system

Abstract

The system according to this embodiment aims to streamline project task management and improve overall performance. [Solution] The system according to the embodiment comprises a meeting minutes generation unit, a task classification unit, a task assignment unit, a task registration unit, and a progress management unit. The meeting minutes generation unit generates meeting minutes from the content of meetings and telephone conversations. The task classification unit extracts tasks from the meeting minutes generated by the meeting minutes generation unit and classifies whether the tasks should be performed by a "human" or an "AI". The task assignment unit assigns the tasks classified by the task classification unit to the person in charge. The task registration unit registers the tasks assigned by the task assignment unit to a project management tool and a personal task management tool. The progress management unit manages the progress of the tasks registered by the task registration unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the task management of a project is insufficient, and there is a risk of a decrease in the overall performance.

[0005] The system according to the embodiment aims to improve the task management of a project and enhance the overall performance.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a meeting minutes generation unit, a task classification unit, a task assignment unit, a task registration unit, and a progress management unit. The meeting minutes generation unit generates meeting minutes from the content of meetings and telephone conversations. The task classification unit extracts tasks from the meeting minutes generated by the meeting minutes generation unit and classifies whether the tasks should be performed by a "human" or an "AI". The task assignment unit assigns the tasks classified by the task classification unit to the responsible person. The task registration unit registers the tasks assigned by the task assignment unit to a project management tool and a personal task management tool. The progress management unit manages the progress of the tasks registered by the task registration unit. [Effects of the Invention]

[0007] The system according to this embodiment can streamline project task management and improve overall performance. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. 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. Also, the database 24 and the communication I / F 26 are 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).

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The project hub system according to an embodiment of the present invention is a system for improving the efficiency of task management in project management. This project hub system automatically generates meeting minutes from the content of meetings and phone conversations, extracts tasks from the generated minutes, and classifies each task as to whether it should be performed by a "human" or an "AI". The classified tasks are assigned to the appropriate person in charge, and tasks to be performed by the AI ​​are automatically executed by the AI. Furthermore, tasks are registered in project management tools and personal task management tools, and the progress of tasks is constantly monitored and supported until the completion of the project. For example, reminders are sent before the deadline, consultations are accepted with task assignees, and tasks are reassigned as needed (changes in assignees or deadlines). With this system, managers and leaders can reduce the time they spend staring at management tools through AI-driven task classification and execution, and dedicate that time to communicating with team members. In addition, team members no longer have to worry about overlooking their tasks and can feel that the AI ​​is providing fair task assignments. As a result, the overall performance of the project is improved. Thus, the project hub system can improve the efficiency of task management in project management.

[0029] The project hub system according to this embodiment comprises a meeting minutes generation unit, a task classification unit, a task assignment unit, a task registration unit, and a progress management unit. The meeting minutes generation unit generates meeting minutes from the content of meetings and telephone conversations. For example, the meeting minutes generation unit uses speech recognition technology to convert audio data from meetings and telephone conversations into text data and automatically generates meeting minutes. The meeting minutes generation unit can also use natural language processing technology to summarize the content of conversations and extract important points. For example, the meeting minutes generation unit can extract frequently occurring keywords and phrases in conversations and create meeting minutes based on them. The task classification unit extracts tasks from the meeting minutes generated by the meeting minutes generation unit and classifies whether the tasks will be performed by a "human" or an "AI". For example, the task classification unit uses natural language processing technology to analyze the content of the meeting minutes and extract tasks. The task classification unit can also classify tasks as "human" or "AI" based on the content and complexity of the tasks. For example, the task classification unit classifies simple data entry and routine tasks as "AI" and tasks requiring complex judgment as "Human". The task assignment unit assigns the tasks classified by the task classification unit to the appropriate person. For example, the task assignment unit selects the optimal person by considering the skill sets and current workload of project members. The task assignment unit can also automate task assignment using AI. For example, the task assignment unit uses AI to analyze the skills and experience of project members and automatically select the optimal person. The task registration unit registers the tasks assigned by the task assignment unit to project management tools and personal task management tools. For example, the task registration unit can use JIRA or Trello as project management tools and Todoist or Microsoft® To-Do as personal task management tools. The task registration unit can also update the progress of tasks in real time and reflect it in project management tools and personal task management tools. The progress management unit manages the progress of tasks registered by the task registration unit. For example, the progress management unit monitors the progress of tasks in real time and sends reminders before the deadline.Furthermore, the progress management department can accept consultations from task assignees and reassign tasks as needed. For example, if a task is behind schedule, the progress management department can change the assignee or extend the deadline. As a result, the project hub system according to this embodiment can improve the efficiency of task management in project management.

[0030] The progress management unit may include a reminder unit that sends reminders before the due date. The reminder unit, for example, sends a reminder to the person in charge when the task due date is approaching. For example, the reminder unit can send a reminder one day or three days before the task due date. The reminder unit can also customize the method of sending reminders. For example, the reminder unit can send reminders using multiple methods, such as email, push notifications, and chat messages. Furthermore, the reminder unit can customize the content of the reminders. For example, the reminder unit can send a reminder message that includes information such as task details, due date, and progress status. This helps prevent task delays by sending reminders before the due date. Some or all of the above processes in the reminder unit may be performed using AI, for example, or not. For example, the reminder unit may use AI to analyze the task progress and send reminders at the appropriate time.

[0031] The progress management department may have a consultation department that receives inquiries from task assignees. The consultation department provides a point of contact for task assignees to consult about technical issues and progress. For example, the consultation department can receive inquiries through multiple methods, such as online chat, telephone, and email. The consultation department can also record the content of the inquiries and escalate them to the appropriate person in charge. For example, the consultation department can escalate inquiries about technical issues to a specialized technical support team. Furthermore, the consultation department can adjust the progress of tasks based on the content of the inquiries. For example, the consultation department can analyze the content of the task assignee's inquiry and extend the task deadline or change the person in charge as necessary. In this way, accepting inquiries from task assignees can ensure that tasks progress smoothly. Some or all of the above processes in the consultation department may be performed using AI, for example, or not using AI. For example, the consultation department may use AI to analyze the content of the inquiries and suggest appropriate responses.

[0032] The progress management unit may include a reassignment unit that reassigns tasks as needed. The reassignment unit reassigns tasks, for example, when a task is behind schedule or when the assigned person lacks the necessary resources. For example, the reassignment unit can monitor the task's progress in real time and change the assigned person as needed. The reassignment unit can also adjust the task's priority and due date. For example, if a task is behind schedule, the reassignment unit can set a higher priority and respond quickly. Furthermore, the reassignment unit can send notifications to the assigned person regarding the task reassignment. For example, when the assigned person for a task changes, the reassignment unit can send a notification to the new person in charge and share the task details and due date. This allows for the optimization of task progress through task reassignment. Some or all of the above processes in the reassignment unit may be performed using AI, for example, or not. For example, the reassignment unit may use AI to analyze the task's progress and select the most suitable person in charge.

[0033] The meeting minutes generation unit can automatically generate meeting minutes from the content of meetings and phone conversations. For example, the unit can use speech recognition technology to convert meeting and phone audio data into text data and automatically generate meeting minutes. For instance, the unit can analyze meeting audio data in real time and record what was said as text. Furthermore, the unit can use natural language processing technology to summarize conversations and extract key points. For example, it can extract frequently occurring keywords and phrases in conversations and create meeting minutes based on them. In addition, the unit can customize the format and content of the meeting minutes. For example, it can generate minutes in multiple formats, such as detailed records, summaries, and bullet points. This reduces the effort required to create meeting minutes by automatically generating meeting and phone conversations. Some or all of the above-described processes in the meeting minutes generation unit may be performed using AI, or without AI. For example, the meeting minutes generation unit can use AI to analyze audio data and automatically generate meeting minutes.

[0034] The task classification unit can extract tasks from generated meeting minutes and classify whether the tasks should be performed by a "human" or "AI". For example, the task classification unit can analyze the content of the meeting minutes using natural language processing technology to extract tasks. For instance, the task classification unit can detect keywords such as "task" or "work" in the meeting minutes, analyze the related context, and extract tasks. Furthermore, the task classification unit can classify tasks as "human" or "AI" based on their content and complexity. For example, the task classification unit can classify simple data entry and routine tasks as "AI" and tasks requiring complex judgment as "human". In addition, the task classification unit can classify tasks considering their priority and deadline. For example, the task classification unit can prioritize assigning urgent tasks to "humans" and routine tasks to "AI". By classifying tasks as "human" or "AI", tasks can be assigned to the appropriate person. Some or all of the processing described above in the task classification unit may be performed using AI, for example, or without AI. For example, the task classification unit may use AI to analyze the contents of the meeting minutes, extract tasks, and classify them.

[0035] The task assignment unit can assign classified tasks to assigned personnel. For example, the task assignment unit can select the most suitable personnel by considering the skill sets and current workload of project members. For instance, the task assignment unit can retrieve project members' skills and experience from a database and assign tasks based on that information. Furthermore, the task assignment unit can automate task assignment using AI. For example, the task assignment unit can use AI to analyze project members' skills and experience and automatically select the most suitable personnel. Additionally, the task assignment unit can assign tasks considering their priority and deadline. For example, the task assignment unit can prioritize high-priority tasks and postpone routine tasks. This improves the efficiency of task execution by assigning tasks to the appropriate personnel. Some or all of the above processes in the task assignment unit may be performed using AI, or not. For example, the task assignment unit can use AI to analyze task content and select the most suitable personnel.

[0036] The task registration unit can register assigned tasks to project management tools and personal task management tools. For example, the task registration unit can use JIRA or Trello as project management tools, and Todoist or Microsoft To-Do as personal task management tools. For instance, the task registration unit can automatically register task details, due dates, assignees, and other information to the project management tools and personal task management tools. Furthermore, the task registration unit can update task progress in real time and reflect this in the project management tools and personal task management tools. For example, the task registration unit can send notifications to the project management tools and personal task management tools whenever task progress is updated, ensuring that the latest information is reflected. Additionally, the task registration unit can register tasks considering their priority and due dates. For example, the task registration unit can prioritize high-priority tasks and postpone routine tasks. This makes task management easier by registering tasks in project management tools and personal task management tools. Some or all of the above-described processes in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the content of tasks and automatically register them in project management tools or personal task management tools.

[0037] The minutes generation unit can analyze the content of a meeting in real time and highlight statements to reflect them in the minutes. For example, the minutes generation unit's generation AI can analyze the content of the meeting in real time and highlight important statements in bold. For example, the minutes generation unit's generation AI can analyze the frequency and content of statements during the meeting and highlight important statements in bold. The minutes generation unit's generation AI can also analyze the content of statements, extract keywords, and highlight them in the minutes. For example, the minutes generation unit's generation AI can analyze the tone of statements and color-code parts that should be emphasized to reflect them in the minutes. Furthermore, the minutes generation unit can adjust the content of the minutes based on the importance of the statements. For example, the minutes generation unit can record important statements in detail and summarize other statements. This makes the content of the minutes clearer by highlighting important statements. Some or all of the above processing in the minutes generation unit may be performed using AI, for example, or without AI. For example, the minutes generation unit can use AI to analyze the content of a meeting, highlight important statements, and reflect them in the minutes.

[0038] The minutes generation unit can analyze the audio data of a meeting and generate minutes, color-coding them for each speaker. For example, the minutes generation unit's generation AI can analyze the audio data and generate minutes in different colors for each speaker. Furthermore, the minutes generation unit's generation AI can analyze the characteristics of each speaker's voice and reflect this in the minutes by color-coding. For example, the minutes generation unit's generation AI can color-code the minutes based on the speaker's position or role. In addition, the minutes generation unit can adjust the color-coding of the minutes based on the speaker's emotions. For example, if a speaker is excited, the minutes generation unit can generate minutes in calm colors. This makes the content of the minutes more visually understandable by color-coding them for each speaker. Some or all of the above-described processes in the minutes generation unit may be performed using AI, or without AI. For example, the minutes generation unit can use AI to analyze audio data and generate minutes, color-coding each speaker's contribution.

[0039] The minutes generation unit can analyze the content of a meeting and automatically link relevant past minutes. For example, the minutes generation unit's generation AI can analyze the content of a meeting and automatically link relevant past minutes. Furthermore, the minutes generation unit's generation AI can analyze keywords and search for and link relevant past minutes. For example, the minutes generation unit's generation AI can analyze the meeting's theme and automatically suggest relevant past minutes. In addition, the minutes generation unit can summarize the content of past minutes and link relevant sections. For example, the minutes generation unit can generate summaries of past minutes, highlighting and linking relevant sections. This makes the content of meetings more consistent by linking relevant past minutes. Some or all of the above processing in the minutes generation unit may be performed using AI, for example, or without AI. For example, the meeting minutes generation unit can use AI to analyze the content of a meeting and automatically link to relevant past meeting minutes.

[0040] The minutes generation unit can analyze the content of a meeting and automatically attach relevant external documents. For example, the minutes generation unit's generation AI can analyze the content of a meeting and automatically attach relevant external documents. Furthermore, the minutes generation unit's generation AI can analyze keywords and search for and attach relevant external documents. For example, the minutes generation unit's generation AI can analyze the meeting topic and automatically suggest relevant external documents. In addition, the minutes generation unit can summarize the content of external documents and attach them to the minutes. For example, the minutes generation unit can generate a summary of external documents, highlight the relevant parts, and attach it. This enriches the content of the minutes by attaching relevant external documents. Some or all of the above processes in the minutes generation unit may be performed using AI, or not. For example, the minutes generation unit's AI can analyze the content of a meeting and automatically attach relevant external documents.

[0041] The task classification unit can analyze the content of tasks and efficiently classify them by grouping similar tasks. For example, the task classification unit can use a generative AI to analyze the content of tasks and automatically group similar tasks. Furthermore, the task classification unit can use a generative AI to analyze keywords and efficiently classify similar tasks. For example, the task classification unit can use a generative AI to analyze the theme of tasks and group related tasks. In addition, the task classification unit can group tasks considering their priority and due date. For example, the task classification unit can prioritize and group high-priority tasks, postponing routine tasks. This makes task classification more efficient by grouping similar tasks. Some or all of the above-described processes in the task classification unit may be performed using AI, or without AI. For example, the task classification unit can use AI to analyze the content of tasks and group similar tasks.

[0042] The task classification unit can select the optimal classification method by referring to the task requester's past task history. For example, the task classification unit can use a generating AI to analyze the task requester's past task history and select the optimal classification method. Furthermore, the task classification unit can also use a generating AI to suggest an efficient classification method based on the task requester's past task history. For example, the task classification unit can use a generating AI to automatically select the optimal classification method based on the task requester's past task history. In addition, the task classification unit can classify tasks considering their priority and due date. For example, the task classification unit can prioritize high-urgency tasks and postpone routine tasks. This allows for the selection of the optimal classification method by referring to past task history. Some or all of the above-described processes in the task classification unit may be performed using AI, or without AI. For example, the task classification unit can use AI to analyze the task requester's past task history and select the optimal classification method.

[0043] The task classification unit can analyze the content of tasks and automatically link related projects. For example, the task classification unit can use a generating AI to analyze the content of tasks and automatically link related projects. The task classification unit can also use a generating AI to analyze keywords, search for related projects, and link them. For example, the task classification unit can use a generating AI to analyze the theme of a task and automatically suggest related projects. Furthermore, the task classification unit can link tasks while considering the progress and priority of the projects. For example, the task classification unit can prioritize linking projects that are behind schedule and postpone routine tasks. This streamlines task management by linking related projects. Some or all of the above processes in the task classification unit may be performed using AI, or not. For example, the task classification unit can use AI to analyze the content of tasks and automatically link related projects.

[0044] The task classification unit can analyze the content of a task and automatically suggest relevant external resources. For example, the task classification unit can use a generative AI to analyze the task content and automatically suggest relevant external resources. Furthermore, the task classification unit can use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the task classification unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. In addition, the task classification unit can summarize the content of external resources and associate them with tasks. For example, the task classification unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task execution by suggesting relevant external resources. Some or all of the above processing in the task classification unit may be performed using AI, or without AI. For example, the task classification unit can use AI to analyze the content of a task and automatically suggest relevant external resources.

[0045] The task assignment unit can analyze the content of a task and select the most suitable person to assign it based on the person's skill set. For example, the task assignment unit can use a generating AI to analyze the content of a task and select the most suitable person to assign it based on the person's skill set. The task assignment unit can also use a generating AI to analyze keywords and suggest the most suitable person to assign it based on the person's skill set. For example, the task assignment unit can use a generating AI to analyze the theme of a task and automatically select the most suitable person to assign it based on the person's skill set. Furthermore, the task assignment unit can also assign tasks while considering the current workload of the person assigning them. For example, the task assignment unit can select the most suitable person by considering the current number of tasks and working hours of the person assigning it. This improves the efficiency of task execution by selecting the most suitable person based on their skill set. Some or all of the above-described processes in the task assignment unit may be performed using AI, or without AI. For example, the task assignment unit can use AI to analyze the content of a task and select the most suitable person to assign it based on the person's skill set.

[0046] The task assignment unit can select the optimal assignment method by referring to the past collaboration history of the task requester and assignee. For example, the task assignment unit can use a generating AI to analyze the past collaboration history of the task requester and assignee and select the optimal assignment method. The task assignment unit can also use a generating AI to refer to the past collaboration history of the task requester and assignee and propose an efficient assignment method. For example, the task assignment unit can use a generating AI to automatically select the optimal assignment method based on the past collaboration history of the task requester and assignee. Furthermore, the task assignment unit can also assign tasks considering their priority and due date. For example, the task assignment unit can prioritize assigning high-priority tasks and postpone routine tasks. This allows for the selection of the optimal assignment method by referring to past collaboration history. Some or all of the above-described processes in the task assignment unit may be performed using AI, for example, or without AI. For example, the task assignment unit can use AI to analyze the past collaboration history between task requesters and assignees and select the optimal assignment method.

[0047] The task assignment unit can analyze the content of a task and assign it considering the current workload of the person in charge. For example, the task assignment unit can use a generating AI to analyze the content of a task and assign it considering the current workload of the person in charge. Furthermore, the task assignment unit can use a generating AI to analyze keywords and propose the optimal assignment considering the workload of the person in charge. For example, the task assignment unit can use a generating AI to analyze the theme of a task and automatically make the optimal assignment considering the workload of the person in charge. In addition, the task assignment unit can assign tasks considering the person in charge's skill set and experience. For example, the task assignment unit can retrieve the person in charge's skill set and experience from a database and assign tasks based on that. This improves the efficiency of task execution by assigning tasks while considering the workload of the person in charge. Some or all of the above-described processes in the task assignment unit may be performed using AI, or not. For example, the task assignment unit can use AI to analyze the content of a task and assign it considering the workload of the person in charge.

[0048] The task assignment unit can analyze the content of a task and automatically suggest relevant external resources. For example, the task assignment unit can use a generative AI to analyze the content of a task and automatically suggest relevant external resources. Furthermore, the task assignment unit can use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the task assignment unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. In addition, the task assignment unit can summarize the content of external resources and associate them with tasks. For example, the task assignment unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task execution by suggesting relevant external resources. Some or all of the above processing in the task assignment unit may be performed using AI, or without AI. For example, the task assignment unit can use AI to analyze the content of a task and automatically suggest relevant external resources.

[0049] The task registration unit can analyze the content of a task and automatically link it to relevant project management tools. For example, the task registration unit can use a generating AI to analyze the task content and automatically link it to relevant project management tools. The task registration unit can also use a generating AI to analyze keywords, search for relevant project management tools, and link them. For example, the task registration unit can use a generating AI to analyze the task's theme and automatically suggest relevant project management tools. Furthermore, the task registration unit can summarize the content of project management tools and associate it with tasks. For example, the task registration unit can generate a summary of project management tools, highlight the relevant parts, and link them. This streamlines task management by linking to relevant project management tools. Some or all of the above processing in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the task content and automatically link it to relevant project management tools.

[0050] The task registration unit can analyze the content of a task and automatically link it to relevant personal task management tools. For example, the task registration unit can use a generating AI to analyze the task content and automatically link it to relevant personal task management tools. The task registration unit can also use a generating AI to analyze keywords, search for relevant personal task management tools, and link them. For example, the task registration unit can use a generating AI to analyze the task's theme and automatically suggest relevant personal task management tools. Furthermore, the task registration unit can summarize the content of personal task management tools and associate it with the task. For example, the task registration unit can generate a summary of personal task management tools, highlight the relevant parts, and link them. This streamlines task management by linking to relevant personal task management tools. Some or all of the above processing in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the task content and automatically link it to relevant personal task management tools.

[0051] The task registration unit can analyze the content of a task and automatically suggest relevant external resources. For example, the task registration unit can use a generating AI to analyze the task content and automatically suggest relevant external resources. Furthermore, the task registration unit can use a generating AI to analyze keywords and search for and suggest relevant external resources. For example, the task registration unit can use a generating AI to analyze the task's theme and automatically suggest relevant external resources. In addition, the task registration unit can summarize the content of external resources and associate them with the task. For example, the task registration unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task execution by suggesting relevant external resources. Some or all of the above-described processes in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the task content and automatically suggest relevant external resources.

[0052] The task registration unit can analyze the content of a task and automatically link related past tasks. For example, the task registration unit can use a generating AI to analyze the content of a task and automatically link related past tasks. The task registration unit can also use a generating AI to analyze keywords and search for and link related past tasks. For example, the task registration unit can use a generating AI to analyze the theme of a task and automatically suggest related past tasks. Furthermore, the task registration unit can summarize the content of past tasks and link the relevant parts. For example, the task registration unit can generate summaries of past tasks, highlight the relevant parts, and link them. This streamlines task management by linking related past tasks. Some or all of the above processing in the task registration unit may be performed using AI, or without AI. For example, the task registration unit can use AI to analyze the content of a task and automatically link related past tasks.

[0053] The progress management unit can analyze task progress in real time and highlight important progress. For example, the progress management unit can use a generating AI to analyze task progress in real time and highlight important progress in bold. The progress management unit can also use a generating AI to analyze progress, extract keywords, and highlight them. For example, the progress management unit can use a generating AI to analyze the tone of progress and color-code the parts that should be emphasized. Furthermore, the progress management unit can adjust progress based on the importance of the progress. For example, the progress management unit can record important progress in detail and summarize other progress. This makes task progress clearer by highlighting important progress. Some or all of the above processes in the progress management unit may be performed using AI, for example, or not using AI. For example, the progress management unit can use AI to analyze task progress and highlight important progress.

[0054] The progress management unit can analyze the progress of tasks and automatically link to relevant project management tools. For example, the progress management unit can use a generating AI to analyze the progress of tasks and automatically link to relevant project management tools. Furthermore, the progress management unit can use a generating AI to analyze keywords, search for relevant project management tools, and link to them. For example, the progress management unit can use a generating AI to analyze the theme of a task and automatically suggest relevant project management tools. In addition, the progress management unit can summarize the content of project management tools and associate them with tasks. For example, the progress management unit can generate a summary of project management tools, highlight the relevant parts, and link them. This streamlines task progress management by linking to relevant project management tools. Some or all of the above processes in the progress management unit may be performed using AI, or not. For example, the progress management unit can use AI to analyze the progress of tasks and automatically link to relevant project management tools.

[0055] The progress management unit can analyze the progress of tasks and automatically suggest relevant external resources. For example, the progress management unit can use a generative AI to analyze the progress of tasks and automatically suggest relevant external resources. The progress management unit can also use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the progress management unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. Furthermore, the progress management unit can summarize the content of external resources and associate them with tasks. For example, the progress management unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task progress by suggesting relevant external resources. Some or all of the above processes in the progress management unit may be performed using AI, for example, or without AI. For example, the progress management unit can use AI to analyze the progress of tasks and automatically suggest relevant external resources.

[0056] The progress management unit can analyze the progress of tasks and automatically link relevant past progress data. For example, the progress management unit can use a generating AI to analyze the progress of tasks and automatically link relevant past progress data. Furthermore, the progress management unit can use a generating AI to analyze keywords and search for and link relevant past progress data. For example, the progress management unit can use a generating AI to analyze the theme of a task and automatically suggest relevant past progress data. In addition, the progress management unit can summarize the content of past progress data and link relevant sections. For example, the progress management unit can generate a summary of past progress data, highlight relevant sections, and link them. This streamlines task progress management by linking relevant past progress data. Some or all of the above processes in the progress management unit may be performed using AI, or not. For example, the progress management unit can use AI to analyze the progress of tasks and automatically link relevant past progress data.

[0057] The reminder function can analyze task due dates in real time and highlight important due dates in reminders. For example, the reminder function can use a generation AI to analyze task due dates in real time and highlight important due dates in bold. The reminder function can also use a generation AI to analyze due dates, extract keywords, and highlight them. For example, the reminder function can use a generation AI to analyze the tone of due dates and color-code the parts that should be emphasized in reminders. Furthermore, the reminder function can adjust the content of reminders based on the importance of the due dates. For example, the reminder function can record important due dates in detail and summarize other due dates. This streamlines task due date management by highlighting important due dates. Some or all of the above processing in the reminder function may be performed using AI, for example, or without AI. For example, the reminder function can use AI to analyze task due dates and highlight important due dates in reminders.

[0058] The reminder unit can analyze task due dates and automatically suggest relevant external resources. For example, the reminder unit's generation AI can analyze task due dates and automatically suggest relevant external resources. The reminder unit can also have its generation AI analyze keywords and search for and suggest relevant external resources. For example, the reminder unit's generation AI can analyze the task theme and automatically suggest relevant external resources. Furthermore, the reminder unit can summarize the content of external resources and associate them with tasks. For example, the reminder unit can generate summaries of external resources, highlighting relevant sections and suggesting them. This streamlines task due date management by suggesting relevant external resources. Some or all of the above processing in the reminder unit may be performed using AI, or without AI. For example, the reminder unit's AI can analyze task due dates and automatically suggest relevant external resources.

[0059] The consultation reception unit can analyze consultation content in real time and highlight important consultations. For example, the consultation reception unit can use a generation AI to analyze consultation content in real time and highlight important consultations in bold. For example, the consultation reception unit can use a generation AI to analyze consultation content in real time and highlight important consultations in bold. The consultation reception unit can also use a generation AI to analyze consultation content, extract keywords, and highlight them. For example, the consultation reception unit can use a generation AI to analyze the tone of the consultation and color-code the parts that should be emphasized. Furthermore, the consultation reception unit can adjust the content of consultations based on their importance. For example, the consultation reception unit can record important consultations in detail and summarize other consultations. This makes the consultation content clearer by highlighting important consultations. Some or all of the above processing in the consultation reception unit may be performed using AI, for example, or without AI. For example, the consultation reception unit can use AI to analyze consultation content and highlight important consultations.

[0060] The consultation reception department can analyze the consultation content and automatically suggest relevant external resources. For example, the consultation reception department can use a generative AI to analyze the consultation content and automatically suggest relevant external resources. The consultation reception department can also use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the consultation reception department can use a generative AI to analyze the consultation theme and automatically suggest relevant external resources. Furthermore, the consultation reception department can summarize the content of external resources and relate them to the consultation. For example, the consultation reception department can generate a summary of external resources, highlight the relevant parts, and suggest them. This enriches the consultation content by suggesting relevant external resources. Some or all of the above processing in the consultation reception department may be performed using AI, for example, or without AI. For example, the consultation reception department can use AI to analyze the consultation content and automatically suggest relevant external resources.

[0061] The reassignment unit can analyze the progress of tasks in real time and determine the need for reassignment. For example, the reassignment unit can use a generation AI to analyze the progress of tasks in real time and determine the need for reassignment. The reassignment unit can also use a generation AI to analyze the progress and automatically suggest tasks that need to be reassigned. For example, the reassignment unit can use a generation AI to analyze the themes of the progress and determine the need for reassignment. Furthermore, the reassignment unit can change the person in charge of a task based on the need for reassignment. For example, the reassignment unit can prioritize the reassignment of tasks that are behind schedule and postpone routine tasks. This ensures that tasks progress smoothly by determining the need for reassignment. Some or all of the above processes in the reassignment unit may be performed using AI, for example, or without AI. For example, the reassignment unit can use AI to analyze the progress of tasks and determine the need for reassignment.

[0062] The reallocation unit can analyze the progress of a task and automatically suggest relevant external resources. For example, the reallocation unit can use a generative AI to analyze the progress of a task and automatically suggest relevant external resources. The reallocation unit can also use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the reallocation unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. Furthermore, the reallocation unit can summarize the content of external resources and associate them with the task. For example, the reallocation unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This allows the task to progress smoothly by suggesting relevant external resources. Some or all of the above processing in the reallocation unit may be performed using AI, for example, or without AI. For example, the reallocation unit can use AI to analyze the progress of a task and automatically suggest relevant external resources.

[0063] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0064] The project hub system can also include a resource addition unit that analyzes task progress and automatically adds resources to tasks that are behind schedule. For example, the resource addition unit can detect tasks that are behind schedule and allocate additional personnel or AI resources. Furthermore, the resource addition unit can automatically select members with the necessary skill sets for tasks that are behind schedule and add them to the task. In addition, the resource addition unit can optimize task progress by allocating additional resources to tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0065] The project hub system can also include a reminder unit that analyzes task progress and automatically sends reminders to tasks that are behind schedule. For example, the reminder unit can detect tasks that are behind schedule and send reminders to the responsible person. Furthermore, the reminder unit can adjust the frequency of reminders for tasks that are behind schedule. In addition, the reminder unit can customize the content of reminders for tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0066] The project hub system can also include a resource addition unit that analyzes task progress and automatically adds resources to tasks that are behind schedule. For example, the resource addition unit can detect tasks that are behind schedule and allocate additional personnel or AI resources. Furthermore, the resource addition unit can automatically select members with the necessary skill sets for tasks that are behind schedule and add them to the task. In addition, the resource addition unit can optimize task progress by allocating additional resources to tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0067] The project hub system can also include a reminder unit that analyzes task progress and automatically sends reminders to tasks that are behind schedule. For example, the reminder unit can detect tasks that are behind schedule and send reminders to the responsible person. Furthermore, the reminder unit can adjust the frequency of reminders for tasks that are behind schedule. In addition, the reminder unit can customize the content of reminders for tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0068] The project hub system can also include a resource addition unit that analyzes task progress and automatically adds resources to tasks that are behind schedule. For example, the resource addition unit can detect tasks that are behind schedule and allocate additional personnel or AI resources. Furthermore, the resource addition unit can automatically select members with the necessary skill sets for tasks that are behind schedule and add them to the task. In addition, the resource addition unit can optimize task progress by allocating additional resources to tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0069] The following briefly describes the processing flow for example form 1.

[0070] Step 1: The minutes generation unit generates meeting minutes based on the content of meetings and phone conversations. For example, it uses speech recognition technology to convert audio data from meetings and phone calls into text data and automatically generates meeting minutes. It can also use natural language processing technology to summarize the conversation content and extract important points. For example, it can extract frequently occurring keywords and phrases in the conversation and create meeting minutes based on them. Step 2: The task classification unit extracts tasks from the meeting minutes generated by the meeting minutes generation unit and classifies whether the tasks should be performed by a "human" or an "AI". For example, it may use natural language processing technology to analyze the content of the meeting minutes and extract tasks. Furthermore, based on the content and complexity of the tasks, it classifies simple data entry and routine tasks as "AI" tasks and tasks requiring complex judgment as "human" tasks. Step 3: The task assignment unit assigns tasks classified by the task classification unit to the appropriate person. For example, it selects the optimal person by considering the skill sets and current workload of the project members. Task assignment can also be automated using AI. For example, the AI ​​analyzes the skills and experience of the project members and automatically selects the optimal person. Step 4: The task registration unit registers the tasks assigned by the task assignment unit to the project management tool and the personal task management tool. For example, JIRA or Trello can be used as the project management tool, and Todoist or Microsoft To-Do can be used as the personal task management tool. It is also possible to update the task progress in real time and reflect it in the project management tool and the personal task management tool. Step 5: The progress management unit manages the progress of tasks registered by the task registration unit. For example, it monitors task progress in real time and sends reminders before the deadline. It can also accept consultations from task assignees and reassign tasks as needed. For example, if a task is behind schedule, the assignee can be changed or the deadline extended.

[0071] (Example of form 2) The project hub system according to an embodiment of the present invention is a system for improving the efficiency of task management in project management. This project hub system automatically generates meeting minutes from the content of meetings and phone conversations, extracts tasks from the generated minutes, and classifies each task as to whether it should be performed by a "human" or an "AI". The classified tasks are assigned to the appropriate person in charge, and tasks to be performed by the AI ​​are automatically executed by the AI. Furthermore, tasks are registered in project management tools and personal task management tools, and the progress of tasks is constantly monitored and supported until the completion of the project. For example, reminders are sent before the deadline, consultations are accepted with task assignees, and tasks are reassigned as needed (changes in assignees or deadlines). With this system, managers and leaders can reduce the time they spend staring at management tools through AI-driven task classification and execution, and dedicate that time to communicating with team members. In addition, team members no longer have to worry about overlooking their tasks and can feel that the AI ​​is providing fair task assignments. As a result, the overall performance of the project is improved. Thus, the project hub system can improve the efficiency of task management in project management.

[0072] The project hub system according to this embodiment comprises a meeting minutes generation unit, a task classification unit, a task assignment unit, a task registration unit, and a progress management unit. The meeting minutes generation unit generates meeting minutes from the content of meetings and telephone conversations. For example, the meeting minutes generation unit uses speech recognition technology to convert audio data from meetings and telephone conversations into text data and automatically generates meeting minutes. The meeting minutes generation unit can also use natural language processing technology to summarize the content of conversations and extract important points. For example, the meeting minutes generation unit can extract frequently occurring keywords and phrases in conversations and create meeting minutes based on them. The task classification unit extracts tasks from the meeting minutes generated by the meeting minutes generation unit and classifies whether the tasks will be performed by a "human" or an "AI". For example, the task classification unit uses natural language processing technology to analyze the content of the meeting minutes and extract tasks. The task classification unit can also classify tasks as "human" or "AI" based on the content and complexity of the tasks. For example, the task classification unit classifies simple data entry and routine tasks as "AI" and tasks requiring complex judgment as "human". The task assignment unit assigns the tasks classified by the task classification unit to the appropriate person. For example, the task assignment unit selects the optimal person by considering the skill sets and current workload of project members. The task assignment unit can also automate task assignment using AI. For example, the task assignment unit uses AI to analyze the skills and experience of project members and automatically select the optimal person. The task registration unit registers the tasks assigned by the task assignment unit to project management tools and personal task management tools. For example, the task registration unit can use JIRA or Trello as project management tools and Todoist or Microsoft To-Do as personal task management tools. The task registration unit can also update the progress of tasks in real time and reflect it in project management tools and personal task management tools. The progress management unit manages the progress of tasks registered by the task registration unit. For example, the progress management unit monitors the progress of tasks in real time and sends reminders before the deadline.Furthermore, the progress management department can accept consultations from task assignees and reassign tasks as needed. For example, if a task is behind schedule, the progress management department can change the assignee or extend the deadline. As a result, the project hub system according to this embodiment can improve the efficiency of task management in project management.

[0073] The progress management unit may include a reminder unit that sends reminders before the due date. The reminder unit, for example, sends a reminder to the person in charge when the task due date is approaching. For example, the reminder unit can send a reminder one day or three days before the task due date. The reminder unit can also customize the method of sending reminders. For example, the reminder unit can send reminders using multiple methods, such as email, push notifications, and chat messages. Furthermore, the reminder unit can customize the content of the reminders. For example, the reminder unit can send a reminder message that includes information such as task details, due date, and progress status. This helps prevent task delays by sending reminders before the due date. Some or all of the above processes in the reminder unit may be performed using AI, for example, or not. For example, the reminder unit may use AI to analyze the task progress and send reminders at the appropriate time.

[0074] The progress management department may have a consultation department that receives inquiries from task assignees. The consultation department provides a point of contact for task assignees to consult about technical issues and progress. For example, the consultation department can receive inquiries through multiple methods, such as online chat, telephone, and email. The consultation department can also record the content of the inquiries and escalate them to the appropriate person in charge. For example, the consultation department can escalate inquiries about technical issues to a specialized technical support team. Furthermore, the consultation department can adjust the progress of tasks based on the content of the inquiries. For example, the consultation department can analyze the content of the task assignee's inquiry and extend the task deadline or change the person in charge as necessary. In this way, accepting inquiries from task assignees can ensure that tasks progress smoothly. Some or all of the above processes in the consultation department may be performed using AI, for example, or not using AI. For example, the consultation department may use AI to analyze the content of the inquiries and suggest appropriate responses.

[0075] The progress management unit may include a reassignment unit that reassigns tasks as needed. The reassignment unit reassigns tasks, for example, when a task is behind schedule or when the assigned person lacks the necessary resources. For example, the reassignment unit can monitor the task's progress in real time and change the assigned person as needed. The reassignment unit can also adjust the task's priority and due date. For example, if a task is behind schedule, the reassignment unit can set a higher priority and respond quickly. Furthermore, the reassignment unit can send notifications to the assigned person regarding the task reassignment. For example, when the assigned person for a task changes, the reassignment unit can send a notification to the new person in charge and share the task details and due date. This allows for the optimization of task progress through task reassignment. Some or all of the above processes in the reassignment unit may be performed using AI, for example, or not. For example, the reassignment unit may use AI to analyze the task's progress and select the most suitable person in charge.

[0076] The meeting minutes generation unit can automatically generate meeting minutes from the content of meetings and phone conversations. For example, the unit can use speech recognition technology to convert meeting and phone audio data into text data and automatically generate meeting minutes. For instance, the unit can analyze meeting audio data in real time and record what was said as text. Furthermore, the unit can use natural language processing technology to summarize conversations and extract key points. For example, it can extract frequently occurring keywords and phrases in conversations and create meeting minutes based on them. In addition, the unit can customize the format and content of the meeting minutes. For example, it can generate minutes in multiple formats, such as detailed records, summaries, and bullet points. This reduces the effort required to create meeting minutes by automatically generating meeting and phone conversations. Some or all of the above-described processes in the meeting minutes generation unit may be performed using AI, or without AI. For example, the meeting minutes generation unit can use AI to analyze audio data and automatically generate meeting minutes.

[0077] The task classification unit can extract tasks from generated meeting minutes and classify whether the tasks should be performed by a "human" or "AI". For example, the task classification unit can analyze the content of the meeting minutes using natural language processing technology to extract tasks. For instance, the task classification unit can detect keywords such as "task" or "work" in the meeting minutes, analyze the related context, and extract tasks. Furthermore, the task classification unit can classify tasks as "human" or "AI" based on their content and complexity. For example, the task classification unit can classify simple data entry and routine tasks as "AI" and tasks requiring complex judgment as "human". In addition, the task classification unit can classify tasks considering their priority and deadline. For example, the task classification unit can prioritize assigning urgent tasks to "humans" and routine tasks to "AI". By classifying tasks as "human" or "AI", tasks can be assigned to the appropriate person. Some or all of the processing described above in the task classification unit may be performed using AI, for example, or without AI. For example, the task classification unit may use AI to analyze the contents of the meeting minutes, extract tasks, and classify them.

[0078] The task assignment unit can assign classified tasks to assigned personnel. For example, the task assignment unit can select the most suitable personnel by considering the skill sets and current workload of project members. For instance, the task assignment unit can retrieve project members' skills and experience from a database and assign tasks based on that information. Furthermore, the task assignment unit can automate task assignment using AI. For example, the task assignment unit can use AI to analyze project members' skills and experience and automatically select the most suitable personnel. Additionally, the task assignment unit can assign tasks considering their priority and deadline. For example, the task assignment unit can prioritize high-priority tasks and postpone routine tasks. This improves the efficiency of task execution by assigning tasks to the appropriate personnel. Some or all of the above processes in the task assignment unit may be performed using AI, or not. For example, the task assignment unit can use AI to analyze task content and select the most suitable personnel.

[0079] The task registration unit can register assigned tasks to project management tools and personal task management tools. For example, the task registration unit can use JIRA or Trello as project management tools, and Todoist or Microsoft To-Do as personal task management tools. For instance, the task registration unit can automatically register task details, due dates, assignees, and other information to the project management tools and personal task management tools. Furthermore, the task registration unit can update task progress in real time and reflect this in the project management tools and personal task management tools. For example, the task registration unit can send notifications to the project management tools and personal task management tools whenever task progress is updated, ensuring that the latest information is reflected. Additionally, the task registration unit can register tasks considering their priority and due dates. For example, the task registration unit can prioritize high-priority tasks and postpone routine tasks. This makes task management easier by registering tasks in project management tools and personal task management tools. Some or all of the above-described processes in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the content of tasks and automatically register them in project management tools or personal task management tools.

[0080] The meeting minutes generation unit can estimate the emotions of meeting participants and adjust the expression of the minutes based on the estimated emotions. For example, the meeting minutes generation unit can analyze the facial expressions and voices of meeting participants to estimate their emotions. For example, the meeting minutes generation unit can use facial recognition technology to analyze the facial expressions of meeting participants and estimate their emotions. The meeting minutes generation unit can also use voice analysis technology to analyze the tone and speed of the voices of meeting participants and estimate their emotions. For example, if a meeting participant's voice tone is high, the meeting minutes generation unit can estimate that they are excited and adjust the expression of the minutes to be calmer. Furthermore, the meeting minutes generation unit can adjust the expression of the minutes based on the estimated emotions. For example, if a meeting participant is tense, the meeting minutes generation unit can soften the expression of the minutes to help them relax. In this way, by adjusting the expression of the minutes according to the emotions of the meeting participants, the content of the minutes is conveyed more appropriately. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generating AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the minutes generation unit may be performed using AI, for example, or not using AI. For example, the minutes generation unit may use AI to analyze the emotions of meeting participants and adjust the way the minutes are presented.

[0081] The minutes generation unit can analyze the content of a meeting in real time and highlight statements to reflect them in the minutes. For example, the minutes generation unit's generation AI can analyze the content of the meeting in real time and highlight important statements in bold. For example, the minutes generation unit's generation AI can analyze the frequency and content of statements during the meeting and highlight important statements in bold. The minutes generation unit's generation AI can also analyze the content of statements, extract keywords, and highlight them in the minutes. For example, the minutes generation unit's generation AI can analyze the tone of statements and color-code parts that should be emphasized to reflect them in the minutes. Furthermore, the minutes generation unit can adjust the content of the minutes based on the importance of the statements. For example, the minutes generation unit can record important statements in detail and summarize other statements. This makes the content of the minutes clearer by highlighting important statements. Some or all of the above processing in the minutes generation unit may be performed using AI, for example, or without AI. For example, the minutes generation unit can use AI to analyze the content of a meeting, highlight important statements, and reflect them in the minutes.

[0082] The minutes generation unit can analyze the audio data of a meeting and generate minutes, color-coding them for each speaker. For example, the minutes generation unit's generation AI can analyze the audio data and generate minutes in different colors for each speaker. Furthermore, the minutes generation unit's generation AI can analyze the characteristics of each speaker's voice and reflect this in the minutes by color-coding. For example, the minutes generation unit's generation AI can color-code the minutes based on the speaker's position or role. In addition, the minutes generation unit can adjust the color-coding of the minutes based on the speaker's emotions. For example, if a speaker is excited, the minutes generation unit can generate minutes in calm colors. This makes the content of the minutes more visually understandable by color-coding them for each speaker. Some or all of the above-described processes in the minutes generation unit may be performed using AI, or without AI. For example, the minutes generation unit can use AI to analyze audio data and generate minutes, color-coding each speaker's contribution.

[0083] The meeting minutes generation unit can estimate the emotions of meeting participants and adjust the summary portion of the minutes based on the estimated emotions. For example, the meeting minutes generation unit can estimate emotions by analyzing the facial expressions and voices of meeting participants. For example, the meeting minutes generation unit can use facial recognition technology to analyze the facial expressions of meeting participants and estimate their emotions. It can also use voice analysis technology to analyze the tone and speed of the voices of meeting participants and estimate their emotions. For example, if a meeting participant's voice tone is high, the meeting minutes generation unit can estimate that they are excited and adjust the summary portion to be calmer. Furthermore, the meeting minutes generation unit can adjust the summary portion of the minutes based on the estimated emotions. For example, if a meeting participant is nervous, the meeting minutes generation unit can make the summary portion concise and easy to understand. In this way, by adjusting the summary portion according to the emotions of the meeting participants, the summary of the minutes becomes more appropriate. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generating AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the minutes generation unit may be performed using AI, for example, or not using AI. For example, the minutes generation unit may use AI to analyze the emotions of meeting participants and adjust the summary portion of the minutes.

[0084] The minutes generation unit can analyze the content of a meeting and automatically link relevant past minutes. For example, the minutes generation unit's generation AI can analyze the content of a meeting and automatically link relevant past minutes. Furthermore, the minutes generation unit's generation AI can analyze keywords and search for and link relevant past minutes. For example, the minutes generation unit's generation AI can analyze the meeting's theme and automatically suggest relevant past minutes. In addition, the minutes generation unit can summarize the content of past minutes and link relevant sections. For example, the minutes generation unit can generate summaries of past minutes, highlighting and linking relevant sections. This makes the content of meetings more consistent by linking relevant past minutes. Some or all of the above processing in the minutes generation unit may be performed using AI, for example, or without AI. For example, the meeting minutes generation unit can use AI to analyze the content of a meeting and automatically link to relevant past meeting minutes.

[0085] The minutes generation unit can analyze the content of a meeting and automatically attach relevant external documents. For example, the minutes generation unit's generation AI can analyze the content of a meeting and automatically attach relevant external documents. Furthermore, the minutes generation unit's generation AI can analyze keywords and search for and attach relevant external documents. For example, the minutes generation unit's generation AI can analyze the meeting topic and automatically suggest relevant external documents. In addition, the minutes generation unit can summarize the content of external documents and attach them to the minutes. For example, the minutes generation unit can generate a summary of external documents, highlight the relevant parts, and attach it. This enriches the content of the minutes by attaching relevant external documents. Some or all of the above processes in the minutes generation unit may be performed using AI, or not. For example, the minutes generation unit's AI can analyze the content of a meeting and automatically attach relevant external documents.

[0086] The task classification unit can estimate the emotions of the task requester and adjust the task priority based on the estimated emotions. For example, the task classification unit can estimate emotions by analyzing the task requester's facial expressions and voice. For example, the task classification unit can analyze the task requester's facial expressions using facial recognition technology and estimate emotions. It can also analyze the tone and speed of the task requester's voice using voice analysis technology and estimate emotions. For example, the task classification unit can estimate that the task requester is nervous if their voice tone is high and set a higher priority. Furthermore, the task classification unit can adjust the task priority based on the estimated emotions. For example, if the task requester is nervous, the task classification unit can set a higher priority and respond quickly. This improves the efficiency of task execution by adjusting task priority according to the emotions of the task requester. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the task classification unit may be performed using AI, for example, or without AI. For example, the task classification unit may use AI to analyze the emotions of the task requester and adjust the task priority.

[0087] The task classification unit can analyze the content of tasks and efficiently classify them by grouping similar tasks. For example, the task classification unit can use a generative AI to analyze the content of tasks and automatically group similar tasks. Furthermore, the task classification unit can use a generative AI to analyze keywords and efficiently classify similar tasks. For example, the task classification unit can use a generative AI to analyze the theme of tasks and group related tasks. In addition, the task classification unit can group tasks considering their priority and due date. For example, the task classification unit can prioritize and group high-priority tasks, postponing routine tasks. This makes task classification more efficient by grouping similar tasks. Some or all of the above-described processes in the task classification unit may be performed using AI, or without AI. For example, the task classification unit can use AI to analyze the content of tasks and group similar tasks.

[0088] The task classification unit can select the optimal classification method by referring to the task requester's past task history. For example, the task classification unit can use a generating AI to analyze the task requester's past task history and select the optimal classification method. Furthermore, the task classification unit can also use a generating AI to suggest an efficient classification method based on the task requester's past task history. For example, the task classification unit can use a generating AI to automatically select the optimal classification method based on the task requester's past task history. In addition, the task classification unit can classify tasks considering their priority and due date. For example, the task classification unit can prioritize high-urgency tasks and postpone routine tasks. This allows for the selection of the optimal classification method by referring to past task history. Some or all of the above-described processes in the task classification unit may be performed using AI, or without AI. For example, the task classification unit can use AI to analyze the task requester's past task history and select the optimal classification method.

[0089] The task classification unit can estimate the emotions of the task requester and adjust the difficulty of the task based on the estimated emotions. For example, the task classification unit can analyze the facial expressions and voice of the task requester to estimate their emotions. For example, the task classification unit can use facial recognition technology to analyze the facial expressions of the task requester and estimate their emotions. The task classification unit can also use voice analysis technology to analyze the tone and speed of the task requester's voice and estimate their emotions. For example, if the task requester's voice tone is high, the task classification unit can estimate that they are nervous and set the difficulty level lower. Furthermore, the task classification unit can adjust the difficulty level of the task based on the estimated emotions. For example, if the task requester is nervous, the task classification unit can set the difficulty level lower to make it easier to handle. In this way, the efficiency of task execution is improved by adjusting the difficulty level of the task according to the emotions of the task requester. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processes in the task classification unit may be performed using AI, for example, or without AI. For example, the task classification unit may use AI to analyze the emotions of the task requester and adjust the difficulty level of the task.

[0090] The task classification unit can analyze the content of tasks and automatically link related projects. For example, the task classification unit can use a generating AI to analyze the content of tasks and automatically link related projects. The task classification unit can also use a generating AI to analyze keywords, search for related projects, and link them. For example, the task classification unit can use a generating AI to analyze the theme of a task and automatically suggest related projects. Furthermore, the task classification unit can link tasks while considering the progress and priority of the projects. For example, the task classification unit can prioritize linking projects that are behind schedule and postpone routine tasks. This streamlines task management by linking related projects. Some or all of the above processes in the task classification unit may be performed using AI, or not. For example, the task classification unit can use AI to analyze the content of tasks and automatically link related projects.

[0091] The task classification unit can analyze the content of a task and automatically suggest relevant external resources. For example, the task classification unit can use a generative AI to analyze the task content and automatically suggest relevant external resources. Furthermore, the task classification unit can use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the task classification unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. In addition, the task classification unit can summarize the content of external resources and associate them with tasks. For example, the task classification unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task execution by suggesting relevant external resources. Some or all of the above processing in the task classification unit may be performed using AI, or without AI. For example, the task classification unit can use AI to analyze the content of a task and automatically suggest relevant external resources.

[0092] The task assignment unit can estimate the emotions of task assignees and adjust the task assignment method based on the estimated emotions. For example, the task assignment unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the task assignment unit can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. The task assignment unit can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the task assignee's voice tone is high, the task assignment unit can estimate that they are nervous and prioritize assigning them easier tasks. Furthermore, the task assignment unit can adjust the task assignment method based on the estimated emotions. For example, if the task assignee is nervous, the task assignment unit can prioritize assigning them easier tasks, and if they are relaxed, it can assign them more difficult tasks. This improves the efficiency of task execution by adjusting the task assignment method according to the task assignee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the task assignment unit may be performed using AI, for example, or without AI. For example, the task assignment unit may use AI to analyze the emotions of task assignees and adjust the task assignment method accordingly.

[0093] The task assignment unit can analyze the content of a task and select the most suitable person to assign it based on the person's skill set. For example, the task assignment unit can use a generating AI to analyze the content of a task and select the most suitable person to assign it based on the person's skill set. The task assignment unit can also use a generating AI to analyze keywords and suggest the most suitable person to assign it based on the person's skill set. For example, the task assignment unit can use a generating AI to analyze the theme of a task and automatically select the most suitable person to assign it based on the person's skill set. Furthermore, the task assignment unit can also assign tasks while considering the current workload of the person assigning them. For example, the task assignment unit can select the most suitable person by considering the current number of tasks and working hours of the person assigning it. This improves the efficiency of task execution by selecting the most suitable person based on their skill set. Some or all of the above-described processes in the task assignment unit may be performed using AI, or without AI. For example, the task assignment unit can use AI to analyze the content of a task and select the most suitable person to assign it based on the person's skill set.

[0094] The task assignment unit can select the optimal assignment method by referring to the past collaboration history of the task requester and assignee. For example, the task assignment unit can use a generating AI to analyze the past collaboration history of the task requester and assignee and select the optimal assignment method. The task assignment unit can also use a generating AI to refer to the past collaboration history of the task requester and assignee and propose an efficient assignment method. For example, the task assignment unit can use a generating AI to automatically select the optimal assignment method based on the past collaboration history of the task requester and assignee. Furthermore, the task assignment unit can also assign tasks considering their priority and due date. For example, the task assignment unit can prioritize assigning high-priority tasks and postpone routine tasks. This allows for the selection of the optimal assignment method by referring to past collaboration history. Some or all of the above-described processes in the task assignment unit may be performed using AI, for example, or without AI. For example, the task assignment unit can use AI to analyze the past collaboration history between task requesters and assignees and select the optimal assignment method.

[0095] The task assignment unit can estimate the emotions of task assignees and adjust the task assignment order based on the estimated emotions. For example, the task assignment unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the task assignment unit can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. The task assignment unit can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the task assignee's voice tone is high, the task assignment unit can estimate that they are nervous and prioritize assigning them easier tasks. Furthermore, the task assignment unit can adjust the task assignment order based on the estimated emotions. For example, if the task assignee is nervous, the task assignment unit can prioritize assigning them easier tasks, and if they are relaxed, it can prioritize assigning them more difficult tasks. By adjusting the task assignment order according to the task assignee's emotions, the efficiency of task execution is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generation AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the task assignment unit may be performed using AI, or not using AI. For example, the task assignment unit may use AI to analyze the emotions of task assignees and adjust the order of task assignments.

[0096] The task assignment unit can analyze the content of a task and assign it considering the current workload of the person in charge. For example, the task assignment unit can use a generating AI to analyze the content of a task and assign it considering the current workload of the person in charge. Furthermore, the task assignment unit can use a generating AI to analyze keywords and propose the optimal assignment considering the workload of the person in charge. For example, the task assignment unit can use a generating AI to analyze the theme of a task and automatically make the optimal assignment considering the workload of the person in charge. In addition, the task assignment unit can assign tasks considering the person in charge's skill set and experience. For example, the task assignment unit can retrieve the person in charge's skill set and experience from a database and assign tasks based on that. This improves the efficiency of task execution by assigning tasks while considering the workload of the person in charge. Some or all of the above-described processes in the task assignment unit may be performed using AI, or not. For example, the task assignment unit can use AI to analyze the content of a task and assign it considering the workload of the person in charge.

[0097] The task assignment unit can analyze the content of a task and automatically suggest relevant external resources. For example, the task assignment unit can use a generative AI to analyze the content of a task and automatically suggest relevant external resources. Furthermore, the task assignment unit can use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the task assignment unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. In addition, the task assignment unit can summarize the content of external resources and associate them with tasks. For example, the task assignment unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task execution by suggesting relevant external resources. Some or all of the above processing in the task assignment unit may be performed using AI, or without AI. For example, the task assignment unit can use AI to analyze the content of a task and automatically suggest relevant external resources.

[0098] The task registration unit can estimate the emotions of the task requester and adjust the task registration method based on the estimated emotions. For example, the task registration unit can analyze the task requester's facial expressions and voice to estimate emotions. For example, the task registration unit can use facial recognition technology to analyze the task requester's facial expressions and estimate emotions. The task registration unit can also use voice analysis technology to analyze the tone and speed of the task requester's voice and estimate emotions. For example, the task registration unit can estimate that the task requester is nervous if their voice tone is high and provide a simple registration method. Furthermore, the task registration unit can adjust the task registration method based on the estimated emotions. For example, the task registration unit can provide a simple registration method when the task requester is nervous and a detailed registration method when they are relaxed. This makes task registration more efficient by adjusting the task registration method according to the task requester's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the task registration unit may be performed using AI, or not using AI. For example, the task registration unit may use AI to analyze the emotions of the task requester and adjust the task registration method.

[0099] The task registration unit can analyze the content of a task and automatically link it to relevant project management tools. For example, the task registration unit can use a generating AI to analyze the task content and automatically link it to relevant project management tools. The task registration unit can also use a generating AI to analyze keywords, search for relevant project management tools, and link them. For example, the task registration unit can use a generating AI to analyze the task's theme and automatically suggest relevant project management tools. Furthermore, the task registration unit can summarize the content of project management tools and associate it with tasks. For example, the task registration unit can generate a summary of project management tools, highlight the relevant parts, and link them. This streamlines task management by linking to relevant project management tools. Some or all of the above processing in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the task content and automatically link it to relevant project management tools.

[0100] The task registration unit can analyze the content of a task and automatically link it to relevant personal task management tools. For example, the task registration unit can use a generating AI to analyze the task content and automatically link it to relevant personal task management tools. The task registration unit can also use a generating AI to analyze keywords, search for relevant personal task management tools, and link them. For example, the task registration unit can use a generating AI to analyze the task's theme and automatically suggest relevant personal task management tools. Furthermore, the task registration unit can summarize the content of personal task management tools and associate it with the task. For example, the task registration unit can generate a summary of personal task management tools, highlight the relevant parts, and link them. This streamlines task management by linking to relevant personal task management tools. Some or all of the above processing in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the task content and automatically link it to relevant personal task management tools.

[0101] The task registration unit can estimate the emotions of the task requester and adjust the order of task registration based on the estimated emotions. For example, the task registration unit can estimate emotions by analyzing the task requester's facial expressions and voice. For example, the task registration unit can use facial recognition technology to analyze the task requester's facial expressions and estimate emotions. The task registration unit can also use voice analysis technology to analyze the tone and speed of the task requester's voice and estimate emotions. For example, if the task requester's voice tone is high, the task registration unit can estimate that they are nervous and prioritize registering important tasks. Furthermore, the task registration unit can adjust the order of task registration based on the estimated emotions. For example, if the task requester is nervous, the task registration unit can prioritize registering important tasks, and if they are relaxed, it can prioritize registering detailed tasks. This makes task registration more efficient by adjusting the order of task registration according to the task requester's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the processing described above in the task registration unit may be performed using AI, or not using AI. For example, the task registration unit may use AI to analyze the emotions of the task requester and adjust the order in which tasks are registered.

[0102] The task registration unit can analyze the content of a task and automatically suggest relevant external resources. For example, the task registration unit can use a generating AI to analyze the task content and automatically suggest relevant external resources. Furthermore, the task registration unit can use a generating AI to analyze keywords and search for and suggest relevant external resources. For example, the task registration unit can use a generating AI to analyze the task's theme and automatically suggest relevant external resources. In addition, the task registration unit can summarize the content of external resources and associate them with the task. For example, the task registration unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task execution by suggesting relevant external resources. Some or all of the above-described processes in the task registration unit may be performed using AI, or not. For example, the task registration unit can use AI to analyze the task content and automatically suggest relevant external resources.

[0103] The task registration unit can analyze the content of a task and automatically link related past tasks. For example, the task registration unit can use a generating AI to analyze the content of a task and automatically link related past tasks. The task registration unit can also use a generating AI to analyze keywords and search for and link related past tasks. For example, the task registration unit can use a generating AI to analyze the theme of a task and automatically suggest related past tasks. Furthermore, the task registration unit can summarize the content of past tasks and link the relevant parts. For example, the task registration unit can generate summaries of past tasks, highlight the relevant parts, and link them. This streamlines task management by linking related past tasks. Some or all of the above processing in the task registration unit may be performed using AI, or without AI. For example, the task registration unit can use AI to analyze the content of a task and automatically link related past tasks.

[0104] The progress management unit can estimate the emotions of task assignees and adjust the progress management method based on the estimated emotions. For example, the progress management unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the progress management unit can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. The progress management unit can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the progress management unit estimates that the task assignee is nervous when their voice tone is high, it can increase the frequency of progress management. Furthermore, the progress management unit can adjust the progress management method based on the estimated emotions. For example, if the progress management unit is nervous, it can increase the frequency of progress management and strengthen support. In this way, by adjusting the progress management method according to the task assignee's emotions, the task progresses smoothly. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processes described above in the progress management department may be performed using AI, for example, or without AI. For example, the progress management department may use AI to analyze the emotions of task assignees and adjust the progress management method accordingly.

[0105] The progress management unit can analyze task progress in real time and highlight important progress. For example, the progress management unit can use a generating AI to analyze task progress in real time and highlight important progress in bold. The progress management unit can also use a generating AI to analyze progress, extract keywords, and highlight them. For example, the progress management unit can use a generating AI to analyze the tone of progress and color-code the parts that should be emphasized. Furthermore, the progress management unit can adjust progress based on the importance of the progress. For example, the progress management unit can record important progress in detail and summarize other progress. This makes task progress clearer by highlighting important progress. Some or all of the above processes in the progress management unit may be performed using AI, for example, or not using AI. For example, the progress management unit can use AI to analyze task progress and highlight important progress.

[0106] The progress management unit can analyze the progress of tasks and automatically link to relevant project management tools. For example, the progress management unit can use a generating AI to analyze the progress of tasks and automatically link to relevant project management tools. Furthermore, the progress management unit can use a generating AI to analyze keywords, search for relevant project management tools, and link to them. For example, the progress management unit can use a generating AI to analyze the theme of a task and automatically suggest relevant project management tools. In addition, the progress management unit can summarize the content of project management tools and associate them with tasks. For example, the progress management unit can generate a summary of project management tools, highlight the relevant parts, and link them. This streamlines task progress management by linking to relevant project management tools. Some or all of the above processes in the progress management unit may be performed using AI, or not. For example, the progress management unit can use AI to analyze the progress of tasks and automatically link to relevant project management tools.

[0107] The progress management unit can estimate the emotions of task assignees and adjust the priority of progress management based on the estimated emotions. For example, the progress management unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the progress management unit can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. It can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the progress management unit estimates that the task assignee is nervous when their voice tone is high, it can prioritize the management of the progress of important tasks. Furthermore, the progress management unit can adjust the priority of progress management based on the estimated emotions. For example, if the progress management unit is nervous, it can prioritize the management of the progress of important tasks, and if they are relaxed, it can prioritize the management of the progress of detailed tasks. In this way, by adjusting the priority of progress management according to the emotions of the task assignee, the progress of tasks proceeds smoothly. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generation AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the processes described above in the progress management unit may be performed using AI, or not using AI. For example, the progress management unit may use AI to analyze the emotions of task assignees and adjust the priority of progress management.

[0108] The progress management unit can analyze the progress of tasks and automatically suggest relevant external resources. For example, the progress management unit can use a generative AI to analyze the progress of tasks and automatically suggest relevant external resources. The progress management unit can also use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the progress management unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. Furthermore, the progress management unit can summarize the content of external resources and associate them with tasks. For example, the progress management unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This streamlines task progress by suggesting relevant external resources. Some or all of the above processes in the progress management unit may be performed using AI, for example, or without AI. For example, the progress management unit can use AI to analyze the progress of tasks and automatically suggest relevant external resources.

[0109] The progress management unit can analyze the progress of tasks and automatically link relevant past progress data. For example, the progress management unit can use a generating AI to analyze the progress of tasks and automatically link relevant past progress data. Furthermore, the progress management unit can use a generating AI to analyze keywords and search for and link relevant past progress data. For example, the progress management unit can use a generating AI to analyze the theme of a task and automatically suggest relevant past progress data. In addition, the progress management unit can summarize the content of past progress data and link relevant sections. For example, the progress management unit can generate a summary of past progress data, highlight relevant sections, and link them. This streamlines task progress management by linking relevant past progress data. Some or all of the above processes in the progress management unit may be performed using AI, or not. For example, the progress management unit can use AI to analyze the progress of tasks and automatically link relevant past progress data.

[0110] The reminder unit can estimate the emotions of the task assignee and adjust the reminder method based on the estimated emotions. For example, the reminder unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the reminder unit can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. The reminder unit can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the reminder unit estimates that the task assignee is nervous when their voice tone is high, it can increase the frequency of reminders. Furthermore, the reminder unit can adjust the reminder method based on the estimated emotions. For example, if the reminder unit is nervous, it can increase the frequency of reminders and strengthen support. By adjusting the reminder method according to the task assignee's emotions, the task progresses smoothly. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit may use AI to analyze the emotions of the task assignee and adjust the method of reminder accordingly.

[0111] The reminder function can analyze task due dates in real time and highlight important due dates in reminders. For example, the reminder function can use a generation AI to analyze task due dates in real time and highlight important due dates in bold. The reminder function can also use a generation AI to analyze due dates, extract keywords, and highlight them. For example, the reminder function can use a generation AI to analyze the tone of due dates and color-code the parts that should be emphasized in reminders. Furthermore, the reminder function can adjust the content of reminders based on the importance of the due dates. For example, the reminder function can record important due dates in detail and summarize other due dates. This streamlines task due date management by highlighting important due dates. Some or all of the above processing in the reminder function may be performed using AI, for example, or without AI. For example, the reminder function can use AI to analyze task due dates and highlight important due dates in reminders.

[0112] The reminder unit can estimate the emotions of the task assignee and adjust the frequency of reminders based on the estimated emotions. For example, the reminder unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For instance, it can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. It can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the task assignee's voice tone is high, the reminder unit can estimate that they are nervous and increase the frequency of reminders. Furthermore, the reminder unit can adjust the frequency of reminders based on the estimated emotions. For example, if the task assignee is nervous, the reminder unit can increase the frequency of reminders and strengthen support. This allows for smoother task progress by adjusting the frequency of reminders according to the task assignee's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the reminder unit may be performed using AI, for example, or without AI. For example, the reminder unit may use AI to analyze the emotions of the task assignee and adjust the frequency of reminders.

[0113] The reminder unit can analyze task due dates and automatically suggest relevant external resources. For example, the reminder unit's generation AI can analyze task due dates and automatically suggest relevant external resources. The reminder unit can also have its generation AI analyze keywords and search for and suggest relevant external resources. For example, the reminder unit's generation AI can analyze the task theme and automatically suggest relevant external resources. Furthermore, the reminder unit can summarize the content of external resources and associate them with tasks. For example, the reminder unit can generate summaries of external resources, highlighting relevant sections and suggesting them. This streamlines task due date management by suggesting relevant external resources. Some or all of the above processing in the reminder unit may be performed using AI, or without AI. For example, the reminder unit's AI can analyze task due dates and automatically suggest relevant external resources.

[0114] The consultation department can estimate the emotions of task assignees and adjust the consultation method based on the estimated emotions. For example, the consultation department can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the consultation department can analyze the task assignee's facial expressions using facial recognition technology and estimate emotions. The consultation department can also analyze the tone and speed of the task assignee's voice using voice analysis technology and estimate emotions. For example, the consultation department can estimate that the task assignee is nervous if their voice tone is high and provide a simple consultation method. Furthermore, the consultation department can adjust the consultation method based on the estimated emotions. For example, the consultation department can provide a simple consultation method if the task assignee is nervous and a more detailed consultation method if they are relaxed. By adjusting the consultation method according to the task assignee's emotions, the task progresses smoothly. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the consultation reception department may be performed using AI, for example, or without AI. For example, the consultation reception department may use AI to analyze the emotions of task managers and adjust the consultation reception method accordingly.

[0115] The consultation reception unit can analyze consultation content in real time and highlight important consultations. For example, the consultation reception unit can use a generation AI to analyze consultation content in real time and highlight important consultations in bold. For example, the consultation reception unit can use a generation AI to analyze consultation content in real time and highlight important consultations in bold. The consultation reception unit can also use a generation AI to analyze consultation content, extract keywords, and highlight them. For example, the consultation reception unit can use a generation AI to analyze the tone of the consultation and color-code the parts that should be emphasized. Furthermore, the consultation reception unit can adjust the content of consultations based on their importance. For example, the consultation reception unit can record important consultations in detail and summarize other consultations. This makes the consultation content clearer by highlighting important consultations. Some or all of the above processing in the consultation reception unit may be performed using AI, for example, or without AI. For example, the consultation reception unit can use AI to analyze consultation content and highlight important consultations.

[0116] The consultation reception department can estimate the emotions of task assignees and adjust the priority of consultations based on the estimated emotions. For example, the consultation reception department can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the consultation reception department can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. The consultation reception department can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the consultation reception department estimates that the task assignee is nervous when their voice tone is high, it can prioritize accepting important consultations. Furthermore, the consultation reception department can adjust the priority of consultations based on the estimated emotions. For example, if the consultation reception department is nervous, it can prioritize accepting important consultations, and if they are relaxed, it can prioritize accepting detailed consultations. In this way, by adjusting the priority of consultations according to the task assignee's emotions, the progress of tasks can proceed smoothly. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. The generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above-described processes in the consultation reception department may be performed using AI, for example, or not using AI. For example, the consultation reception department may use AI to analyze the emotions of task assignees and adjust the priority of consultations.

[0117] The consultation reception department can analyze the consultation content and automatically suggest relevant external resources. For example, the consultation reception department can use a generative AI to analyze the consultation content and automatically suggest relevant external resources. The consultation reception department can also use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the consultation reception department can use a generative AI to analyze the consultation theme and automatically suggest relevant external resources. Furthermore, the consultation reception department can summarize the content of external resources and relate them to the consultation. For example, the consultation reception department can generate a summary of external resources, highlight the relevant parts, and suggest them. This enriches the consultation content by suggesting relevant external resources. Some or all of the above processing in the consultation reception department may be performed using AI, for example, or without AI. For example, the consultation reception department can use AI to analyze the consultation content and automatically suggest relevant external resources.

[0118] The reassignment unit can estimate the emotions of task assignees and adjust the reassignment method based on the estimated emotions. For example, the reassignment unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the reassignment unit can analyze the task assignee's facial expressions using facial recognition technology and estimate emotions. The reassignment unit can also analyze the tone and speed of the task assignee's voice using voice analysis technology and estimate emotions. For example, if the reassignment unit estimates that the task assignee is nervous when their voice tone is high, it can prioritize reassigning them to easier tasks. Furthermore, the reassignment unit can adjust the reassignment method based on the estimated emotions. For example, if the task assignee is nervous, the reassignment unit can prioritize reassigning them to easier tasks, and if they are relaxed, it can prioritize reassigning them to more difficult tasks. In this way, by adjusting the reassignment method according to the task assignee's emotions, the progress of tasks can proceed smoothly. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal-generating AI. Some or all of the processing described above in the reassignment unit may be performed using AI, for example, or not using AI. For example, the reassignment unit may use AI to analyze the emotions of task assignees and adjust the reassignment method accordingly.

[0119] The reassignment unit can analyze the progress of tasks in real time and determine the need for reassignment. For example, the reassignment unit can use a generation AI to analyze the progress of tasks in real time and determine the need for reassignment. The reassignment unit can also use a generation AI to analyze the progress and automatically suggest tasks that need to be reassigned. For example, the reassignment unit can use a generation AI to analyze the themes of the progress and determine the need for reassignment. Furthermore, the reassignment unit can change the person in charge of a task based on the need for reassignment. For example, the reassignment unit can prioritize the reassignment of tasks that are behind schedule and postpone routine tasks. This ensures that tasks progress smoothly by determining the need for reassignment. Some or all of the above processes in the reassignment unit may be performed using AI, for example, or without AI. For example, the reassignment unit can use AI to analyze the progress of tasks and determine the need for reassignment.

[0120] The reassignment unit can estimate the emotions of task assignees and adjust the reassignment priority based on the estimated emotions. For example, the reassignment unit can estimate emotions by analyzing the task assignee's facial expressions and voice. For example, the reassignment unit can use facial recognition technology to analyze the task assignee's facial expressions and estimate emotions. The reassignment unit can also use voice analysis technology to analyze the tone and speed of the task assignee's voice and estimate emotions. For example, if the reassignment unit estimates that the task assignee is nervous when their voice tone is high, it can prioritize reassigning them to important tasks. Furthermore, the reassignment unit can adjust the reassignment priority based on the estimated emotions. For example, if the task assignee is nervous, the reassignment unit can prioritize reassigning them to important tasks, and if they are relaxed, it can prioritize reassigning them to detailed tasks. This allows tasks to progress smoothly by adjusting the reassignment priority according to the task assignee's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the reassignment unit may be performed using AI, for example, or not using AI. For example, the reassignment unit may use AI to analyze the emotions of task assignees and adjust the reassignment priority.

[0121] The reallocation unit can analyze the progress of a task and automatically suggest relevant external resources. For example, the reallocation unit can use a generative AI to analyze the progress of a task and automatically suggest relevant external resources. The reallocation unit can also use a generative AI to analyze keywords and search for and suggest relevant external resources. For example, the reallocation unit can use a generative AI to analyze the theme of a task and automatically suggest relevant external resources. Furthermore, the reallocation unit can summarize the content of external resources and associate them with the task. For example, the reallocation unit can generate a summary of external resources, highlight the relevant parts, and suggest them. This allows the task to progress smoothly by suggesting relevant external resources. Some or all of the above processing in the reallocation unit may be performed using AI, for example, or without AI. For example, the reallocation unit can use AI to analyze the progress of a task and automatically suggest relevant external resources. === Hard Collateral 1-1 === Each of the multiple elements described above, including the meeting minutes generation unit, task classification unit, task assignment unit, task registration unit, and progress management unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the meeting minutes generation unit acquires audio data from meetings and phone calls using the camera 42 and microphone 38B of the smart device 14, converts the audio data into text data using the specific processing unit 290 of the data processing unit 12, and generates meeting minutes. The task classification unit extracts tasks from the meeting minutes using, for example, the specific processing unit 290 of the data processing unit 12 and classifies the tasks as "human" or "AI". The task assignment unit assigns tasks to appropriate personnel using, for example, the specific processing unit 290 of the data processing unit 12. The task registration unit registers tasks in a project management tool or personal task management tool using, for example, the control unit 46A of the smart device 14. The progress management unit manages the progress of tasks and provides reminders and reassignments using, for example, the specific processing unit 290 of the data processing unit 12. === Hard Collateral 1-2 === Each of the multiple elements described above, including the meeting minutes generation unit, task classification unit, task assignment unit, task registration unit, and progress management unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the meeting minutes generation unit acquires audio data from meetings or phone calls using the camera 42 and microphone 238 of the smart glasses 214, converts the audio data into text data using the identification processing unit 290 of the data processing unit 12, and generates meeting minutes. The task classification unit extracts tasks from the meeting minutes using the identification processing unit 290 of the data processing unit 12 and classifies the tasks as either "human" or "AI". The task assignment unit assigns tasks to appropriate personnel using the identification processing unit 290 of the data processing unit 12. The task registration unit registers tasks in a project management tool or personal task management tool using the control unit 46A of the smart glasses 214. The progress management unit manages the progress of tasks and provides reminders and reassignments using the identification processing unit 290 of the data processing unit 12. === Hard Collateral 1-3 === Each of the multiple elements described above, including the meeting minutes generation unit, task classification unit, task assignment unit, task registration unit, and progress management unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the meeting minutes generation unit acquires audio data from meetings and phone calls using the camera 42 and microphone 238 of the headset terminal 314, converts the audio data into text data using the specific processing unit 290 of the data processing unit 12, and generates meeting minutes. The task classification unit extracts tasks from the meeting minutes using, for example, the specific processing unit 290 of the data processing unit 12 and classifies the tasks as either "human" or "AI". The task assignment unit assigns tasks to appropriate personnel using, for example, the specific processing unit 290 of the data processing unit 12. The task registration unit registers tasks in a project management tool or personal task management tool using, for example, the control unit 46A of the headset terminal 314. The progress management unit manages the progress of tasks and provides reminders and reassignments using, for example, the specific processing unit 290 of the data processing unit 12. === Hard Collateral 1-4 === Each of the multiple elements described above, including the meeting minutes generation unit, task classification unit, task assignment unit, task registration unit, and progress management unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the meeting minutes generation unit uses the camera 42 and microphone 238 of the robot 414 to acquire audio data from meetings and phone calls, and the specific processing unit 290 of the data processing unit 12 converts the audio data into text data to generate meeting minutes. The task classification unit extracts tasks from the meeting minutes using, for example, the specific processing unit 290 of the data processing unit 12 and classifies the tasks as either "human" or "AI". The task assignment unit assigns tasks to appropriate personnel using, for example, the specific processing unit 290 of the data processing unit 12. The task registration unit registers tasks in a project management tool or personal task management tool using, for example, the control unit 46A of the robot 414. The progress management unit manages the progress of tasks and provides reminders and reassignments using, for example, the specific processing unit 290 of the data processing unit 12.

[0122] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0123] The project hub system may also include an emotion estimation unit that estimates the emotions of the task requester and adjusts the task priority based on the estimated emotions. For example, the emotion estimation unit can analyze the task requester's facial expressions and voice to estimate their emotions. If the task requester is tense, the emotion estimation unit can adjust the system to prioritize that task. Conversely, if the requester is relaxed, the emotion estimation unit can set the task priority as usual. This improves the efficiency of task execution by adjusting task priorities according to the emotions of the task requester.

[0124] The project hub system can also include a resource addition unit that analyzes task progress and automatically adds resources to tasks that are behind schedule. For example, the resource addition unit can detect tasks that are behind schedule and allocate additional personnel or AI resources. Furthermore, the resource addition unit can automatically select members with the necessary skill sets for tasks that are behind schedule and add them to the task. In addition, the resource addition unit can optimize task progress by allocating additional resources to tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0125] The project hub system can also include an emotion estimation unit that estimates the emotions of the task requester and adjusts the difficulty of the task based on the estimated emotions. For example, the emotion estimation unit can analyze the task requester's facial expressions and voice to estimate their emotions. If the task requester is nervous, the emotion estimation unit can lower the difficulty of the task. Conversely, if the requester is relaxed, the emotion estimation unit can set the difficulty of the task to normal. This improves the efficiency of task execution by adjusting the difficulty of the task according to the emotions of the task requester.

[0126] The project hub system can also include a reminder unit that analyzes task progress and automatically sends reminders to tasks that are behind schedule. For example, the reminder unit can detect tasks that are behind schedule and send reminders to the responsible person. Furthermore, the reminder unit can adjust the frequency of reminders for tasks that are behind schedule. In addition, the reminder unit can customize the content of reminders for tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0127] The project hub system may further include an emotion estimation unit that estimates the emotions of the task requester and adjusts the task assignment method based on the estimated emotions. For example, the emotion estimation unit can analyze the task requester's facial expressions and voice to estimate their emotions. If the task requester is tense, the emotion estimation unit can assign the task as an easy task. Conversely, if the requester is relaxed, the emotion estimation unit can assign the task as usual. This improves the efficiency of task execution by adjusting the task assignment method according to the emotions of the task requester.

[0128] The project hub system can also include a resource addition unit that analyzes task progress and automatically adds resources to tasks that are behind schedule. For example, the resource addition unit can detect tasks that are behind schedule and allocate additional personnel or AI resources. Furthermore, the resource addition unit can automatically select members with the necessary skill sets for tasks that are behind schedule and add them to the task. In addition, the resource addition unit can optimize task progress by allocating additional resources to tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0129] The project hub system may also include an emotion estimation unit that estimates the emotions of the task requester and adjusts the task priority based on the estimated emotions. For example, the emotion estimation unit can analyze the task requester's facial expressions and voice to estimate their emotions. If the task requester is tense, the emotion estimation unit can adjust the system to prioritize that task. Conversely, if the requester is relaxed, the emotion estimation unit can set the task priority as usual. This improves the efficiency of task execution by adjusting task priorities according to the emotions of the task requester.

[0130] The project hub system can also include a reminder unit that analyzes task progress and automatically sends reminders to tasks that are behind schedule. For example, the reminder unit can detect tasks that are behind schedule and send reminders to the responsible person. Furthermore, the reminder unit can adjust the frequency of reminders for tasks that are behind schedule. In addition, the reminder unit can customize the content of reminders for tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0131] The project hub system can also include an emotion estimation unit that estimates the emotions of the task requester and adjusts the difficulty of the task based on the estimated emotions. For example, the emotion estimation unit can analyze the task requester's facial expressions and voice to estimate their emotions. If the task requester is nervous, the emotion estimation unit can lower the difficulty of the task. Conversely, if the requester is relaxed, the emotion estimation unit can set the difficulty of the task to normal. This improves the efficiency of task execution by adjusting the difficulty of the task according to the emotions of the task requester.

[0132] The project hub system can also include a resource addition unit that analyzes task progress and automatically adds resources to tasks that are behind schedule. For example, the resource addition unit can detect tasks that are behind schedule and allocate additional personnel or AI resources. Furthermore, the resource addition unit can automatically select members with the necessary skill sets for tasks that are behind schedule and add them to the task. In addition, the resource addition unit can optimize task progress by allocating additional resources to tasks that are behind schedule. This allows for a quick response even when tasks are behind schedule.

[0133] The following briefly describes the processing flow for example form 2.

[0134] Step 1: The minutes generation unit generates meeting minutes based on the content of meetings and phone conversations. For example, it uses speech recognition technology to convert audio data from meetings and phone calls into text data and automatically generates meeting minutes. It can also use natural language processing technology to summarize the conversation content and extract important points. For example, it can extract frequently occurring keywords and phrases in the conversation and create meeting minutes based on them. Step 2: The task classification unit extracts tasks from the meeting minutes generated by the meeting minutes generation unit and classifies whether the tasks should be performed by a "human" or an "AI". For example, it may use natural language processing technology to analyze the content of the meeting minutes and extract tasks. Furthermore, based on the content and complexity of the tasks, it classifies simple data entry and routine tasks as "AI" tasks and tasks requiring complex judgment as "human" tasks. Step 3: The task assignment unit assigns tasks classified by the task classification unit to the appropriate person. For example, it selects the optimal person by considering the skill sets and current workload of the project members. Task assignment can also be automated using AI. For example, the AI ​​analyzes the skills and experience of the project members and automatically selects the optimal person. Step 4: The task registration unit registers the tasks assigned by the task assignment unit to the project management tool and the personal task management tool. For example, JIRA or Trello can be used as the project management tool, and Todoist or Microsoft To-Do can be used as the personal task management tool. It is also possible to update the task progress in real time and reflect it in the project management tool and the personal task management tool. Step 5: The progress management unit manages the progress of tasks registered by the task registration unit. For example, it monitors task progress in real time and sends reminders before the deadline. It can also accept consultations from task assignees and reassign tasks as needed. For example, if a task is behind schedule, the assignee can be changed or the deadline extended.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0136] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (for example, still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or Naive Bayes, and can perform a variety of operations, but is not limited to these examples. Furthermore, AI may also be an AI agent. Also, when the operations described above are performed by AI, the operations may be performed partially or entirely by AI, but is not limited to these examples. Additionally, operations performed by AI, including generative AI, may be replaced by rule-based operations, and rule-based operations may be replaced by operations performed by AI, including generative AI.

[0137] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0138] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0139] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0140] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0141] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0142] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0143] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0145] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0146] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0147] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0148] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0149] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0150] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0151] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0153] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0155] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0156] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0157] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0158] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0159] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0161] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0162] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0163] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0164] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0165] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0167] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0169] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0170] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0171] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0172] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0173] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0174] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0175] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0177] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0178] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0179] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0180] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0181] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0182] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0183] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0184] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0185] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0186] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0187] The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0188] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0189] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0190] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0191] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0192] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0193] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0194] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0195] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0196] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0197] 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.

[0198] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0199] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0200] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0201] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0202] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0203] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0204] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0205] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0206] [Explanation of symbols]

[0207] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A meeting minutes generation unit that generates meeting minutes from the content of meetings and telephone conversations, A task classification unit extracts tasks from the minutes generated by the minutes generation unit and classifies whether the tasks should be performed by a human or by AI. A task assignment unit that assigns tasks classified by the task classification unit to a person in charge, A task registration unit registers tasks assigned by the task assignment unit to a project management tool and a personal task management tool, A progress management unit manages the progress of tasks registered by the task registration unit, Equipped with A system characterized by the following features.

2. The aforementioned progress management unit, It includes a reminder function to send reminders before the due date. The system according to feature 1.

3. The aforementioned progress management unit, We have a consultation department to receive inquiries from task assignees. The system according to feature 1.

4. The aforementioned progress management unit, It includes a reassignment unit that reassigns tasks as needed. The system according to feature 1.

5. The aforementioned minutes generation unit, Automatically generates meeting minutes from the content of meetings and phone conversations. The system according to feature 1.

6. The task classification unit, The generated meeting minutes are used to extract tasks, and then the tasks are classified as either performed by a human or by AI. The system according to feature 1.

7. The task assignment unit, Assign categorized tasks to assigned personnel. The system according to feature 1.

8. The task registration unit, Register assigned tasks in project management tools and personal task management tools. The system according to feature 1.

9. The aforementioned minutes generation unit, The system estimates the emotions of meeting participants and adjusts the wording of the meeting minutes based on those estimates. The system according to feature 1.

Images