system

Abstract

The system according to this embodiment aims to automatically optimize the performance of the AI ​​agent and promote the use of AI through intuitive operation. [Solution] The system according to the embodiment comprises a code management unit, an automation unit, a dialogue unit, and a feedback unit. The code management unit manages code and data. The automation unit executes an automation process using the data managed by the code management unit. The dialogue unit interacts with the user based on the process executed by the automation unit. The feedback unit provides visual feedback based on the information obtained by the dialogue 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 character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there are problems that manual adjustment wastes time and it is difficult to improve the performance of an AI agent.

[0005] The system according to the embodiment aims to automatically optimize the performance of an AI agent and promote the use of AI with intuitive operations.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a code management unit, an automation unit, an interaction unit, and a feedback unit. The code management unit manages code and data. The automation unit executes an automation process using the data managed by the code management unit. The interaction unit interacts with the user based on the process executed by the automation unit. The feedback unit provides visual feedback based on the information obtained by the interaction unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically optimize the performance of the AI ​​agent and promote the use of AI through intuitive operation. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 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 system according to an embodiment of the present invention is a system that automatically optimizes the performance of an AI agent and enhances user support functions. To address the challenges of time-consuming manual adjustments and the difficulty in improving AI agent performance, this system includes the following components: First, it uses a code management system to manage the AI ​​agent's code and data and track its history. This enables centralized management of code and data, allowing developers to work efficiently. Next, it uses an automation tool to execute an automated process, optimizing settings and updating the AI ​​agent. This eliminates the need for manual fine-tuning, efficiently improving the AI ​​agent's performance. Furthermore, it uses a generative AI interface to support and improve the AI ​​agent's performance through interaction with the user. For example, it leverages generative AI to provide real-time interactive support, simplifying technical support. It also visualizes the AI ​​agent's growth using graphs to provide visual feedback. This allows users to intuitively understand the AI ​​agent's performance improvements. This system automatically optimizes the AI ​​agent's performance and promotes AI utilization through intuitive operation. It also enhances user support functions and contributes to the improvement of the AI ​​agent. This allows the system to automatically optimize the performance of AI agents and enhance user support capabilities.

[0029] The system according to the embodiment comprises a code management unit, an automation unit, an interaction unit, and a feedback unit. The code management unit manages code and data. The code management unit centrally manages code and data such as source code, binary data, and configuration files. The code management unit can track the history of code and data using a version control system. The code management unit records change history and can revert to previous versions. The automation unit executes automation processes using the data managed by the code management unit. The automation unit executes automation processes such as build processes, test processes, and deployment processes. The automation unit optimizes settings and updates AI agents. The automation unit performs performance tuning and resource allocation optimization, for example. The automation unit retrains AI agent models and adjusts parameters. The automation unit executes automation processes using automation tools such as Screwdriver. The interaction unit interacts with the user based on the processes executed by the automation unit. The interaction unit provides real-time interactive support using generative AI. The dialogue unit interacts with the user using means such as chatbots, voice assistants, and interactive UIs. The dialogue unit uses generative AI to provide appropriate answers to user questions. The dialogue unit uses generative AI to provide support for solving user problems. For example, the dialogue unit uses generative AI to generate answers to user questions in real time. The feedback unit provides visual feedback based on the information obtained by the dialogue unit. The feedback unit visualizes the growth of the AI ​​agent using graphs. For example, the feedback unit displays metrics such as performance improvement and learning progress in graphs. The feedback unit visually displays the growth of the AI ​​agent using a dashboard. The feedback unit provides visual feedback in a way that users can intuitively understand. This allows the system to efficiently manage code and data, execute automated processes, interact with users, and provide visual feedback.

[0030] The code management department manages code and data. For example, it centrally manages code and data such as source code, binary data, and configuration files. Specifically, source code is text files that describe the design and functionality of a program, while binary data includes compiled executable files and libraries. Configuration files are files that describe parameters and options for controlling the operation of a system or application. The code management department can use version control systems to track the history of code and data. Version control systems record the history of code changes and provide the ability to revert to previous versions. This allows developers to revert incorrect changes or add new features based on specific versions. Each developer can work in their local repository and share changes with other developers by pushing them to a remote repository. This allows the code management department to manage code and data efficiently and effectively, improving transparency and traceability of the development process. Furthermore, the code management department can ensure security by implementing access control and permission management. For example, it can set read-only or write permissions for specific users or groups. This allows the code management department to maintain security and compliance while promoting collaboration across the entire development team.

[0031] The Automation Department executes automation processes using data managed by the Code Management Department. The Automation Department executes automation processes such as build, test, and deployment processes. The build process compiles source code to generate an executable binary, the test process verifies that the generated binary works correctly, and the deployment process places the tested binary into the production environment. The Automation Department also optimizes settings and updates AI agents. Specifically, this includes performance tuning and resource allocation optimization. Performance tuning involves adjustments to improve system speed and efficiency, while resource allocation optimization involves adjustments to efficiently utilize system resources (CPU, memory, storage, etc.). The Automation Department also retrains AI agent models and adjusts parameters. An AI agent is a program that uses a machine learning model to perform specific tasks; retraining is the process of improving the model's accuracy using new data, and parameter adjustment involves changing settings to optimize the model's behavior. The Automation Department executes automation processes using automation tools such as Screwdriver. Screwdriver is an automation tool that supports continuous integration and continuous delivery (CI / CD), enabling the automation of build, test, and deployment processes. This allows the automation team to execute automated processes efficiently and effectively, improving the speed and quality of the development process. Furthermore, the automation team can assist in early problem detection and resolution through error handling and log management. For example, it can issue alerts when builds or tests fail and analyze logs to identify the cause. This allows the automation team to improve the reliability and stability of the development process.

[0032] The dialogue unit interacts with the user based on processes executed by the automation unit. The dialogue unit provides real-time interactive support using generative AI. The generative AI uses natural language processing technology to understand user input and generate appropriate responses. The dialogue unit interacts with the user using means such as chatbots, voice assistants, and interactive UIs. A chatbot is a program that conducts text-based conversations and provides text answers to user questions. A voice assistant is a program that accepts voice input and provides voice responses, allowing users to ask questions by voice. An interactive UI is a program that allows users to interact through a graphical interface and operate using buttons and menus. The dialogue unit uses generative AI to provide appropriate answers to user questions. The generative AI has learned from a large amount of data and can generate the most appropriate answers to user questions. For example, if a user asks about a specific error message, the generative AI can explain the meaning of that error message and how to resolve it. The dialogue unit uses generative AI to provide support for solving user problems. The generative AI can understand the user's problem and suggest solutions. For example, if a user asks about how to use a specific function, the generative AI can explain how to use that function step by step. The dialogue unit, for instance, generates answers to the user's questions in real time. This allows the dialogue unit to provide users with quick and appropriate support, improving user satisfaction. Furthermore, the dialogue unit can collect user feedback and continuously improve the accuracy and quality of the generative AI's responses. For example, users can rate the provided answers, and the generative AI's training data can be updated based on that rating. This allows the dialogue unit to always provide high-quality support based on the latest information and technology.

[0033] The feedback unit provides visual feedback based on information obtained from the dialogue unit. The feedback unit visualizes the AI ​​agent's growth using graphs. Specifically, it displays indicators such as performance improvements and learning progress of the AI ​​agent in graph form. For example, it can display evaluation indicators such as the AI ​​agent's accuracy, recall, and F1 score over time, visually showing the degree of improvement. The feedback unit visually displays the AI ​​agent's growth using a dashboard. The dashboard is an interface that displays multiple graphs and charts on a single screen, allowing users to intuitively grasp the information. For example, the AI ​​agent's learning progress, performance fluctuations, and resource usage can be checked at a glance. The feedback unit provides visual feedback in a way that users can intuitively understand. Specifically, it can highlight important information using color coding and icons. For example, improved performance can be displayed in green, and decreased performance in red, allowing users to grasp the situation at a glance. This enables the feedback unit to provide users with clear and effective information. Furthermore, the feedback unit can customize the dashboard layout and display content based on the user's operation history and feedback. For example, a layout can be provided that highlights a specific metric for users who are interested in that metric. This allows the feedback system to provide flexible information tailored to the user's needs, supporting their understanding and decision-making.

[0034] The code management unit can track the history of code and data. For example, the code management unit uses a version control system to track the history of code and data. The code management unit can record change histories and revert to previous versions. This makes management easier by tracking the history of code and data. Specific methods and criteria for tracking history include the use of a version control system and methods for recording change histories. Some or all of the above processes in the code management unit may or may not be performed using AI. For example, the code management unit can input the history of code and data into an AI model and have the AI ​​perform the history tracking.

[0035] The automation unit can optimize settings and update AI agents. For example, the automation unit can perform performance tuning and resource allocation optimization. The automation unit can retrain the AI ​​agent model and adjust parameters. The automation unit executes automated processes using automation tools such as Screwdriver. This enables automated optimization of settings and updates of AI agents. Specific methods and criteria for setting optimization include performance tuning and resource allocation optimization. Specific methods and criteria for updating AI agents include model retraining and parameter adjustment. Some or all of the above processes in the automation unit may be performed using AI or not. For example, the automation unit can input settings optimization and AI agent updates into an AI model and have the AI ​​perform the optimization and updates.

[0036] The dialogue unit can provide real-time interactive support using generative AI. The dialogue unit interacts with the user using means such as a chatbot, voice assistant, or interactive UI. The dialogue unit uses generative AI to provide appropriate answers to the user's questions. The dialogue unit uses generative AI to provide support for solving the user's problems. For example, the dialogue unit has the generative AI generate answers to the user's questions in real time. This provides real-time interactive support and enhances user support. Specific examples of real-time interactive support include chatbots, voice assistants, and interactive UIs. Some or all of the above-described processes in the dialogue unit may be performed using generative AI or not. For example, the dialogue unit can input the user's question into the generative AI and have the generative AI generate the answer.

[0037] The feedback unit can visualize the growth of the AI ​​agent using graphs. For example, the feedback unit displays metrics such as performance improvement and learning progress in graphs. The feedback unit visually displays the AI ​​agent's growth using a dashboard. The feedback unit provides visual feedback so that users can intuitively understand it. This allows for a visual understanding of the AI ​​agent's growth. Specific metrics and evaluation methods for the AI ​​agent's growth include performance improvement and learning progress. Some or all of the above-described processes in the feedback unit may be performed using AI or not. For example, the feedback unit can input AI agent growth data into an AI model and have the AI ​​perform the visualization of growth.

[0038] The code management unit can analyze past version history and select the optimal management method. For example, the code management unit can automatically select the most stable version based on past version history. The code management unit can identify frequently changed parts from past version history and manage them with focus. The code management unit can analyze past version history and propose the optimal release timing. In this way, the optimal management method can be selected by analyzing past version history. Specific details and analysis methods of past version history include methods of recording change history and the use of version control systems. Specific details and selection criteria for the optimal management method include optimization of resource allocation and performance tuning. Some or all of the above processes in the code management unit may be performed using AI, or not. For example, the code management unit can input past version history data into an AI model and have the AI ​​select the optimal management method.

[0039] The code management department can adjust management priorities according to the project's progress. For example, the code management department monitors project progress in real time and prioritizes the management of important tasks. The code management department dynamically adjusts resource allocation according to project progress. The code management department analyzes project progress and proposes the optimal management method. This enables efficient management by adjusting management priorities according to project progress. Specific methods and criteria for understanding project progress include progress reports and the use of task management systems. Specific methods and criteria for adjusting management priorities include prioritizing high-priority tasks and changing resource allocations. Some or all of the above processes in the code management department may be performed using AI or not. For example, the code management department can input project progress data into an AI model and have the AI ​​perform the adjustment of management priorities.

[0040] The code management unit can dynamically change access permissions according to the roles of team members. For example, the code management unit can automatically assign necessary access permissions according to the roles of team members. The code management unit can dynamically change access permissions according to the progress of the project. The code management unit can automatically update access permissions when the roles of team members change. This improves security and usability by dynamically changing access permissions according to the roles of team members. Specific methods and criteria for dynamically changing access permissions include setting permissions according to the user's role and real-time permission changes. Some or all of the above processes in the code management unit may be performed using AI or not. For example, the code management unit can input team member role data into an AI model and have the AI ​​perform the dynamic changes to access permissions.

[0041] The code management department can customize management methods according to the scale of the project. For example, for small-scale projects, the code management department provides a simple management method. For large-scale projects, the code management department provides a detailed management method to achieve efficient management. The code management department proposes the optimal management method according to the scale of the project. This allows for efficient management by customizing the management method according to the scale of the project. Specific methods and criteria for customizing the management method include resource allocation according to the scale of the project and optimization of task management. Some or all of the above processes in the code management department may be performed using AI, or not. For example, the code management department can input project scale data into an AI model and have the AI ​​perform the customization of the management method.

[0042] The automation unit can analyze past execution results and select the optimal settings. For example, the automation unit can automatically select the most effective settings based on past execution results. The automation unit can identify and improve settings that frequently failed based on past execution results. The automation unit analyzes past execution results and proposes the optimal execution timing. In this way, the optimal settings can be selected by analyzing past execution results. Specific details and analysis methods for past execution results include analysis of execution logs and performance data. Specific details and selection criteria for the optimal settings include performance tuning and optimization of resource allocation. Some or all of the above processes in the automation unit may be performed using AI, or they may not. For example, the automation unit can input past execution result data into an AI model and have the AI ​​select the optimal settings.

[0043] The automation unit can adjust process priorities according to the project's progress. For example, the automation unit monitors the project's progress in real time and prioritizes the execution of critical processes. The automation unit dynamically adjusts resource allocation according to the project's progress. The automation unit analyzes the project's progress and proposes the optimal execution order of processes. This enables efficient process execution by adjusting process priorities according to the project's progress. Specific methods and criteria for adjusting process priorities include prioritizing high-priority processes and changing resource allocations. Some or all of the above processes in the automation unit may be performed using AI, or not. For example, the automation unit can input project progress data into an AI model and have the AI ​​perform the process prioritization adjustments.

[0044] The automation unit can customize processes according to the scale of the project. For example, for small-scale projects, the automation unit provides a simple process. For large-scale projects, the automation unit provides a detailed process to ensure efficient execution. The automation unit proposes the optimal process according to the scale of the project. This allows for efficient process execution by customizing the process according to the scale of the project. Specific methods and criteria for customizing the process include resource allocation and task management optimization according to the scale of the project. Some or all of the above processes in the automation unit may be performed using AI or not. For example, the automation unit can input project scale data into an AI model and have the AI ​​perform the process customization.

[0045] The automation unit can dynamically change process execution permissions according to the roles of team members. For example, the automation unit automatically assigns the necessary execution permissions according to the roles of team members. The automation unit dynamically changes execution permissions according to the progress of the project. The automation unit automatically updates execution permissions when the roles of team members change. This improves security and convenience by dynamically changing process execution permissions according to the roles of team members. Specific methods and criteria for dynamically changing process execution permissions include setting permissions according to the user's role and real-time permission changes. Some or all of the above processes in the automation unit may be performed using AI or not. For example, the automation unit can input team member role data into an AI model and have the AI ​​perform the dynamic changes to execution permissions.

[0046] The dialogue unit can analyze the user's past dialogue history and select the optimal dialogue method. For example, the dialogue unit selects the most effective dialogue method based on the user's past dialogue history. The dialogue unit identifies frequently used dialogue methods from the user's past dialogue history and uses them with emphasis. The dialogue unit analyzes the user's past dialogue history and proposes the optimal dialogue timing. In this way, the optimal dialogue method can be selected by analyzing the user's past dialogue history. Specific content and analysis methods of past dialogue history include analysis of dialogue logs and analysis of user feedback. Specific content and selection criteria for the optimal dialogue method include dialogue methods that meet the user's needs and selection of methods based on past dialogue history. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input the user's past dialogue history data into a generative AI and have the generative AI perform the selection of the optimal dialogue method.

[0047] The dialogue unit can adjust the priority of dialogues according to the project's progress. For example, the dialogue unit monitors the project's progress in real time and prioritizes important dialogues. The dialogue unit dynamically adjusts the content of dialogues according to the project's progress. The dialogue unit analyzes the project's progress and proposes the optimal dialogue method. This allows for efficient dialogue by adjusting the priority of dialogues according to the project's progress. Specific methods and criteria for adjusting dialogue priorities include prioritizing high-priority dialogues and changing resource allocations. Some or all of the above processes in the dialogue unit may be performed using generative AI, or they may be performed without generative AI. For example, the dialogue unit can input project progress data into the generative AI and have the generative AI perform the adjustment of dialogue priorities.

[0048] The dialogue unit can customize the content of the conversation according to the user's role. For example, if the user is a developer, the dialogue unit will engage in conversations that include technical details. If the user is an administrator, the dialogue unit will engage in conversations about the progress of the project. If the user is an end-user, the dialogue unit will engage in conversations that are concise and easy to understand. By customizing the content of the conversation according to the user's role, user convenience is improved. Specific methods and criteria for customizing the content of the conversation include changing the content according to the user's role and changing the content according to the progress of the project. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input user role data into a generative AI and have the generative AI perform the customization of the conversation content.

[0049] The dialogue unit can change its dialogue method according to the scale of the project. For example, for small-scale projects, the dialogue unit provides a simple dialogue method. For large-scale projects, the dialogue unit provides a detailed dialogue method to achieve efficient dialogue. The dialogue unit proposes the optimal dialogue method according to the scale of the project. This makes efficient dialogue possible by changing the dialogue method according to the scale of the project. Specific methods and criteria for changing the dialogue method include changing the dialogue method according to the scale of the project and changing the method according to the user's needs. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input project scale data into a generative AI and have the generative AI execute the change in the dialogue method.

[0050] The feedback unit can analyze past feedback history and select the optimal display method. For example, the feedback unit can automatically select the most effective display method based on past feedback history. The feedback unit can identify frequently used display methods from past feedback history and use them with emphasis. The feedback unit analyzes past feedback history and proposes the optimal display timing. In this way, the optimal display method can be selected by analyzing past feedback history. Specific details and analysis methods for past feedback history include analysis of feedback logs and analysis of user feedback. Specific details and selection criteria for the optimal display method include display methods that meet user needs and selection of methods based on past feedback history. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can input past feedback history data into an AI model and have the AI ​​select the optimal display method.

[0051] The feedback unit can adjust the priority of feedback according to the project's progress. For example, the feedback unit monitors the project's progress in real time and prioritizes providing important feedback. The feedback unit dynamically adjusts the content of feedback according to the project's progress. The feedback unit analyzes the project's progress and proposes the optimal feedback method. This enables efficient feedback by adjusting the priority of feedback according to the project's progress. Specific methods and criteria for adjusting feedback priority include prioritizing high-priority feedback and changing resource allocation. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can input project progress data into an AI model and have the AI ​​perform the adjustment of feedback priority.

[0052] The feedback section can adjust the display order of feedback according to the user's role. For example, if the user is a developer, the feedback section will prioritize displaying technical feedback. If the user is an administrator, the feedback section will prioritize displaying feedback regarding project progress. If the user is an end-user, the feedback section will prioritize displaying concise and easy-to-understand feedback. By adjusting the display order of feedback according to the user's role, user convenience is improved. Specific methods and criteria for adjusting the display order of feedback include prioritizing the display of high-priority feedback and changing the display order according to the user's role. Some or all of the above processing in the feedback section may be performed using AI or not. For example, the feedback section can input user role data into an AI model and have the AI ​​perform the adjustment of the display order of feedback.

[0053] The feedback unit can change its feedback method according to the scale of the project. For example, for small-scale projects, the feedback unit provides a simple feedback method. For large-scale projects, the feedback unit provides a detailed feedback method to achieve efficient feedback. The feedback unit proposes the optimal feedback method according to the scale of the project. This makes efficient feedback possible by changing the feedback method according to the scale of the project. Specific methods and criteria for changing the feedback method include changing the feedback method according to the scale of the project and changing the method according to user needs. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input project scale data into an AI model and have the AI ​​perform the change in the feedback method.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The code management department can adjust the frequency of code reviews according to the project's progress. For example, in the early stages of a project, frequent code reviews are conducted to ensure code quality. In the middle stages of the project, the review frequency is reduced to prioritize development speed. In the final stages of the project, frequent reviews are conducted again to ensure final quality. By adjusting the frequency of code reviews according to the project's progress, efficient development becomes possible.

[0056] The automation department can adjust the priority of automation processes according to the project's progress. For example, in the early stages of a project, the build process is prioritized to solidify the foundation. In the middle stages of the project, the test process is prioritized to ensure quality. In the final stages of the project, the deployment process is prioritized to prepare for release. This allows for efficient project management by adjusting the priority of automation processes according to the project's progress.

[0057] The dialogue section can customize the content of the conversation according to the user's role. For example, if the user is a developer, the conversation will include technical details. If the user is an administrator, the conversation will be about the progress of the project. If the user is an end-user, the conversation will be concise and easy to understand. By customizing the dialogue content according to the user's role, user convenience is improved.

[0058] The feedback department can adjust the content of feedback according to the project's progress. For example, in the initial stages of the project, basic feedback is provided to confirm the direction. In the middle stages, detailed feedback is provided to check progress. In the final stages of the project, final feedback is provided to confirm the level of completion. By adjusting the content of feedback according to the project's progress, efficient project management becomes possible.

[0059] The feedback section can adjust how feedback is displayed according to the user's role. For example, if the user is a developer, technical feedback will be prioritized. If the user is an administrator, feedback regarding project progress will be prioritized. If the user is an end-user, concise and easy-to-understand feedback will be prioritized. By adjusting how feedback is displayed according to the user's role, user convenience is improved.

[0060] The following briefly describes the processing flow for example form 1.

[0061] Step 1: The Code Management Department manages the code and data. The Code Management Department centrally manages code and data such as source code, binary data, and configuration files, and tracks the history of the code and data using a version control system. This allows for recording change history and reverting to previous versions. Step 2: The Automation Department executes the automation process using data managed by the Code Management Department. The Automation Department executes automation processes such as build, test, and deployment processes, and optimizes settings and updates AI agents. For example, it performs performance tuning, optimizes resource allocation, retrains AI agent models, and adjusts parameters. The Automation Department executes the automation process using automation tools such as Screwdriver. Step 3: The dialogue unit interacts with the user based on the process executed by the automation unit. The dialogue unit provides real-time conversational support using generative AI and interacts with the user using means such as chatbots, voice assistants, and interactive UIs. Using generative AI, it provides appropriate answers to user questions and provides support to solve user problems. For example, the generative AI generates answers to user questions in real time. Step 4: The feedback unit provides visual feedback based on the information obtained by the dialogue unit. The feedback unit visualizes the AI ​​agent's growth using graphs and displays indicators such as performance improvement and learning progress in graph form. The dashboard visually displays the AI ​​agent's growth and provides visual feedback so that users can intuitively understand it.

[0062] (Example of form 2) The system according to an embodiment of the present invention is a system that automatically optimizes the performance of an AI agent and enhances user support functions. To address the challenges of time-consuming manual adjustments and the difficulty in improving AI agent performance, this system includes the following components: First, it uses a code management system to manage the AI ​​agent's code and data and track its history. This enables centralized management of code and data, allowing developers to work efficiently. Next, it uses an automation tool to execute an automated process, optimizing settings and updating the AI ​​agent. This eliminates the need for manual fine-tuning, efficiently improving the AI ​​agent's performance. Furthermore, it uses a generative AI interface to support and improve the AI ​​agent's performance through interaction with the user. For example, it leverages generative AI to provide real-time interactive support, simplifying technical support. It also visualizes the AI ​​agent's growth using graphs to provide visual feedback. This allows users to intuitively understand the AI ​​agent's performance improvements. This system automatically optimizes the AI ​​agent's performance and promotes AI utilization through intuitive operation. It also enhances user support functions and contributes to the improvement of the AI ​​agent. This allows the system to automatically optimize the performance of AI agents and enhance user support capabilities.

[0063] The system according to the embodiment comprises a code management unit, an automation unit, an interaction unit, and a feedback unit. The code management unit manages code and data. The code management unit centrally manages code and data such as source code, binary data, and configuration files. The code management unit can track the history of code and data using a version control system. The code management unit records change history and can revert to previous versions. The automation unit executes automation processes using the data managed by the code management unit. The automation unit executes automation processes such as build processes, test processes, and deployment processes. The automation unit optimizes settings and updates AI agents. The automation unit performs performance tuning and resource allocation optimization, for example. The automation unit retrains AI agent models and adjusts parameters. The automation unit executes automation processes using automation tools such as Screwdriver. The interaction unit interacts with the user based on the processes executed by the automation unit. The interaction unit provides real-time interactive support using generative AI. The dialogue unit interacts with the user using means such as chatbots, voice assistants, and interactive UIs. The dialogue unit uses generative AI to provide appropriate answers to user questions. The dialogue unit uses generative AI to provide support for solving user problems. For example, the dialogue unit uses generative AI to generate answers to user questions in real time. The feedback unit provides visual feedback based on the information obtained by the dialogue unit. The feedback unit visualizes the growth of the AI ​​agent using graphs. For example, the feedback unit displays metrics such as performance improvement and learning progress in graphs. The feedback unit visually displays the growth of the AI ​​agent using a dashboard. The feedback unit provides visual feedback in a way that users can intuitively understand. This allows the system to efficiently manage code and data, execute automated processes, interact with users, and provide visual feedback.

[0064] The code management department manages code and data. For example, it centrally manages code and data such as source code, binary data, and configuration files. Specifically, source code is text files that describe the design and functionality of a program, while binary data includes compiled executable files and libraries. Configuration files are files that describe parameters and options for controlling the operation of a system or application. The code management department can use version control systems to track the history of code and data. Version control systems record the history of code changes and provide the ability to revert to previous versions. This allows developers to revert incorrect changes or add new features based on specific versions. Each developer can work in their local repository and share changes with other developers by pushing them to a remote repository. This allows the code management department to manage code and data efficiently and effectively, improving transparency and traceability of the development process. Furthermore, the code management department can ensure security by implementing access control and permission management. For example, it can set read-only or write permissions for specific users or groups. This allows the code management department to maintain security and compliance while promoting collaboration across the entire development team.

[0065] The Automation Department executes automation processes using data managed by the Code Management Department. The Automation Department executes automation processes such as build, test, and deployment processes. The build process compiles source code to generate an executable binary, the test process verifies that the generated binary works correctly, and the deployment process places the tested binary into the production environment. The Automation Department also optimizes settings and updates AI agents. Specifically, this includes performance tuning and resource allocation optimization. Performance tuning involves adjustments to improve system speed and efficiency, while resource allocation optimization involves adjustments to efficiently utilize system resources (CPU, memory, storage, etc.). The Automation Department also retrains AI agent models and adjusts parameters. An AI agent is a program that uses a machine learning model to perform specific tasks; retraining is the process of improving the model's accuracy using new data, and parameter adjustment involves changing settings to optimize the model's behavior. The Automation Department executes automation processes using automation tools such as Screwdriver. Screwdriver is an automation tool that supports continuous integration and continuous delivery (CI / CD), enabling the automation of build, test, and deployment processes. This allows the automation team to execute automated processes efficiently and effectively, improving the speed and quality of the development process. Furthermore, the automation team can assist in early problem detection and resolution through error handling and log management. For example, it can issue alerts when builds or tests fail and analyze logs to identify the cause. This allows the automation team to improve the reliability and stability of the development process.

[0066] The dialogue unit interacts with the user based on processes executed by the automation unit. The dialogue unit provides real-time interactive support using generative AI. The generative AI uses natural language processing technology to understand user input and generate appropriate responses. The dialogue unit interacts with the user using means such as chatbots, voice assistants, and interactive UIs. A chatbot is a program that conducts text-based conversations and provides text answers to user questions. A voice assistant is a program that accepts voice input and provides voice responses, allowing users to ask questions by voice. An interactive UI is a program that allows users to interact through a graphical interface and operate using buttons and menus. The dialogue unit uses generative AI to provide appropriate answers to user questions. The generative AI has learned from a large amount of data and can generate the most appropriate answers to user questions. For example, if a user asks about a specific error message, the generative AI can explain the meaning of that error message and how to resolve it. The dialogue unit uses generative AI to provide support for solving user problems. The generative AI can understand the user's problem and suggest solutions. For example, if a user asks about how to use a specific function, the generative AI can explain how to use that function step by step. The dialogue unit, for instance, generates answers to the user's questions in real time. This allows the dialogue unit to provide users with quick and appropriate support, improving user satisfaction. Furthermore, the dialogue unit can collect user feedback and continuously improve the accuracy and quality of the generative AI's responses. For example, users can rate the provided answers, and the generative AI's training data can be updated based on that rating. This allows the dialogue unit to always provide high-quality support based on the latest information and technology.

[0067] The feedback unit provides visual feedback based on information obtained from the dialogue unit. The feedback unit visualizes the AI ​​agent's growth using graphs. Specifically, it displays indicators such as performance improvements and learning progress of the AI ​​agent in graph form. For example, it can display evaluation indicators such as the AI ​​agent's accuracy, recall, and F1 score over time, visually showing the degree of improvement. The feedback unit visually displays the AI ​​agent's growth using a dashboard. The dashboard is an interface that displays multiple graphs and charts on a single screen, allowing users to intuitively grasp the information. For example, the AI ​​agent's learning progress, performance fluctuations, and resource usage can be checked at a glance. The feedback unit provides visual feedback in a way that users can intuitively understand. Specifically, it can highlight important information using color coding and icons. For example, improved performance can be displayed in green, and decreased performance in red, allowing users to grasp the situation at a glance. This enables the feedback unit to provide users with clear and effective information. Furthermore, the feedback unit can customize the dashboard layout and display content based on the user's operation history and feedback. For example, a layout can be provided that highlights a specific metric for users who are interested in that metric. This allows the feedback system to provide flexible information tailored to the user's needs, supporting their understanding and decision-making.

[0068] The code management unit can track the history of code and data. For example, the code management unit uses a version control system to track the history of code and data. The code management unit can record change histories and revert to previous versions. This makes management easier by tracking the history of code and data. Specific methods and criteria for tracking history include the use of a version control system and methods for recording change histories. Some or all of the above processes in the code management unit may or may not be performed using AI. For example, the code management unit can input the history of code and data into an AI model and have the AI ​​perform the history tracking.

[0069] The automation unit can optimize settings and update AI agents. For example, the automation unit can perform performance tuning and resource allocation optimization. The automation unit can retrain the AI ​​agent model and adjust parameters. The automation unit executes automated processes using automation tools such as Screwdriver. This enables automated optimization of settings and updates of AI agents. Specific methods and criteria for setting optimization include performance tuning and resource allocation optimization. Specific methods and criteria for updating AI agents include model retraining and parameter adjustment. Some or all of the above processes in the automation unit may be performed using AI or not. For example, the automation unit can input settings optimization and AI agent updates into an AI model and have the AI ​​perform the optimization and updates.

[0070] The dialogue unit can provide real-time interactive support using generative AI. The dialogue unit interacts with the user using means such as a chatbot, voice assistant, or interactive UI. The dialogue unit uses generative AI to provide appropriate answers to the user's questions. The dialogue unit uses generative AI to provide support for solving the user's problems. For example, the dialogue unit has the generative AI generate answers to the user's questions in real time. This provides real-time interactive support and enhances user support. Specific examples of real-time interactive support include chatbots, voice assistants, and interactive UIs. Some or all of the above-described processes in the dialogue unit may be performed using generative AI or not. For example, the dialogue unit can input the user's question into the generative AI and have the generative AI generate the answer.

[0071] The feedback unit can visualize the growth of the AI ​​agent using graphs. For example, the feedback unit displays metrics such as performance improvement and learning progress in graphs. The feedback unit visually displays the AI ​​agent's growth using a dashboard. The feedback unit provides visual feedback so that users can intuitively understand it. This allows for a visual understanding of the AI ​​agent's growth. Specific metrics and evaluation methods for the AI ​​agent's growth include performance improvement and learning progress. Some or all of the above-described processes in the feedback unit may be performed using AI or not. For example, the feedback unit can input AI agent growth data into an AI model and have the AI ​​perform the visualization of growth.

[0072] The code management unit can estimate the user's emotions and adjust how codes and data are managed based on those emotions. For example, if the user is stressed, the code management unit provides a simple interface and minimizes the steps involved in managing codes and data. If the user is relaxed, the code management unit provides detailed management options and suggests customizable management methods. If the user is in a hurry, the code management unit prioritizes voice input to enable quick code and data management. This improves user convenience by adjusting how codes and data are managed according to the user's emotions. Specific methods and criteria for estimating user emotions include facial recognition, voice analysis, and text analysis. Specific methods and criteria for adjusting management methods include changing access permissions and changing notification methods. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the code management unit may be performed using AI or not. For example, the code management unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0073] The code management unit can analyze past version history and select the optimal management method. For example, the code management unit can automatically select the most stable version based on past version history. The code management unit can identify frequently changed parts from past version history and manage them with focus. The code management unit can analyze past version history and propose the optimal release timing. In this way, the optimal management method can be selected by analyzing past version history. Specific details and analysis methods of past version history include methods of recording change history and the use of version control systems. Specific details and selection criteria for the optimal management method include optimization of resource allocation and performance tuning. Some or all of the above processes in the code management unit may be performed using AI, or not. For example, the code management unit can input past version history data into an AI model and have the AI ​​select the optimal management method.

[0074] The code management department can adjust management priorities according to the project's progress. For example, the code management department monitors project progress in real time and prioritizes the management of important tasks. The code management department dynamically adjusts resource allocation according to project progress. The code management department analyzes project progress and proposes the optimal management method. This enables efficient management by adjusting management priorities according to project progress. Specific methods and criteria for understanding project progress include progress reports and the use of task management systems. Specific methods and criteria for adjusting management priorities include prioritizing high-priority tasks and changing resource allocations. Some or all of the above processes in the code management department may be performed using AI or not. For example, the code management department can input project progress data into an AI model and have the AI ​​perform the adjustment of management priorities.

[0075] The code management unit can estimate the user's emotions and adjust the order in which it displays the history of codes and data based on the estimated emotions. For example, if the user is stressed, the code management unit will prioritize displaying important history and omit unnecessary information. If the user is relaxed, the code management unit will display detailed history and provide a customizable display method. If the user is in a hurry, the code management unit will prioritize displaying the most recent history and provide information quickly. This improves user convenience by adjusting the display order of history according to the user's emotions. Specific methods and criteria for estimating the user's emotions include facial recognition, voice analysis, and text analysis. Specific methods and criteria for adjusting the order in which history is displayed include prioritizing the display of high-importance history and displaying it in chronological order. 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) and multimodal generation AI. Some or all of the above processing in the code management unit may be performed using AI or not. For example, the code management unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0076] The code management unit can dynamically change access permissions according to the roles of team members. For example, the code management unit can automatically assign necessary access permissions according to the roles of team members. The code management unit can dynamically change access permissions according to the progress of the project. The code management unit can automatically update access permissions when the roles of team members change. This improves security and usability by dynamically changing access permissions according to the roles of team members. Specific methods and criteria for dynamically changing access permissions include setting permissions according to the user's role and real-time permission changes. Some or all of the above processes in the code management unit may be performed using AI or not. For example, the code management unit can input team member role data into an AI model and have the AI ​​perform the dynamic changes to access permissions.

[0077] The code management department can customize management methods according to the scale of the project. For example, for small-scale projects, the code management department provides a simple management method. For large-scale projects, the code management department provides a detailed management method to achieve efficient management. The code management department proposes the optimal management method according to the scale of the project. This allows for efficient management by customizing the management method according to the scale of the project. Specific methods and criteria for customizing the management method include resource allocation according to the scale of the project and optimization of task management. Some or all of the above processes in the code management department may be performed using AI, or not. For example, the code management department can input project scale data into an AI model and have the AI ​​perform the customization of the management method.

[0078] The automation unit can estimate the user's emotions and adjust the execution timing of automated processes based on the estimated emotions. For example, if the user is stressed, the automation unit will delay the execution of the process. If the user is relaxed, the automation unit will speed up the execution of the process. If the user is in a hurry, the automation unit will optimize the execution timing of the process and execute it quickly. This improves user convenience by adjusting the execution timing of automated processes according to the user's emotions. Specific methods and criteria for adjusting the execution timing of automated processes include timing adjustments according to the user's work status and changes in execution timing according to the system load. Emotion estimation is achieved using an emotion estimation function with 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 processing in the automation unit may be performed using AI or not. For example, the automation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0079] The automation unit can analyze past execution results and select the optimal settings. For example, the automation unit can automatically select the most effective settings based on past execution results. The automation unit can identify and improve settings that frequently failed based on past execution results. The automation unit analyzes past execution results and proposes the optimal execution timing. In this way, the optimal settings can be selected by analyzing past execution results. Specific details and analysis methods for past execution results include analysis of execution logs and performance data. Specific details and selection criteria for the optimal settings include performance tuning and optimization of resource allocation. Some or all of the above processes in the automation unit may be performed using AI, or they may not. For example, the automation unit can input past execution result data into an AI model and have the AI ​​select the optimal settings.

[0080] The automation unit can adjust process priorities according to the project's progress. For example, the automation unit monitors the project's progress in real time and prioritizes the execution of critical processes. The automation unit dynamically adjusts resource allocation according to the project's progress. The automation unit analyzes the project's progress and proposes the optimal execution order of processes. This enables efficient process execution by adjusting process priorities according to the project's progress. Specific methods and criteria for adjusting process priorities include prioritizing high-priority processes and changing resource allocations. Some or all of the above processes in the automation unit may be performed using AI, or not. For example, the automation unit can input project progress data into an AI model and have the AI ​​perform the process prioritization adjustments.

[0081] The automation unit can estimate the user's emotions and adjust the execution order of automated processes based on the estimated emotions. For example, if the user is stressed, the automation unit will prioritize important processes and skip unnecessary ones. If the user is relaxed, the automation unit will execute detailed processes and provide a customizable execution order. If the user is in a hurry, the automation unit will prioritize processes that can be executed quickly. This improves user convenience by adjusting the execution order of automated processes according to the user's emotions. Specific methods and criteria for adjusting the execution order of automated processes include prioritizing the execution of high-priority processes and changing the execution order based on dependencies. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the automation unit may be performed using AI or not. For example, the automation unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0082] The automation unit can customize processes according to the scale of the project. For example, for small-scale projects, the automation unit provides a simple process. For large-scale projects, the automation unit provides a detailed process to ensure efficient execution. The automation unit proposes the optimal process according to the scale of the project. This allows for efficient process execution by customizing the process according to the scale of the project. Specific methods and criteria for customizing the process include resource allocation and task management optimization according to the scale of the project. Some or all of the above processes in the automation unit may be performed using AI or not. For example, the automation unit can input project scale data into an AI model and have the AI ​​perform the process customization.

[0083] The automation unit can dynamically change process execution permissions according to the roles of team members. For example, the automation unit automatically assigns the necessary execution permissions according to the roles of team members. The automation unit dynamically changes execution permissions according to the progress of the project. The automation unit automatically updates execution permissions when the roles of team members change. This improves security and convenience by dynamically changing process execution permissions according to the roles of team members. Specific methods and criteria for dynamically changing process execution permissions include setting permissions according to the user's role and real-time permission changes. Some or all of the above processes in the automation unit may be performed using AI or not. For example, the automation unit can input team member role data into an AI model and have the AI ​​perform the dynamic changes to execution permissions.

[0084] The dialogue unit can estimate the user's emotions and adjust the way the dialogue is expressed based on the estimated emotions. For example, if the user is nervous, the dialogue unit will use a calm tone. If the user is relaxed, the dialogue unit will use a cheerful tone. If the user is in a hurry, the dialogue unit will use a quick and concise tone. This improves user convenience by adjusting the way the dialogue is expressed according to the user's emotions. Specific methods and criteria for adjusting the way the dialogue is expressed include changing wording and adjusting the tone of the dialogue. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the dialogue unit may be performed using or without a generative AI. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0085] The dialogue unit can analyze the user's past dialogue history and select the optimal dialogue method. For example, the dialogue unit selects the most effective dialogue method based on the user's past dialogue history. The dialogue unit identifies frequently used dialogue methods from the user's past dialogue history and uses them with emphasis. The dialogue unit analyzes the user's past dialogue history and proposes the optimal dialogue timing. In this way, the optimal dialogue method can be selected by analyzing the user's past dialogue history. Specific content and analysis methods of past dialogue history include analysis of dialogue logs and analysis of user feedback. Specific content and selection criteria for the optimal dialogue method include dialogue methods that meet the user's needs and selection of methods based on past dialogue history. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input the user's past dialogue history data into a generative AI and have the generative AI perform the selection of the optimal dialogue method.

[0086] The dialogue unit can adjust the priority of dialogues according to the project's progress. For example, the dialogue unit monitors the project's progress in real time and prioritizes important dialogues. The dialogue unit dynamically adjusts the content of dialogues according to the project's progress. The dialogue unit analyzes the project's progress and proposes the optimal dialogue method. This allows for efficient dialogue by adjusting the priority of dialogues according to the project's progress. Specific methods and criteria for adjusting dialogue priorities include prioritizing high-priority dialogues and changing resource allocations. Some or all of the above processes in the dialogue unit may be performed using generative AI, or they may be performed without generative AI. For example, the dialogue unit can input project progress data into the generative AI and have the generative AI perform the adjustment of dialogue priorities.

[0087] The dialogue unit can estimate the user's emotions and adjust the length of the dialogue based on the estimated emotions. For example, if the user is nervous, the dialogue unit will provide a short, to-the-point dialogue. If the user is relaxed, the dialogue unit will provide a longer dialogue with detailed explanations. If the user is in a hurry, the dialogue unit will provide a quick and concise dialogue. This improves user convenience by adjusting the length of the dialogue according to the user's emotions. Specific methods and criteria for adjusting the length of the dialogue include adjusting the length according to the user's needs and adjusting the length according to the content of the dialogue. Emotion estimation is achieved using an emotion estimation function, such as 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 processing in the dialogue unit may be performed using generative AI or not. For example, the dialogue unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0088] The dialogue unit can customize the content of the conversation according to the user's role. For example, if the user is a developer, the dialogue unit will engage in conversations that include technical details. If the user is an administrator, the dialogue unit will engage in conversations about the progress of the project. If the user is an end-user, the dialogue unit will engage in conversations that are concise and easy to understand. By customizing the content of the conversation according to the user's role, user convenience is improved. Specific methods and criteria for customizing the content of the conversation include changing the content according to the user's role and changing the content according to the progress of the project. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input user role data into a generative AI and have the generative AI perform the customization of the conversation content.

[0089] The dialogue unit can change its dialogue method according to the scale of the project. For example, for small-scale projects, the dialogue unit provides a simple dialogue method. For large-scale projects, the dialogue unit provides a detailed dialogue method to achieve efficient dialogue. The dialogue unit proposes the optimal dialogue method according to the scale of the project. This makes efficient dialogue possible by changing the dialogue method according to the scale of the project. Specific methods and criteria for changing the dialogue method include changing the dialogue method according to the scale of the project and changing the method according to the user's needs. Some or all of the above processing in the dialogue unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the dialogue unit can input project scale data into a generative AI and have the generative AI execute the change in the dialogue method.

[0090] The feedback unit can estimate the user's emotions and adjust how the feedback is displayed based on the estimated emotions. For example, if the user is nervous, the feedback unit provides a simple and highly visible display method. If the user is relaxed, the feedback unit provides a display method that includes detailed information. If the user is in a hurry, the feedback unit provides a concise display method. This improves user convenience by adjusting the feedback display method according to the user's emotions. Specific methods and criteria for adjusting the feedback display method include visual display methods and changes to the display method according to the content of the feedback. Emotion estimation is achieved using an emotion estimation function with 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 processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0091] The feedback unit can analyze past feedback history and select the optimal display method. For example, the feedback unit can automatically select the most effective display method based on past feedback history. The feedback unit can identify frequently used display methods from past feedback history and use them with emphasis. The feedback unit analyzes past feedback history and proposes the optimal display timing. In this way, the optimal display method can be selected by analyzing past feedback history. Specific details and analysis methods for past feedback history include analysis of feedback logs and analysis of user feedback. Specific details and selection criteria for the optimal display method include display methods that meet user needs and selection of methods based on past feedback history. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can input past feedback history data into an AI model and have the AI ​​select the optimal display method.

[0092] The feedback unit can adjust the priority of feedback according to the project's progress. For example, the feedback unit monitors the project's progress in real time and prioritizes providing important feedback. The feedback unit dynamically adjusts the content of feedback according to the project's progress. The feedback unit analyzes the project's progress and proposes the optimal feedback method. This enables efficient feedback by adjusting the priority of feedback according to the project's progress. Specific methods and criteria for adjusting feedback priority include prioritizing high-priority feedback and changing resource allocation. Some or all of the above processes in the feedback unit may be performed using AI or not. For example, the feedback unit can input project progress data into an AI model and have the AI ​​perform the adjustment of feedback priority.

[0093] The feedback unit can estimate the user's emotions and customize the content of the feedback based on the estimated emotions. For example, if the user is nervous, the feedback unit will prioritize providing positive feedback. If the user is relaxed, the feedback unit will provide detailed feedback and clarify areas for improvement. If the user is in a hurry, the feedback unit will provide quick and concise feedback. This improves user convenience by customizing the content of feedback according to the user's emotions. Specific methods and criteria for customizing the content of feedback include providing feedback that meets the user's needs and changing the content according to the progress of the project. Emotion estimation is achieved using an emotion estimation function, such as 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 processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0094] The feedback section can adjust the display order of feedback according to the user's role. For example, if the user is a developer, the feedback section will prioritize displaying technical feedback. If the user is an administrator, the feedback section will prioritize displaying feedback regarding project progress. If the user is an end-user, the feedback section will prioritize displaying concise and easy-to-understand feedback. By adjusting the display order of feedback according to the user's role, user convenience is improved. Specific methods and criteria for adjusting the display order of feedback include prioritizing the display of high-priority feedback and changing the display order according to the user's role. Some or all of the above processing in the feedback section may be performed using AI or not. For example, the feedback section can input user role data into an AI model and have the AI ​​perform the adjustment of the display order of feedback.

[0095] The feedback unit can change its feedback method according to the scale of the project. For example, for small-scale projects, the feedback unit provides a simple feedback method. For large-scale projects, the feedback unit provides a detailed feedback method to achieve efficient feedback. The feedback unit proposes the optimal feedback method according to the scale of the project. This makes efficient feedback possible by changing the feedback method according to the scale of the project. Specific methods and criteria for changing the feedback method include changing the feedback method according to the scale of the project and changing the method according to user needs. Some or all of the above processing in the feedback unit may be performed using AI or not. For example, the feedback unit can input project scale data into an AI model and have the AI ​​perform the change in the feedback method.

[0096] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0097] The code management department can estimate the user's emotions and adjust code review feedback based on those emotions. For example, if the user is stressed, the feedback will be concise and positive comments will be prioritized. If the user is relaxed, detailed feedback will be provided, and areas for improvement will be clearly identified. If the user is in a hurry, only the essential points will be conveyed quickly. This improves user experience by adjusting the content of feedback according to the user's emotions. Emotion estimation can be performed using methods such as facial recognition, speech analysis, and text analysis.

[0098] The automation unit can estimate the user's emotions and adjust the notification method of the automated process based on the estimated emotions. For example, if the user is stressed, notifications will be minimized, and only important notifications will be sent. If the user is relaxed, detailed notifications will be provided, and the progress of the process will be reported step by step. If the user is in a hurry, concise and to-the-point notifications will be sent quickly. This improves user convenience by adjusting the notification method according to the user's emotions. Emotion estimation can be performed using methods such as facial recognition, voice analysis, and text analysis.

[0099] The dialogue unit can estimate the user's emotions and adjust the content of the dialogue based on those emotions. For example, if the user is stressed, the dialogue will be concise and prioritize positive content. If the user is relaxed, the dialogue will include detailed explanations to deepen the user's understanding. If the user is in a hurry, the dialogue will be quick and concise, providing necessary information promptly. By adjusting the content of the dialogue according to the user's emotions, the user experience is improved. Emotion estimation can be performed using methods such as facial recognition, speech analysis, and text analysis.

[0100] The feedback unit can estimate the user's emotions and adjust the timing of feedback based on those emotions. For example, if the user is stressed, feedback can be delayed and provided when the user is relaxed. If the user is relaxed, feedback can be provided immediately to deepen the user's understanding. If the user is in a hurry, quick and concise feedback can be provided to quickly convey the necessary information. This improves user convenience by adjusting the timing of feedback according to the user's emotions. Emotion estimation can be performed using methods such as facial recognition, voice analysis, and text analysis.

[0101] The code management unit can estimate the user's emotions and adjust the code versioning method based on those emotions. For example, if the user is stressed, it provides a simple versioning method and simplifies the operation. If the user is relaxed, it provides detailed versioning options and suggests a customizable management method. If the user is in a hurry, it prioritizes voice input to allow for quick versioning. In this way, the user experience is improved by adjusting the versioning method according to the user's emotions. Emotion estimation can be performed using methods such as facial recognition, voice analysis, and text analysis.

[0102] The code management department can adjust the frequency of code reviews according to the project's progress. For example, in the early stages of a project, frequent code reviews are conducted to ensure code quality. In the middle stages of the project, the review frequency is reduced to prioritize development speed. In the final stages of the project, frequent reviews are conducted again to ensure final quality. By adjusting the frequency of code reviews according to the project's progress, efficient development becomes possible.

[0103] The automation department can adjust the priority of automation processes according to the project's progress. For example, in the early stages of a project, the build process is prioritized to solidify the foundation. In the middle stages of the project, the test process is prioritized to ensure quality. In the final stages of the project, the deployment process is prioritized to prepare for release. This allows for efficient project management by adjusting the priority of automation processes according to the project's progress.

[0104] The dialogue section can customize the content of the conversation according to the user's role. For example, if the user is a developer, the conversation will include technical details. If the user is an administrator, the conversation will be about the progress of the project. If the user is an end-user, the conversation will be concise and easy to understand. By customizing the dialogue content according to the user's role, user convenience is improved.

[0105] The feedback department can adjust the content of feedback according to the project's progress. For example, in the initial stages of the project, basic feedback is provided to confirm the direction. In the middle stages, detailed feedback is provided to check progress. In the final stages of the project, final feedback is provided to confirm the level of completion. By adjusting the content of feedback according to the project's progress, efficient project management becomes possible.

[0106] The feedback section can adjust how feedback is displayed according to the user's role. For example, if the user is a developer, technical feedback will be prioritized. If the user is an administrator, feedback regarding project progress will be prioritized. If the user is an end-user, concise and easy-to-understand feedback will be prioritized. By adjusting how feedback is displayed according to the user's role, user convenience is improved.

[0107] The following briefly describes the processing flow for example form 2.

[0108] Step 1: The Code Management Department manages the code and data. The Code Management Department centrally manages code and data such as source code, binary data, and configuration files, and tracks the history of the code and data using a version control system. This allows for recording change history and reverting to previous versions. Step 2: The Automation Department executes the automation process using data managed by the Code Management Department. The Automation Department executes automation processes such as build, test, and deployment processes, and optimizes settings and updates AI agents. For example, it performs performance tuning, optimizes resource allocation, retrains AI agent models, and adjusts parameters. The Automation Department executes the automation process using automation tools such as Screwdriver. Step 3: The dialogue unit interacts with the user based on the process executed by the automation unit. The dialogue unit provides real-time conversational support using generative AI and interacts with the user using means such as chatbots, voice assistants, and interactive UIs. Using generative AI, it provides appropriate answers to user questions and provides support to solve user problems. For example, the generative AI generates answers to user questions in real time. Step 4: The feedback unit provides visual feedback based on the information obtained by the dialogue unit. The feedback unit visualizes the AI ​​agent's growth using graphs and displays indicators such as performance improvement and learning progress in graph form. The dashboard visually displays the AI ​​agent's growth and provides visual feedback so that users can intuitively understand it.

[0109] 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.

[0110] 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 text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (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 from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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 various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts 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.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0111] 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.

[0112] Each of the multiple elements described above, including the code management unit, automation unit, dialogue unit, and feedback unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the code management unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12. The dialogue unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The feedback unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0113] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.).

[0125] 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.

[0126] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0127] 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.

[0128] Each of the multiple elements described above, including the code management unit, automation unit, dialogue unit, and feedback unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the code management unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12. The dialogue unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The feedback unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0129] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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).

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.).

[0141] 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.

[0142] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the code management unit, automation unit, dialogue unit, and feedback unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the code management unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12. The dialogue unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The feedback unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0145] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the code management unit, automation unit, dialogue unit, and feedback unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the code management unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The automation unit is implemented by the specific processing unit 290 of the data processing unit 12. The dialogue unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The feedback unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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."

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] (Note 1) The code management department manages the code and data, An automation unit that executes an automation process using data managed by the code management unit, A dialogue unit that interacts with the user based on the process executed by the automation unit, The system includes a feedback unit that provides visual feedback based on the information obtained by the dialogue unit. A system characterized by the following features. (Note 2) The aforementioned code management unit, Track the history of code and data. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned automation unit, Optimize settings and update the AI ​​agent. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned dialogue unit, We provide real-time interactive support using generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned feedback unit is Visualize the growth of AI agents using graphs. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned code management unit, We estimate user sentiment and adjust how we manage code and data based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned code management unit, Analyze past version history and select the optimal management method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned code management unit, Prioritize management according to the project's progress. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned code management unit, It estimates the user's sentiment and adjusts the order in which the code and data history are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned code management unit, Dynamically change access permissions based on the roles of team members. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned code management unit, Customize management methods according to the scale of the project. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned automation unit, It estimates the user's emotions and adjusts the timing of automated processes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned automation unit, Analyze past execution results and select the optimal settings. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned automation unit, Adjust process priorities according to the project's progress. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned automation unit, It estimates the user's emotions and adjusts the execution order of automated processes based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned automation unit, Customize the process according to the scale of the project. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned automation unit, Dynamically change process execution permissions according to the roles of team members. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the way the dialogue is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned dialogue unit, Analyze the user's past conversation history and select the optimal conversation method. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned dialogue unit, Prioritize dialogue according to the project's progress. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned dialogue unit, It estimates the user's emotions and adjusts the length of the conversation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned dialogue unit, Customize the dialogue content according to the user's role. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned dialogue unit, Change the dialogue method depending on the scale of the project. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned feedback unit is It estimates the user's emotions and adjusts how feedback is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned feedback unit is Analyze past feedback history and select the optimal display method. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned feedback unit is Prioritize feedback based on the project's progress. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned feedback unit is It estimates the user's emotions and customizes the content of the feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned feedback unit is Adjust the display order of feedback according to the user's role. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned feedback unit is The feedback method will be changed depending on the scale of the project. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0181] 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. The code management department manages the code and data, An automation unit that executes an automation process using data managed by the code management unit, A dialogue unit that interacts with the user based on the process executed by the automation unit, The system includes a feedback unit that provides visual feedback based on the information obtained by the dialogue unit. A system characterized by the following features.

2. The aforementioned code management unit, Track the history of code and data. The system according to feature 1.

3. The aforementioned automation unit, Optimize settings and update the AI ​​agent. The system according to feature 1.

4. The aforementioned dialogue unit, Providing real-time interactive support using generative AI. The system according to feature 1.

5. The aforementioned feedback unit is Visualize the growth of AI agents using graphs. The system according to feature 1.

6. The aforementioned code management unit, We estimate user sentiment and adjust how we manage code and data based on that estimated sentiment. The system according to feature 1.

7. The aforementioned code management unit, Analyze past version history and select the optimal management method. The system according to feature 1.

8. The aforementioned code management unit, Adjust management priorities according to the project's progress. The system according to feature 1.

Images