, images, videos, etc.) and attachments

[0935] Output: The requested data and attached files are sent from the device to the server.

[0936] Step 2:

[0937] The device sends data to the server, and the server stores the data.

[0938] Specific operation: The terminal sends the input request and attached file to the server. The server receives this data and temporarily stores it in a database.

[0939] Input: Request content and attachments sent from the device

[0940] Output: The request details and attachments are saved in the database.

[0941] Step 3:

[0942] The server requests the generated AI model to analyze the data.

[0943] Specific operation: The server passes the saved request content and attachments to the generative AI model and requests text analysis. The generative AI model analyzes the request text and attachments and extracts specific task information.

[0944] Input: Saved request and attachments

[0945] Output: Parsed task content

[0946] Step 4:

[0947] The server sets the priority of the task

[0948] Specific operation: The server sets the priority of tasks based on the analysis results from the generative AI model. In doing so, it considers the urgency, importance, deadline, etc. of the task and determines it as "high priority."

[0949] Input: Analysis results from a generative AI model

[0950] Output: Prioritized task information

[0951] Step 5:

[0952] The server uses an emotion recognition engine to analyze the user's emotional state.

[0953] Specific operation: The server analyzes the user's latest input data and real-time feedback using an emotion recognition engine. For example, using the text entered by the user and real-time facial expression images, the emotion recognition engine determines that the user is feeling stressed.

[0954] Input: Latest user input data and real-time feedback

[0955] Output: Parsed user's emotional state

[0956] Step 6:

[0957] The server adjusts task priorities and execution times

[0958] Specific operation: The server receives the results of the emotion recognition engine, considers the user's stress level, and adjusts the task priority and execution time. Specifically, it suggests execution times that avoid high-stress times.

[0959] Input: Emotion recognition engine results, prioritized task information

[0960] Output: Adjusted task priorities and execution times

[0961] Step 7:

[0962] The server automatically adds a schedule using the schedule management device's API.

[0963] Specific operation: The server uses the schedule management device's API to obtain the user's current schedule. Based on the obtained schedule, the server automatically adds the optimal time slot to the schedule management device, taking into account task priority and emotional state.

[0964] Input: User's current schedule, adjusted task priority and execution time

[0965] Output: The proposed task execution times are automatically added to the scheduler.

[0966] Step 8:

[0967] User reviews proposed schedule and adjusts as needed

[0968] Specific operation: The user checks the proposed schedule on the device. For example, they open a schedule management app on their smartphone and see that "Create materials for Project X" has been added. They can manually adjust the time as needed.

[0969] Input: Schedule information provided by the server

[0970] Output: Schedule approved and adjusted by user

[0971] Step 9:

[0972] The server sends the reminder

[0973] Specific operation: The server sends a reminder to the user when the task execution time approaches. Specifically, a push notification is displayed on the smartphone saying, "Please start creating materials for Project X."

[0974] Input: Confirmed schedule information

[0975] Output: Reminder notification sent to user

[0976] Step 10:

[0977] A user performs a task

[0978] Specific behavior: After receiving the reminder, the user starts and completes the task according to the confirmed schedule. For example, according to the schedule management app, the user starts preparing documents and completes the task at the specified time.

[0979] Input: Reminder sent

[0980] Output: Completed tasks

[0981] (Application example 2)

[0982] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0983] Conventional factory task management relies on manual work and human judgment, making it difficult to efficiently prioritize tasks and optimize execution schedules. Furthermore, task management does not take into account the emotional state of workers, resulting in increased worker fatigue and stress and reduced productivity. The purpose of this invention is to solve these problems and provide a more effective and user-friendly task management system.

[0984] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for recognizing emotional states and managing tasks based on that information, and means for working with a schedule management device to propose task execution times based on the priorities and emotional states. This improves work efficiency in factories and enables flexible task management that takes into account the emotional states of workers.

[0985] The "request content" is information that requests or instructs the execution of a task, and is provided in the form of text, audio, images, video, or the like.

[0986] A "generative model" is a model that uses machine learning and artificial intelligence techniques to analyze data and extract useful information.

[0987] "Task content" refers to the details and necessary information of a specific task or process extracted from the analysis results of the request content.

[0988] "Priority" is a criterion for determining the execution priority of a task relative to other tasks based on the importance and urgency of the task.

[0989] "Emotional state" refers to the user's psychological or physiological emotional state, including stress, fatigue, and the like.

[0990] "Task management" refers to activities that support the effective execution of tasks, such as planning, prioritizing, scheduling, and progress management of tasks.

[0991] A "schedule management device" is a device or system for recording, adjusting, and managing task execution times.

[0992] In order to put this invention into practice, it is first necessary to build a system in which a server, a terminal, and a user work in cooperation with each other.

[0993] The server includes the following means:

[0994] 1. Method of receiving request content: The user inputs the task request content from a device such as a smartphone, smart glasses, or head-mounted display. The input format can be a variety of formats, including text, audio, images, and video. The request content is sent from the device to the server.

[0995] 2. Generative model analysis: The server temporarily stores the received request and sends it to the generative model (machine learning model) for analysis. Here, the task content and necessary information are extracted, and the next step is taken based on the results.

[0996] 3. Priority setting method: Priorities are automatically set based on the importance and urgency of tasks. This priority setting is performed using an evaluation algorithm that runs on the server.

[0997] 4. Emotional state recognition: The emotion engine recognizes the user's emotional state by analyzing the user's input data and real-time feedback. If the user is in a stressful state, the priority is adjusted.

[0998] 5. Schedule suggestion method: Works with schedule management devices (such as Google Calendar API) to suggest optimal task execution times. Schedules based on priorities and emotional state are automatically added to the calendar.

[0999] The terminal has the following features:

[1000] 1. Task input interface: Provides an interface for users to input task requests. This can be a smartphone, smart glasses, or a head-mounted display.

[1001] 2. Schedule Review Interface: Includes an interface that allows the user to review the proposed schedule and manually adjust it if necessary.

[1002] The user does the following:

[1003] 1. Task request: The user inputs the task request details using the terminal, which are then sent to the server.

[1004] 2. Providing feedback: Providing feedback on the execution of schedules and tasks generated by the server.

[1005] As a concrete example, consider a scenario in which a factory worker is asked to perform "maintenance work on a new machine" using smart glasses. In this case, the worker inputs the task details by voice through the smart glasses. The voice data is sent to the server, and the task details are analyzed by a generative model. Next, an emotion engine checks the worker's emotional state, and if the worker is feeling stressed, the priority is adjusted based on that information. Finally, the optimal execution time is suggested using the Google Calendar API and displayed on the smart glasses.

[1006] Example prompt sentence:

[1007] "I've been asked to carry out maintenance work on a new machine. The details are to check the inspection list and related manuals."

[1008] In this way, combining a generative AI model with an emotion engine enables more efficient and flexible task management than conventional task management systems.

[1009] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1010] Step 1:

[1011] The user uses a device to input the task request. The input can be text, voice, image, or video. For example, a user can use smart glasses to input voice input such as "Request maintenance work on a new machine." This request is then sent from the device to the server.

[1012] Step 2:

[1013] The server temporarily stores the received request (voice data). It then sends the request to the generative AI model, requesting it to analyze the task content. The generative AI model analyzes the voice data, extracts the necessary information, and returns it to the server as the task content. Input: Request content (voice data), Output: Task content (analysis results)

[1014] Step 3:

[1015] The server evaluates the importance and urgency of the tasks based on the task content obtained from the generative AI model, and automatically sets priorities. Priority is set using an algorithm that takes into account the importance and urgency of the task content, resource usage, etc. Input: Task content (analysis results), Output: Priority

[1016] Step 4:

[1017] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's emotional state (stress, etc.) from the voice data and returns the results to the server. Input: Request content (voice data), Output: Emotional state (analysis results)

[1018] Step 5:

[1019] The server works with a schedule management device (such as Google Calendar API) based on the priority and emotional state to propose the optimal task execution time. Here, a time period with high priority and when the user is not feeling stressed is selected and added to the Google Calendar as a schedule. Input: Priority, emotional state, Output: Proposed execution time (schedule)

[1020] Step 6:

[1021] The user uses the device to check the proposed schedule. The schedule is displayed through the smart glasses, and the user manually adjusts it as needed. Once the user approves the schedule, the server confirms it and begins monitoring. Input: Proposed execution time (schedule), Output: Confirmed schedule

[1022] Step 7:

[1023] The server monitors the confirmed schedule and sends reminders when the task execution time approaches. The reminders are sent to the terminal, and the user executes the task according to the confirmed schedule. Input: Confirmed schedule, Output: Reminder notification

[1024] In this way, the entire process from inputting the request details to finalizing the schedule and executing the task becomes clear at each step. This improves work efficiency in the factory and enables flexible task management that takes into account the emotional state of the user.

[1025] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1026] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1027] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1028] [Fourth embodiment]

[1029] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1030] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1032] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1033] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1034] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1036] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1037] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1038] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1040] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1042] This invention relates to a task management system used by corporate employees and freelancers to improve work efficiency. This system simplifies complex task management by quickly and accurately analyzing requests, automatically prioritizing tasks, and proposing optimal execution times.

[1043] Program Description

[1044] This system starts when the user inputs the request details into the terminal. The user can input the request information in the form of text, images, audio, video, etc. This data is sent to the server.

[1045] The server passes the received data to the generative model and requests it to analyze it. The generative model analyzes the received data and extracts the necessary task information. The analysis results may include detailed task content and additional questions. In this case, the server notifies the user who made the request of the generated questions.

[1046] After obtaining the task information, the server automatically prioritizes the task based on this information. Priority is determined by the task's importance and deadline. Next, the server uses the Google Calendar API to retrieve the user's current schedule. This allows it to suggest the best time to execute the new task while coordinating with existing schedules.

[1047] The proposed schedule is added to the user's Google Calendar and can be viewed on the user's device. The user can review the proposed schedule and make adjustments as necessary. The user then carries out each task according to the confirmed schedule.

[1048] Specific examples

[1049] As an example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to input the request as text, attach any relevant image files, and send it to the server. The server passes this request to a generative model, which analyzes the task content. The analysis results include the task's importance and the necessary materials.

[1050] Based on this information, the server sets the task priority to "high." It then checks the user's schedule using the Google Calendar API and suggests that the task be performed the following morning. The suggested schedule is automatically added to Google Calendar, and the user can view it on their smartphone.

[1051] The user checks the schedule and accepts it if there are no problems. If adjustments are needed, the user manually edits the schedule. Once the schedule is confirmed, the user executes the tasks according to the schedule.

[1052] This system allows users to reduce the time spent on prioritizing tasks and adjusting schedules, allowing them to focus on their core work. By integrating the generative model with the Google Calendar API, task management is automated, significantly improving work efficiency.

[1053] The above is a specific embodiment for carrying out the present invention. By using this system, the productivity of companies and freelance workers can be increased.

[1054] The processing flow will be explained below.

[1055] Step 1:

[1056] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[1057] Step 2:

[1058] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[1059] Step 3:

[1060] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[1061] Step 4:

[1062] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[1063] Step 5:

[1064] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[1065] Step 6:

[1066] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[1067] Step 7:

[1068] Based on the schedule and priorities obtained by the server, the optimal execution time for each task is proposed, and the proposed task execution time is automatically added to the user's schedule.

[1069] Step 8:

[1070] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[1071] Step 9:

[1072] The server monitors the confirmed schedule and has the function of sending reminders when the task execution time approaches, so that users do not forget to execute the task.

[1073] Step 10:

[1074] Tasks are executed according to a schedule determined by the user. Once the task is completed, the user can notify the server of the task completion from their terminal.

[1075] Through these processing steps, users can efficiently manage the entire process from receiving to executing tasks. The automated integration of the generative model and the Google Calendar API enables quick task prioritization and scheduling, improving productivity.

[1076] Example 1

[1077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1078] In conventional task management systems, task prioritization and schedule adjustments are often done manually, resulting in problems that reduce worker efficiency. Furthermore, when there are unclear points about a request, there is a lack of a way to quickly and accurately address them. This leads to the complexity of task management, waste of time, and hinders work efficiency.

[1079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1080] In this invention, the server includes: a means for a user to input request details and send them from a terminal; a means for the server to receive the request details, analyze them using a generative AI model, and extract task details; a means for the server to automatically set priorities based on the task details; a means for the server to acquire the user's schedule via a schedule management device and propose task execution times; and a means for reflecting the proposed execution times in the schedule management device so that the user can confirm and adjust them. This automates task priority setting and schedule adjustment, improving work efficiency and reducing the complexity of task management.

[1081] "User" refers to a general user who uses the system to input and manage task requests.

[1082] "Terminal" refers to the device used by the user to input task requests and send them to the server. Examples include smartphones and personal computers.

[1083] "Server" refers to a central computer system that receives and analyzes requests, prioritizes tasks, and manages schedules.

[1084] "Generative AI model" refers to an artificial intelligence model used to analyze received requests and extract task content.

[1085] "Task content" refers to the specific work items extracted from the request content analyzed by the generative AI model.

[1086] "Priority" refers to the execution priority set based on the importance and deadline of a task.

[1087] "Execution time" refers to the specific date, time, and time period when a task should be executed.

[1088] A "schedule management device" refers to a system or application for managing a user's schedule, such as a general calendar application.

[1089] "Request content" refers to the task content and requirements that the user inputs into the system.

[1090] "Question" refers to the content that the generative AI model automatically generates when there is an unclear point in the request content and asks the user for confirmation.

[1091] "Analysis" refers to the process in which the generative AI model deciphers the request received and extracts the necessary task content.

[1092] "Reflecting" refers to the process in which the server adds the proposed execution time to the schedule management device and has the user confirm it.

[1093] This invention relates to a task management system that workers can use to improve their work efficiency. This system simplifies complex task management by quickly and accurately analyzing task requests, automatically setting priorities, and proposing optimal execution times.

[1094] System configuration

[1095] This system is composed of a combination of terminals, a server, and a schedule management device. Terminals are devices used by users to input task requests, and include smartphones and PCs. The server is a central computer system that analyzes the request content, sets task priorities, and manages schedules. The schedule management device is a system or application for managing users' schedules, such as a general calendar application.

[1096] Data Processing Procedures

[1097] The process of this system is as follows.

[1098] A user uses a device to input task requests and transmit the data. The requests can be in the form of text, images, audio, or video. For example, a user may input details about a new marketing project and attach images of related materials. After input, the data is transmitted from the device to the server.

[1099] The server receives the data sent by the user and then has the generative AI model analyze the request. The generative AI model analyzes the received request and extracts the task details. Based on the analysis results, the server automatically sets the priority of the task. At this time, the priority is set to "high," "medium," or "low" based on the importance and deadline of the task.

[1100] The server also obtains the user's current schedule through the schedule management device, allowing it to suggest the best time to execute a new task. For example, the server may check the user's schedule using the Google Calendar API and suggest executing the task in the morning of the following day.

[1101] The proposed schedule is automatically added to the schedule management device and can be viewed by the user through their terminal. The user can check the schedule and make adjustments as necessary. Once the schedule is confirmed, the user can carry out tasks according to the schedule.

[1102] Specific examples

[1103] A specific scenario is shown below.

[1104] During a meeting, a user is verbally requested to complete a new marketing task. The user then uses their smartphone to type the request into text, attaching any related image files, and submitting it to the server.

[1105] The server receives the request and sends a prompt to the generative AI model, such as, "Your task is to create a marketing strategy for a new product. The image below contains detailed information." The generative AI model then responds with an analysis result, such as, "The key points are based on the graphs in the document. Additional materials are also required."

[1106] Based on the analysis results, the server sets the task priority to "high" and checks the user's schedule using the Google Calendar API. The optimal execution time is suggested as the morning of the following day. The suggested schedule is automatically added to Google Calendar for the user to view.

[1107] The user checks the schedule and accepts it if there are no problems, or manually adjusts it if there are any overlapping schedules. Once the schedule is confirmed, the user executes the task according to the specified time.

[1108] This system significantly reduces the time required for setting task priorities and adjusting schedules, thereby improving work efficiency. In addition, by linking the generative AI model with the schedule management device, task management is automated, allowing users to focus on their primary work.

[1109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1110] Step 1:

[1111] The user inputs the request details.

[1112] Specific operation: The user operates a device (smartphone or PC) to input the task request details. The input format can be text, images, audio, video, etc.

[1113] Input: Marketing project request details and image files of related materials.

[1114] Output: The input request data.

[1115] Step 2:

[1116] The terminal sends the request to the server.

[1117] Specific operation: When the user presses the input completion button, the terminal sends the request content data to the server.

[1118] Input: The requested data entered.

[1119] Output: The request data sent to the server.

[1120] Step 3:

[1121] The server receives the request and asks the generative AI model to analyze it.

[1122] Specific operation: The server processes the request content data received from the terminal, creates a prompt sentence for analyzing the request content, and sends it to the generative AI model.

[1123] Input: The request data sent to the server.

[1124] Output: A prompt to the generative AI model to analyze.

[1125] Step 4:

[1126] The generative AI model analyzes the request and extracts the task content.

[1127] Specific operation: The generative AI model receives the prompt, analyzes the input request, and extracts the necessary task information.

[1128] Input: A prompt to request the generative AI model to analyze.

[1129] Output: Analysis results including task content (e.g., task details and follow-up questions).

[1130] Step 5:

[1131] The server sets the priority of the tasks based on the analysis results.

[1132] Specific operation: Based on the analysis results obtained from the generative AI model, the server sets priorities based on task importance and deadlines.

[1133] Input: Analysis results of the generative AI model.

[1134] Output: The priority of the task (e.g. "High", "Medium", "Low").

[1135] Step 6:

[1136] The server obtains the user's current schedule from the schedule management device.

[1137] Specific operation: The server uses a schedule management API (e.g., Google Calendar API) to obtain the user's current schedule information.

[1138] Input: User authentication information and schedule management device API.

[1139] Output: The user's current schedule data.

[1140] Step 7:

[1141] The server suggests the best time to execute the task.

[1142] Specific operation: The server calculates and proposes the optimal task execution time based on the acquired schedule data and task priority.

[1143] Input: Task priority and user schedule data.

[1144] Output: Proposed task execution time.

[1145] Step 8:

[1146] The proposed execution time is reflected in the schedule management device.

[1147] Specific operation: The server adds the proposed task execution time to the schedule management device.

[1148] Input: Proposed task execution time.

[1149] Output: New scheduled tasks added to the scheduler.

[1150] Step 9:

[1151] The user reviews the schedule and adjusts it as needed.

[1152] Specific operation: The user checks the task execution time proposed by the schedule management device through the terminal and manually adjusts the time if necessary.

[1153] Input: A new scheduled task added to the schedule management device.

[1154] Output: The confirmed task execution time, or the task execution time adjusted by the user.

[1155] Step 10:

[1156] Execute tasks according to a schedule established by the user.

[1157] Specific Action: The user starts and executes a task at a specified time based on a fixed schedule.

[1158] Input: The confirmed task execution time.

[1159] Output: Completed tasks and their progress reports.

[1160] This concludes the detailed explanation of each processing step in the program for this system. This system allows users to significantly reduce the time it takes to set task priorities and adjust schedules, thereby improving work efficiency.

[1161] (Application example 1)

[1162] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1163] In today's factories, multiple processes are carried out simultaneously, making scheduling and prioritization complicated and difficult to manage efficiently. Furthermore, if factory equipment is not operated at the appropriate time, unnecessary waiting time and process delays occur, resulting in reduced production efficiency and increased operating costs.

[1164] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1165] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for linking with a schedule management device and proposing task execution times based on the priorities, and means for optimizing the schedule of work processes in the factory and controlling the operation of factory work equipment, thereby enabling automatic adjustment of schedules and efficient task management in the factory production process.

[1166] The "means for receiving the request content" is a device or function that takes in the request information such as text, images, audio, and video received from the user.

[1167] A "generative model" is a type of artificial intelligence algorithm used to analyze input data and extract specific information.

[1168] The "means for extracting task content" is a device or function that uses a generative model to identify a specific task and its details from the received request content.

[1169] The "means for automatically setting priorities" is a device or function that evaluates the importance and deadlines based on the extracted task contents and automatically determines the priority of the work.

[1170] A "schedule management device" is a device or system that manages the start and end times of tasks and appropriately adjusts a user's schedule.

[1171] "Means for optimizing the schedule of work processes in a factory and controlling the operation of factory work equipment" refers to a device or function that automatically controls the operation of factory work equipment to optimize the timing of each work process in a factory and efficiently carry out work.

[1172] To implement the present invention, an information processing system is required to efficiently manage factory work processes and their schedules. This system receives requests, analyzes them using a generative model, sets priorities based on the analysis, and works in conjunction with a schedule management device to optimize the operation of factory work equipment.

[1173] First, the user inputs the request details from their device. This request is input in the form of text, images, audio, video, etc., and sent to the server. The server then passes the received request details to the generative AI model and requests that it be analyzed. The generative AI model analyzes the request details and extracts the task details. The extracted task details include the task priority and required operation information.

[1174] Next, the server automatically sets priorities based on the extracted task content. These priorities are determined by the task's importance and deadline. Furthermore, the server works with a schedule management device to suggest optimal execution times. In this process, the server uses existing schedule management software, such as the Google Calendar API, to obtain the user's current schedule and adjust the optimal execution time for the new task.

[1175] The proposed schedule is added to the user's schedule management device and can be viewed by the user via a terminal. The user can review the proposed schedule and make adjustments as necessary. Factory equipment is automatically operated at the specified times according to the confirmed schedule. This operation is used, for example, for parts assembly and inspection work on a factory line.

[1176] As a concrete example, consider a scenario in which a factory worker is requested to perform a new task. The worker uses a tablet device to enter the request details as text, attach any relevant image files, and send it to the server. The server then uses a generative AI model to analyze the request and extract the task's importance and required materials. Based on the extracted information, the server sets the task's priority to "high," checks the worker's schedule using the Google Calendar API, and proposes that the task be completed the following morning. The proposed schedule is automatically added to Google Calendar and can be viewed by the worker on their tablet.

[1177] This system allows the factory's work processes to proceed smoothly and significantly reduces the time required for task prioritization and schedule management. An example of a prompt that a user might use when inputting their request into the system would be, "I'm requesting assembly work for a new part. I've attached a related image. It's of high importance." In this way, it is possible to significantly improve the factory's production efficiency.

[1178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1179] Step 1:

[1180] The user uses a terminal to input the request content. The request content can be input in the form of text, image, audio, video, etc. The input data is formatted appropriately according to the format and sent to the server. Input: Request content (text, image, audio, video) Output: Formatted request data

[1181] Specific operation: For example, the user inputs text and an image from a tablet device, such as "I would like to request assembly work for a new part. I have attached a related image." Then, the user presses the send button to send the data to the server.

[1182] Step 2:

[1183] The server sends the received request to the generative AI model and requests it to analyze it. The generative AI model analyzes the data and extracts the necessary task information. Input: Formatted request data Output: Detailed task information (e.g., task content, priority)

[1184] How it works: The server sends the formatted request data to the analysis API endpoint, and the generative AI model analyzes it. For example, it can obtain an analysis result such as "This image shows the assembly work of part A."

[1185] Step 3:

[1186] The server automatically sets task priorities based on detailed task information obtained from the generated AI model. Input: Detailed task information Output: Prioritized task data

[1187] Specific operation: The server evaluates the analysis results and sets priorities based on the importance and urgency of the tasks. For example, tasks that are judged to be of high importance are set to "High."

[1188] Step 4:

[1189] The server works with a schedule management device (e.g., Google Calendar API) to obtain the user's current schedule and propose new task execution times. Input: prioritized task data, user's current schedule. Output: proposed execution schedule.

[1190] Specific operation: The server uses the Google Calendar API to obtain the user's current schedule. Then, based on the priority, it selects an available time slot and suggests a time to execute the task. For example, it suggests executing the task in the morning of the following day.

[1191] Step 5:

[1192] The server adds the proposed schedule to the user's schedule management device, allowing the user to view it through their device. Input: Proposed execution schedule Output: Schedule added to the user's Google Calendar

[1193] Specific operation: The server sends an API request to add the proposed task schedule to Google Calendar. The schedule is displayed on the calendar in a format that the user can view on a tablet or other device.

[1194] Step 6:

[1195] The user confirms the proposed schedule. If necessary, the user can adjust the schedule. Input: Schedule added to Google Calendar Output: Schedule confirmed by the user

[1196] What happens: The user opens Google Calendar on their device, reviews the proposed task schedule, and, if necessary, changes or adjusts the schedule and finally confirms it.

[1197] Step 7:

[1198] Factory equipment is automatically operated at the specified time according to the confirmed schedule. Input: Confirmed schedule Output: Work execution status

[1199] Specific operation: Factory equipment automatically starts work based on the confirmed schedule. For example, assembly work for part A starts and finishes at the specified time.

[1200] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1201] This invention relates to a task management system that helps corporate employees and freelancers improve their work efficiency. In particular, it is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[1202] Program Description

[1203] This system starts with the user inputting the request details from the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is then sent from the terminal to the server.

[1204] The server temporarily stores the received data and sends it to the generative model for analysis. The generative model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[1205] The server then utilizes an emotion engine to recognize the user's emotional state. The emotion engine identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[1206] The server then uses the Google Calendar API to retrieve the user's current schedule, and, taking into account the priority and the user's emotional state, suggests the optimal time to execute the task and automatically adds it to the Google Calendar.

[1207] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[1208] Specific examples

[1209] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. The user uses their smartphone to type the request as text, attach any relevant image files, and send it to a server. The server then passes the request to a generative model, which analyzes the task. The user's emotional state (e.g., stress, anxiety, etc.) is also analyzed along with the analysis results.

[1210] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[1211] The proposed schedule is automatically added to Google Calendar and can be viewed by the user on their smartphone. The user can review the schedule and accept it if there are no problems, or manually adjust it if necessary. Once the schedule is confirmed, the user can carry out the tasks according to the schedule.

[1212] In this way, by combining the emotion engine, task management that takes into account the user's emotional state becomes possible, realizing more efficient and user-friendly task management. By linking the generative model with the Google Calendar API, task prioritization and schedule adjustment can be performed quickly, improving productivity.

[1213] The processing flow will be explained below.

[1214] Step 1:

[1215] A user receives a new task request. Using a device (PC or smartphone), the user inputs the request in text format and adds attachments (images, audio files, videos, etc.) as needed. This input data is sent from the device to the server.

[1216] Step 2:

[1217] The server receives the data sent by the user, temporarily stores the received data, and organizes the text data and attachments.

[1218] Step 3:

[1219] The server passes the received data to the generative model for analysis. The generative model uses multimodal capabilities to analyze all text, images, audio, and video to extract task content.

[1220] Step 4:

[1221] The generative model returns the analysis results, which may include detailed task content, unclear points, and follow-up questions. The server receives the analysis results and, if necessary, notifies the requester of any questions.

[1222] Step 5:

[1223] The server automatically sets the priority of each task based on the task information, which is determined based on the importance, deadline, and urgency of the request.

[1224] Step 6:

[1225] The server analyzes the user's emotional state using an emotion engine, which analyzes the user's input data and real-time feedback to identify the user's emotions.

[1226] Step 7:

[1227] The server adjusts task priorities and suggested execution times as needed based on the user's emotional state. For example, if the user is feeling stressed, the schedule is adjusted to avoid those times.

[1228] Step 8:

[1229] The server uses the Google Calendar API to retrieve the user's current schedule, which includes existing events and task information.

[1230] Step 9:

[1231] The server takes into account the user's schedule, priorities, and emotional state to suggest the optimal execution time for each task. The suggested execution times are automatically added to the user's Google Calendar.

[1232] Step 10:

[1233] The user will then review the proposed schedule on their device, which they can review in detail and manually adjust if necessary.

[1234] Step 11:

[1235] The server monitors the schedule and sends reminders when the task is about to be performed, helping users remember to perform the task.

[1236] Step 12:

[1237] Tasks are executed according to a schedule determined by the user. When a task is completed, the user can notify the server of the completion of the task from the terminal.

[1238] In this way, taking into account the user's emotional state enables more adaptive and efficient task management. By combining a generative model, an emotion engine, and the Google Calendar API, this system can improve the user's overall work efficiency.

[1239] Example 2

[1240] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1241] In conventional task management systems, task prioritization and schedule adjustments are performed without taking the user's emotional state into consideration, which often leads to problems such as stress and reduced efficiency. Furthermore, there is no automated response when the request content is unclear, which increases the burden on the user.

[1242] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1243] In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for analyzing the user's emotional state using an emotion recognition engine, means for adjusting task priorities and execution times based on the user's emotional state, and means for working in conjunction with a schedule management device to suggest task execution times based on the priorities and emotional state. This allows task prioritization and schedule adjustment to be performed automatically and optimally while taking the user's emotional state into consideration, thereby improving work efficiency and reducing stress.

[1244] "Request content" refers to input data that includes specific information and instructions that a user needs to perform a job or task.

[1245] A "generative model" is an algorithm or system that uses artificial intelligence technology to analyze received requests and extract task content.

[1246] "Task content" refers to the specific work or processing items that the user must perform, extracted from the request content.

[1247] "Priority" is an evaluation criterion that determines the order and importance of execution based on the importance and urgency of the task content.

[1248] An "emotion recognition engine" is a system or algorithm that analyzes a user's emotional state from input data and real-time feedback.

[1249] "User's emotional state" refers to the user's psychological state and emotions analyzed by the emotion recognition engine.

[1250] A "schedule management device" is an external system or application for managing task execution times and schedules.

[1251] A "task execution time" is a specific time period allotted to a user to perform a particular task.

[1252] This invention relates to a task management system for improving the work efficiency of corporate employees and freelance workers. It is characterized by analyzing the content of requests, automatically setting task priorities, proposing optimal execution times, and recognizing the user's emotional state and managing tasks based on that information.

[1253] The program for this system starts with the user inputting the request details on the terminal. The user can input the request details in text format, audio, images, video, etc., and can also add attachments in some cases. This data is sent from the terminal to the server.

[1254] The server temporarily stores the received data and sends it to the generative AI model for analysis. The generative AI model analyzes the received data and extracts the task content and necessary information. Based on the analysis results, the server automatically sets task priorities. Priorities are determined based on factors such as importance and deadlines.

[1255] The server then utilizes an emotion recognition engine to recognize the user's emotional state, which identifies the user's emotions by analyzing the user's input data and real-time feedback, and adjusts task priorities and suggested execution times based on the user's emotional state.

[1256] The server then uses the schedule management device's API to obtain the user's current schedule, and, taking into account the priority and the user's emotional state, proposes optimal task execution times and automatically adds them to the schedule management device.

[1257] The user can check the proposed schedule through their device and manually adjust it as necessary. Once the schedule is confirmed, the server monitors the schedule and sends reminders when the task execution time approaches. The user then executes the task according to the confirmed schedule.

[1258] Specific examples

[1259] For example, consider a scenario in which a user is verbally requested to complete a new task during a meeting. Using their smartphone, the user types the request as text and attaches any relevant image files, sending it to a server. The server then passes the request to a generative AI model, which analyzes the task. The user's emotional state (e.g., stress or anxiety) is also analyzed along with the analysis results.

[1260] The server sets the priority of a task as "high," but if it determines that the user is feeling very stressed, it will lower the priority or adjust the execution time. It also suggests appropriate task execution times based on the user's specific emotional state. For example, it may suggest avoiding times when the user is feeling stressed.

[1261] The proposed schedule is automatically added to the schedule management device and becomes available for the user to view on their smartphone. The user reviews the schedule and, if there are no particular problems, accepts it as is, making manual adjustments as necessary. Once the schedule is finalized, the user carries out tasks according to the schedule. In this way, combining an emotion recognition engine enables task management that takes the user's emotional state into account, resulting in even more efficient and user-friendly task management.

[1262] An example prompt is:

[1263] "User entered text:

[1264] I want to schedule a meeting for new project X next Monday at 3 PM. Please review the relevant materials and set the priority to high. Also, analyze the user's emotional state and adjust the schedule if necessary."

[1265] The above system utilizes a generative AI model and an emotion recognition engine to not only improve the efficiency of task management for users but also reduce emotional burden, thereby increasing work productivity.

[1266] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1267] Step 1:

[1268] The user enters the request details

[1269] Specific operation: The user uses their device (smartphone, tablet, PC) to input the details of a new task request. Input formats include text, audio, images, and video. Specifically, the user enters text such as "Create materials for Project X" and attaches the relevant PDF file.

[1270] Input: Request details entered by the user (text, audio, images, videos, etc.) and attachments

[1271] Output: The requested data and attached files are sent from the device to the server.

[1272] Step 2:

[1273] The device sends data to the server, and the server stores the data.

[1274] Specific operation: The terminal sends the input request and attached file to the server. The server receives this data and temporarily stores it in a database.

[1275] Input: Request content and attachments sent from the device

[1276] Output: The request details and attachments are saved in the database.

[1277] Step 3:

[1278] The server requests the generated AI model to analyze the data.

[1279] Specific operation: The server passes the saved request content and attachments to the generative AI model and requests text analysis. The generative AI model analyzes the request text and attachments and extracts specific task information.

[1280] Input: Saved request and attachments

[1281] Output: Parsed task content

[1282] Step 4:

[1283] The server sets the priority of the task

[1284] Specific operation: The server sets the priority of tasks based on the analysis results from the generative AI model. In doing so, it considers the urgency, importance, deadline, etc. of the task and determines it as "high priority."

[1285] Input: Analysis results from a generative AI model

[1286] Output: Prioritized task information

[1287] Step 5:

[1288] The server uses an emotion recognition engine to analyze the user's emotional state.

[1289] Specific operation: The server analyzes the user's latest input data and real-time feedback using an emotion recognition engine. For example, using the text entered by the user and real-time facial expression images, the emotion recognition engine determines that the user is feeling stressed.

[1290] Input: Latest user input data and real-time feedback

[1291] Output: Parsed user's emotional state

[1292] Step 6:

[1293] The server adjusts task priorities and execution times

[1294] Specific operation: The server receives the results of the emotion recognition engine, considers the user's stress level, and adjusts the task priority and execution time. Specifically, it suggests execution times that avoid high-stress times.

[1295] Input: Emotion recognition engine results, prioritized task information

[1296] Output: Adjusted task priorities and execution times

[1297] Step 7:

[1298] The server automatically adds a schedule using the schedule management device's API.

[1299] Specific operation: The server uses the schedule management device's API to obtain the user's current schedule. Based on the obtained schedule, the server automatically adds the optimal time slot to the schedule management device, taking into account task priority and emotional state.

[1300] Input: User's current schedule, adjusted task priority and execution time

[1301] Output: The proposed task execution times are automatically added to the scheduler.

[1302] Step 8:

[1303] User reviews proposed schedule and adjusts as needed

[1304] Specific operation: The user checks the proposed schedule on the device. For example, they open a schedule management app on their smartphone and see that "Create materials for Project X" has been added. They can manually adjust the time as needed.

[1305] Input: Schedule information provided by the server

[1306] Output: Schedule approved and adjusted by user

[1307] Step 9:

[1308] The server sends the reminder

[1309] Specific operation: The server sends a reminder to the user when the task execution time approaches. Specifically, a push notification is displayed on the smartphone saying, "Please start creating materials for Project X."

[1310] Input: Confirmed schedule information

[1311] Output: Reminder notification sent to user

[1312] Step 10:

[1313] A user performs a task

[1314] Specific behavior: After receiving the reminder, the user starts and completes the task according to the confirmed schedule. For example, according to the schedule management app, the user starts preparing documents and completes the task at the scheduled time.

[1315] Input: Reminder sent

[1316] Output: Completed tasks

[1317] (Application example 2)

[1318] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1319] Conventional factory task management relies on manual work and human judgment, making it difficult to efficiently prioritize tasks and optimize execution schedules. Furthermore, task management does not take into account the emotional state of workers, resulting in increased worker fatigue and stress and reduced productivity. The purpose of this invention is to solve these problems and provide a more effective and user-friendly task management system.

[1320] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving request content, means for analyzing the received request content using a generative model and extracting task content, means for automatically setting priorities based on the task content, means for recognizing emotional states and managing tasks based on that information, and means for working with a schedule management device to propose task execution times based on the priorities and emotional states. This improves work efficiency in factories and enables flexible task management that takes into account the emotional states of workers.

[1321] The "request content" is information that requests or instructs the execution of a task, and is provided in the form of text, audio, images, video, or the like.

[1322] A "generative model" is a model that uses machine learning and artificial intelligence techniques to analyze data and extract useful information.

[1323] "Task content" refers to the details and necessary information of a specific task or process extracted from the analysis results of the request content.

[1324] "Priority" is a criterion for determining the execution priority of a task relative to other tasks based on the importance and urgency of the task.

[1325] "Emotional state" refers to the user's psychological or physiological emotional state, including stress, fatigue, and the like.

[1326] "Task management" refers to activities that support the effective execution of tasks, such as planning, prioritizing, scheduling, and progress management of tasks.

[1327] A "schedule management device" is a device or system for recording, adjusting, and managing task execution times.

[1328] In order to put this invention into practice, it is first necessary to build a system in which a server, a terminal, and a user work in cooperation with each other.

[1329] The server includes the following means:

[1330] 1. Method of receiving request content: The user inputs the task request content from a device such as a smartphone, smart glasses, or head-mounted display. The input format can be a variety of formats, including text, audio, images, and video. The request content is sent from the device to the server.

[1331] 2. Generative model analysis: The server temporarily stores the received request and sends it to the generative model (machine learning model) for analysis. Here, the task content and necessary information are extracted, and the next step is taken based on the results.

[1332] 3. Priority setting method: Priorities are automatically set based on the importance and urgency of tasks. This priority setting is performed using an evaluation algorithm that runs on the server.

[1333] 4. Emotional state recognition: The emotion engine recognizes the user's emotional state by analyzing the user's input data and real-time feedback. If the user is in a stressful state, the priority is adjusted.

[1334] 5. Schedule suggestion method: Works with schedule management devices (such as Google Calendar API) to suggest optimal task execution times. Schedules based on priorities and emotional state are automatically added to the calendar.

[1335] The terminal has the following features:

[1336] 1. Task input interface: Provides an interface for users to input task requests. This can be a smartphone, smart glasses, or a head-mounted display.

[1337] 2. Schedule Review Interface: Includes an interface that allows the user to review the proposed schedule and manually adjust it if necessary.

[1338] The user does the following:

[1339] 1. Task request: The user inputs the task request details using the terminal, which are then sent to the server.

[1340] 2. Providing feedback: Providing feedback on the execution of schedules and tasks generated by the server.

[1341] As a concrete example, consider a scenario in which a factory worker is asked to perform "maintenance work on a new machine" using smart glasses. In this case, the worker inputs the task details by voice through the smart glasses. The voice data is sent to the server, and the task details are analyzed by a generative model. Next, an emotion engine checks the worker's emotional state, and if the worker is feeling stressed, the priority is adjusted based on that information. Finally, the optimal execution time is suggested using the Google Calendar API and displayed on the smart glasses.

[1342] Example prompt sentence:

[1343] "I've been asked to carry out maintenance work on a new machine. The details are to check the inspection list and related manuals."

[1344] In this way, combining a generative AI model with an emotion engine enables more efficient and flexible task management than conventional task management systems.

[1345] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1346] Step 1:

[1347] The user uses a device to input the task request. The input can be text, voice, image, or video. For example, a user can use smart glasses to input voice input such as "Request maintenance work on a new machine." This request is then sent from the device to the server.

[1348] Step 2:

[1349] The server temporarily stores the received request (voice data). It then sends the request to the generative AI model, requesting it to analyze the task content. The generative AI model analyzes the voice data, extracts the necessary information, and returns it to the server as the task content. Input: Request content (voice data), Output: Task content (analysis results)

[1350] Step 3:

[1351] The server evaluates the importance and urgency of the tasks based on the task content obtained from the generative AI model, and automatically sets priorities. Priority is set using an algorithm that takes into account the importance and urgency of the task content, resource usage, etc. Input: Task content (analysis results), Output: Priority

[1352] Step 4:

[1353] The server uses an emotion engine to recognize the user's emotional state. The emotion engine analyzes the user's emotional state (stress, etc.) from the voice data and returns the results to the server. Input: Request content (voice data), Output: Emotional state (analysis results)

[1354] Step 5:

[1355] The server works with a schedule management device (such as Google Calendar API) based on the priority and emotional state to propose the optimal task execution time. Here, a time period with high priority and when the user is not feeling stressed is selected and added to the Google Calendar as a schedule. Input: Priority, emotional state, Output: Proposed execution time (schedule)

[1356] Step 6:

[1357] The user uses the device to check the proposed schedule. The schedule is displayed through the smart glasses, and the user manually adjusts it as needed. Once the user approves the schedule, the server confirms it and begins monitoring. Input: Proposed execution time (schedule), Output: Confirmed schedule

[1358] Step 7:

[1359] The server monitors the confirmed schedule and sends reminders when the task execution time approaches. The reminders are sent to the terminal, and the user executes the task according to the confirmed schedule. Input: Confirmed schedule, Output: Reminder notification

[1360] In this way, the entire process from inputting the request details to finalizing the schedule and executing the task becomes clear at each step. This improves work efficiency in the factory and enables flexible task management that takes into account the emotional state of the user.

[1361] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1362] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1363] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1364] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1365] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1366] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1367] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1368] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1369] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1370] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1371] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1372] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1373] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1374] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1375] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1376] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1377] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1378] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1379] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1380] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1381] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1382] The following is further disclosed regarding the above embodiment.

[1383] (Claim 1)

[1384] An information processing device,

[1385] A means for receiving the request content;

[1386] A means for analyzing received request content and extracting task content using a generative model;

[1387] A means for automatically setting priorities based on task content;

[1388] a means for suggesting task execution times based on priority in cooperation with the schedule management device;

[1389] A system including:

[1390] (Claim 2)

[1391] 10. The system of claim 1, further comprising means for automatically modifying the execution schedule to optimize task execution times in cooperation with the schedule management device.

[1392] (Claim 3)

[1393] 2. The system according to claim 1, further comprising means for automatically generating and transmitting a question to the requester when there is a contradiction or an unclear point in the request content.

[1394] "Example 1"

[1395] (Claim 1)

[1396] A means for a user to input request details and send them from a terminal;

[1397] A means for the server to receive the request content, analyze it using the generative AI model, and extract the task content;

[1398] A means for the server to automatically set priorities based on task content;

[1399] a means for the server to acquire a user's schedule through a schedule management device and propose a task execution time;

[1400] A means for reflecting the proposed execution time in the schedule management device so that the user can check and adjust it;

[1401] A system including:

[1402] (Claim 2)

[1403] 10. The system according to claim 1, further comprising means for the server to cooperate with the schedule management device to automatically modify the execution schedule to optimize task execution times.

[1404] (Claim 3)

[1405] 2. The system according to claim 1, further comprising means for the server to automatically generate and transmit a question to the requester when there is a contradiction or an unclear point in the request content.

[1406] "Application Example 1"

[1407] (Claim 1)

[1408] A means for receiving the request content;

[1409] A means for analyzing received request content and extracting task content using a generative model;

[1410] A means for automatically setting priorities based on task content;

[1411] a means for suggesting task execution times based on priority in cooperation with the schedule management device;

[1412] a means for optimizing the schedule of work processes in a factory and controlling the operation of factory work equipment;

[1413] A system including:

[1414] (Claim 2)

[1415] 10. The system of claim 1, further comprising means for automatically modifying the execution schedule to optimize task execution times in cooperation with the schedule management device.

[1416] (Claim 3)

[1417] 2. The system according to claim 1, further comprising means for automatically generating and transmitting a question to the requester when there is a contradiction or an unclear point in the request content.

[1418] "Example 2: Combining Emotion Engines"

[1419] (Claim 1)

[1420] A means for receiving the request content;

[1421] A means for analyzing received request content and extracting task content using a generative model;

[1422] A means for automatically setting priorities based on task content;

[1423] means for analyzing the emotional state of a user using an emotion recognition engine;

[1424] A means for adjusting task priorities and execution times based on the user's emotional state;

[1425] a means for suggesting task execution times based on priority and emotional state in cooperation with the schedule management device;

[1426] A system including:

[1427] (Claim 2)

[1428] 10. The system of claim 1, further comprising means for automatically modifying the execution schedule to optimize task execution times in cooperation with the schedule management device.

[1429] (Claim 3)

[1430] 2. The system according to claim 1, further comprising means for automatically generating and transmitting a question to the requester when there is a contradiction or an unclear point in the request content.

[1431] "Application example 2 when combining emotion engines"

[1432] (Claim 1)

[1433] A means for receiving the request content;

[1434] A means for analyzing received request content and extracting task content using a generative model;

[1435] A means for automatically setting priorities based on task content;

[1436] A means of recognizing emotional states and managing tasks based on that information;

[1437] a means for suggesting task execution times based on priority and emotional state in cooperation with the schedule management device;

[1438] A system including:

[1439] (Claim 2)

[1440] 10. The system of claim 1, further comprising means for automatically modifying the execution schedule to optimize task execution times based on priorities and emotional states in cooperation with the schedule management device.

[1441] (Claim 3)

[1442] 2. The system according to claim 1, further comprising means for automatically generating and transmitting a question to the requester when there is a contradiction or an unclear point in the request content. [Explanation of symbols]

[1443] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. An information processing device, A means for receiving the request content; A means for analyzing received request content and extracting task content using a generative model; A means for automatically setting priorities based on task content; a means for suggesting task execution times based on priority in cooperation with the schedule management device; A system including:

2. 2. The system according to claim 1, further comprising means for automatically modifying the execution schedule to optimize task execution times in cooperation with the schedule management device.

3. 2. The system according to claim 1, further comprising means for automatically generating and transmitting a question to the requester when there is a contradiction or an unclear point in the request content.

Images