system

Abstract

The system according to this embodiment aims to efficiently design, build, and operate AI agents without relying on technical skills. [Solution] The system according to the embodiment comprises a design unit, a feedback unit, a test unit, and a deployment unit. The design unit designs an AI agent. The feedback unit tests the AI ​​agent designed by the design unit. The test unit automatically tests the AI ​​agent tested by the feedback unit. The deployment unit deploys the AI ​​agent tested by the test unit to a cloud platform.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there is a problem that the design, construction, and operation of an AI agent are complex and depend on technical skills, making efficient development and operation difficult.

[0005] The system according to the embodiment aims to efficiently design, construct, and operate an AI agent without depending on technical skills.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a design unit, a feedback unit, a test unit, and a deployment unit. The design unit designs an AI agent. The feedback unit tests the AI ​​agent designed by the design unit. The test unit automatically tests the AI ​​agent tested by the feedback unit. The deployment unit deploys the AI ​​agent tested by the test unit to a cloud platform. [Effects of the Invention]

[0007] The system according to this embodiment allows for the efficient design, construction, and operation of AI agents without relying on technical skills. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The AI ​​agent construction support platform according to an embodiment of the present invention is a platform that provides a multi-functional environment for facilitating the design, construction, and operation of AI agents. This platform incorporates an intuitive drag-and-drop visual programming tool and industry-specific templates, enabling the development of AI agents regardless of the user's technical skills, thereby addressing a wide range of business needs. For example, the user designs an AI agent using the drag-and-drop visual programming tool. This tool provides industry-specific customized templates, allowing the user to quickly and easily design an AI agent simply by selecting a template. Next, the designed AI agent is tested using a real-time feedback function. This function allows the user to check the AI ​​agent's operation in real time and make necessary corrections immediately. Furthermore, the operation of the AI ​​agent is verified using an automated testing function. This function allows the user to automatically test the AI ​​agent's operation and confirm that there are no problems. Finally, the AI ​​agent is deployed to a cloud platform and put into operation. This platform supports seamless integration with existing application programming interfaces, allowing users to integrate it with existing systems. In this way, the AI ​​agent construction support platform provides an environment in which users can quickly and easily design, build, and operate AI agents, achieving business efficiency and maximizing revenue. This enables the AI ​​agent development support platform to provide users with an environment where they can quickly and easily design, build, and operate AI agents, thereby improving business efficiency and maximizing revenue.

[0029] The AI ​​agent construction support platform according to this embodiment comprises a design unit, a feedback unit, a testing unit, and a deployment unit. The design unit designs the AI ​​agent. The design unit can, for example, design the AI ​​agent using a drag-and-drop visual programming tool. The design unit may also include a template unit that provides industry-specific customized templates. For example, the design unit may include a customization unit that allows users to select a template and customize the AI ​​agent. The feedback unit tests the AI ​​agent designed by the design unit. The feedback unit may, for example, include a scenario unit that checks the operation of the AI ​​agent in real time and makes necessary corrections. The testing unit automatically tests the AI ​​agent tested by the feedback unit. The testing unit can, for example, automatically test the operation of the AI ​​agent and check for any problems. The deployment unit deploys the AI ​​agent tested by the testing unit to a cloud platform. The deployment unit may, for example, include an integration unit for integrating with existing systems. As a result, the AI ​​agent construction support platform according to this embodiment enables efficient design, testing, automated testing, and deployment of AI agents.

[0030] The design department designs AI agents. For example, the design department can design AI agents using a drag-and-drop visual programming tool. This visual programming tool provides an intuitive interface, allowing users to design AI agents without programming expertise. Users can build the AI ​​agent's operation flow by dragging and dropping various components within the tool. For example, users define the AI ​​agent's operation by placing components such as input data processing, conditional branching, and external API calls, and connecting them with lines. The design department can also have a template department that provides industry-specific templates. This allows users to select a template specific to their industry and customize the AI ​​agent based on it. For example, a template for the medical industry would have pre-built functions for patient data management and diagnostic support, allowing users to build an AI agent simply by adding or modifying the necessary functions. Furthermore, the design department can have a customization department where users can select a template and customize the AI ​​agent. In the customization department, users can freely edit each component of the template and optimize the AI ​​agent to their needs. For example, users can change the data processing logic included in the template or add new functions. This allows the design department to provide users with an environment that enables them to design AI agents efficiently and flexibly.

[0031] The feedback unit tests the AI ​​agent designed by the design unit. The feedback unit may include a scenario unit that, for example, checks the AI ​​agent's behavior in real time and makes necessary corrections. In the scenario unit, users can set up behavior scenarios for the AI ​​agent and simulate the AI ​​agent's behavior based on those scenarios. For example, a user can check the AI ​​agent's response to specific input data and evaluate whether the response is as expected. If there is a problem with the AI ​​agent's behavior, the user can make corrections in real time through the scenario unit. This allows the feedback unit to provide a feedback loop for quickly evaluating the AI ​​agent's behavior and making necessary corrections. Furthermore, the feedback unit can collect feedback from users and incorporate it into the AI ​​agent's design. For example, if a user suggests specific improvements to the AI ​​agent's behavior, that suggestion can be fed back to the design unit, which can then modify the AI ​​agent's design based on that suggestion. In this way, the feedback unit can support the design of AI agents that meet user needs and improve the quality of the AI ​​agent.

[0032] The testing department automatically tests AI agents that have been tested by the feedback department. For example, the testing department can automatically test the operation of AI agents and check for any problems. Specifically, the testing department verifies the operation of AI agents based on pre-configured test cases. This allows for automatic verification of whether the AI ​​agents are operating as expected. For example, the testing department provides various input data to the AI ​​agent and verifies its responses. If the AI ​​agent's response is not as expected, the testing department reports the problem and provides feedback to the design department and feedback department. This allows the testing department to automatically verify the quality of AI agents and respond quickly if problems occur. Furthermore, the testing department can conduct load tests and stress tests to evaluate the performance and scalability of AI agents. This allows for prior verification of how much load the AI ​​agent can withstand in a real operating environment. For example, the testing department sends a large number of requests to the AI ​​agent and monitors its response time and resource usage. This allows for the identification of performance bottlenecks in the AI ​​agent and the implementation of necessary improvements. In this way, the testing department can play a crucial role in improving the quality and performance of AI agents.

[0033] The Deployment Unit deploys AI agents tested by the Testing Unit to the cloud infrastructure. The Deployment Unit may also include an Integration Unit for integrating with existing systems. The Integration Unit can perform necessary configurations and adjustments to ensure seamless integration of AI agents with existing systems and services. For example, it can configure AI agents to interact with databases and external APIs, ensuring smooth operation after deployment. Furthermore, the Deployment Unit can provide a deployment pipeline to automate the AI ​​agent deployment process. This allows users to deploy AI agents easily and quickly. For example, the Deployment Unit automates the entire process of building the AI ​​agent code, resolving necessary dependencies, and deploying it to the cloud infrastructure. This significantly reduces deployment effort and prevents deployment errors. Additionally, the Deployment Unit can include functions to support monitoring and maintenance of AI agents after deployment. For example, it can monitor the AI ​​agent's operational status in real time and issue alerts if an anomaly occurs. The Deployment Unit also provides version control and rollback functionality for AI agents, allowing for quick reverting to previous versions in case of problems. This enables the Deployment Unit to support stable operation of AI agents and improve the overall system reliability.

[0034] The design department includes a template department that provides customized templates for each industry. For example, the design department can provide industry-specific templates, enabling users to quickly design AI agents. The template department can provide elements and settings specific to each industry. This allows users to quickly design AI agents by providing industry-specific templates.

[0035] The design department includes a customization department where users can select templates and customize AI agents. For example, the design department allows users to design AI agents tailored to their specific needs by selecting templates and customizing them. The customization department can provide template selection criteria and customizable items, enabling users to select templates and customize AI agents.

[0036] The feedback unit includes a scenario unit that monitors the AI ​​agent's behavior in real time and makes necessary corrections. For example, by monitoring the AI ​​agent's behavior in real time, the feedback unit allows users to check the AI ​​agent's actions in real time and make immediate necessary corrections. For instance, the scenario unit can provide the monitoring tools to be used and the items to be checked. This enables real-time monitoring of the AI ​​agent's behavior and the necessary corrections.

[0037] The deployment unit includes an integration unit for linking with existing systems. For example, by linking with existing systems, the deployment unit can facilitate the operation of the AI ​​agent for users. For instance, the integration unit can provide the types of systems to link with and the linking procedures. This makes it easier to operate the AI ​​agent by linking with existing systems.

[0038] The design department can analyze past design history and propose the optimal design methodology. For example, the design department can suggest the optimal template based on the design methodology the user has used in the past. Furthermore, the design department can prioritize displaying frequently used functions based on the user's past design history. In addition, the design department can analyze the user's past design history and propose the most efficient design methodology. Thus, by analyzing past design history, the design department can propose the optimal design methodology.

[0039] The design department can determine design priorities based on the user's business processes during the design phase. For example, the design department can analyze the user's business processes and prioritize the design of the most important functions. Furthermore, the design department can automatically suggest necessary functions based on the user's business processes. In addition, the design department can visualize the design progress while considering the user's business processes. This enables efficient design by determining design priorities based on the user's business processes.

[0040] The design department can prioritize the display of relevant design elements during the design process, taking into account the user's geographical location. For example, the design department can prioritize the display of region-specific design elements based on the user's geographical location. Furthermore, the design department can suggest relevant templates, taking the user's geographical location into consideration. In addition, the design department can suggest the optimal design methodology based on the user's geographical location. This enables efficient design by prioritizing the display of relevant design elements while considering the user's geographical location.

[0041] The design department can analyze users' social media activity during the design phase and propose relevant design ideas. For example, the design department can analyze users' social media activity and propose relevant design ideas. Furthermore, the design department can propose optimal templates based on users' social media activity. In addition, the design department can visualize the design progress while considering users' social media activity. This allows them to propose relevant design ideas by analyzing users' social media activity.

[0042] The feedback unit can provide optimal feedback by referring to past feedback history. For example, it can provide optimal feedback based on feedback the user has received in the past. Furthermore, the feedback unit can prioritize displaying frequently used feedback methods based on the user's past feedback history. In addition, the feedback unit can analyze the user's past feedback history and suggest the most efficient feedback method. This allows for the provision of optimal feedback by referring to past feedback history.

[0043] The feedback unit can improve the accuracy of feedback by analyzing the AI ​​agent's operation history during the feedback process. For example, the feedback unit can analyze the AI ​​agent's operation history and provide optimal feedback. Furthermore, the feedback unit can identify frequently occurring problems from the AI ​​agent's operation history and improve the accuracy of feedback. In addition, the feedback unit can propose the most efficient feedback method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, the accuracy of feedback can be improved.

[0044] The feedback unit can prioritize providing relevant feedback by considering the user's geographical location information during the feedback process. For example, the feedback unit can prioritize providing region-specific feedback based on the user's geographical location information. Furthermore, the feedback unit can suggest relevant feedback considering the user's geographical location information. In addition, the feedback unit can suggest the optimal feedback method based on the user's geographical location information. This enables efficient feedback by prioritizing the provision of relevant feedback while considering the user's geographical location information.

[0045] The feedback unit can analyze the user's social media activity and provide relevant feedback during the feedback process. For example, the feedback unit can analyze the user's social media activity and provide relevant feedback. Furthermore, the feedback unit can suggest the optimal feedback method based on the user's social media activity. In addition, the feedback unit can visualize the progress of the feedback process, taking into account the user's social media activity. This allows for the provision of relevant feedback by analyzing the user's social media activity.

[0046] The testing unit can propose the optimal testing method by referring to past test history during testing. For example, it can propose the optimal testing method based on tests the user has previously undergone. Furthermore, the testing unit can prioritize displaying frequently used testing methods based on the user's past test history. In addition, the testing unit can analyze the user's past test history and propose the most efficient testing method. Thus, by referring to past test history, the optimal testing method can be proposed.

[0047] The testing department can improve test accuracy by analyzing the AI ​​agent's operation history during testing. For example, the testing department can analyze the AI ​​agent's operation history and propose the optimal testing method. Furthermore, the testing department can identify frequently occurring problems from the AI ​​agent's operation history, thereby improving test accuracy. In addition, the testing department can propose the most efficient testing method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, test accuracy can be improved.

[0048] The testing department can prioritize relevant tests during testing by considering the user's geographical location. For example, the testing department can prioritize region-specific tests based on the user's geographical location. Furthermore, the testing department can suggest relevant tests considering the user's geographical location. In addition, the testing department can suggest the optimal testing method based on the user's geographical location. This allows for more efficient testing by prioritizing relevant tests while considering the user's geographical location.

[0049] The testing department can analyze users' social media activity during testing and conduct relevant tests. For example, the testing department can analyze users' social media activity and conduct relevant tests. Furthermore, the testing department can propose optimal testing methods based on users' social media activity. In addition, the testing department can visualize the progress of the tests, taking into account users' social media activity. This allows for the implementation of relevant tests by analyzing users' social media activity.

[0050] The deployment unit can suggest the optimal deployment method by referring to past deployment history during deployment. For example, the deployment unit can suggest the optimal deployment method based on the deployment method the user has used in the past. Furthermore, the deployment unit can prioritize displaying frequently used deployment methods from the user's past deployment history. In addition, the deployment unit can analyze the user's past deployment history and suggest the most efficient deployment method. This allows the system to suggest the optimal deployment method by referring to past deployment history.

[0051] The deployment unit can improve deployment accuracy by analyzing the AI ​​agent's operation history during deployment. For example, the deployment unit can analyze the AI ​​agent's operation history and propose the optimal deployment method. Furthermore, the deployment unit can identify frequently occurring problems from the AI ​​agent's operation history, thereby improving deployment accuracy. In addition, the deployment unit can propose the most efficient deployment method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, deployment accuracy can be improved.

[0052] The deployment unit can prioritize relevant deployments by considering the user's geographical location during deployment. For example, the deployment unit can prioritize region-specific deployments based on the user's geographical location. Furthermore, the deployment unit can propose relevant deployments considering the user's geographical location. In addition, the deployment unit can propose the optimal deployment method based on the user's geographical location. This enables efficient deployment by prioritizing relevant deployments while considering the user's geographical location.

[0053] The deployment unit can analyze users' social media activity during deployment and perform relevant deployments. For example, the deployment unit can analyze users' social media activity and perform relevant deployments. Furthermore, the deployment unit can propose the optimal deployment method based on users' social media activity. In addition, the deployment unit can visualize the deployment progress, taking into account users' social media activity. This allows for the implementation of relevant deployments by analyzing users' social media activity.

[0054] The template section can suggest the most suitable template by referring to past template usage history during template selection. For example, the template section can suggest the most suitable template based on templates the user has used in the past. Furthermore, the template section can prioritize displaying frequently used templates based on the user's past template usage history. In addition, the template section can analyze the user's past template usage history and suggest the most efficient template. This allows the system to suggest the most suitable template by referring to past template usage history.

[0055] The template section can prioritize displaying relevant templates by considering the user's geographical location during template selection. For example, the template section can prioritize displaying region-specific templates based on the user's geographical location. Furthermore, the template section can suggest relevant templates considering the user's geographical location. In addition, the template section can suggest the most suitable template based on the user's geographical location. This enables efficient template selection by prioritizing the display of relevant templates based on the user's geographical location.

[0056] The customization section can suggest the optimal customization method by referring to past customization history during the customization process. For example, it can suggest the optimal customization method based on the customization methods the user has used in the past. Furthermore, the customization section can prioritize displaying frequently used customization methods from the user's past customization history. In addition, the customization section can analyze the user's past customization history and suggest the most efficient customization method. This allows for the suggestion of the optimal customization method by referring to past customization history.

[0057] The customization department can prioritize relevant customizations by considering the user's geographical location during the customization process. For example, the customization department can prioritize region-specific customizations based on the user's geographical location. Furthermore, the customization department can propose relevant customizations considering the user's geographical location. In addition, the customization department can propose the optimal customization method based on the user's geographical location. This enables efficient customization by prioritizing relevant customizations while considering the user's geographical location.

[0058] The scenario department can suggest the optimal scenario when creating a scenario by referring to past scenario history. For example, it can suggest the optimal scenario based on scenarios the user has used in the past. Furthermore, the scenario department can prioritize displaying frequently used scenarios from the user's past scenario history. In addition, the scenario department can analyze the user's past scenario history and suggest the most efficient scenario. This allows for the suggestion of the optimal scenario by referring to past scenario history.

[0059] The scenario creation function can prioritize the creation of relevant scenarios by considering the user's geographical location information. For example, the scenario creation function can prioritize the creation of region-specific scenarios based on the user's geographical location information. Furthermore, the scenario creation function can propose relevant scenarios considering the user's geographical location information. In addition, the scenario creation function can propose the optimal scenario based on the user's geographical location information. This enables efficient scenario creation by prioritizing the creation of relevant scenarios while considering the user's geographical location information.

[0060] The integration unit can propose the optimal integration method by referring to past integration history during integration. For example, the integration unit can propose the optimal integration method based on integration methods previously used by the user. Furthermore, the integration unit can prioritize displaying frequently used integration methods from the user's past integration history. In addition, the integration unit can analyze the user's past integration history and propose the most efficient integration method. Thus, by referring to past integration history, the optimal integration method can be proposed.

[0061] The collaboration unit can improve the accuracy of collaboration by analyzing the AI ​​agent's operation history during collaboration. For example, the collaboration unit can analyze the AI ​​agent's operation history and propose the optimal collaboration method. Furthermore, the collaboration unit can identify frequently occurring problems from the AI ​​agent's operation history and improve the accuracy of collaboration. In addition, the collaboration unit can propose the most efficient collaboration method based on the AI ​​agent's operation history. In this way, the accuracy of collaboration can be improved by analyzing the AI ​​agent's operation history.

[0062] The integration unit can prioritize relevant integrations by considering the user's geographical location information during integration. For example, the integration unit can prioritize region-specific integrations based on the user's geographical location information. Furthermore, the integration unit can propose relevant integrations considering the user's geographical location information. In addition, the integration unit can propose the optimal integration method based on the user's geographical location information. This enables efficient integration by prioritizing relevant integrations while considering the user's geographical location information.

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

[0064] The design department can analyze past design history and propose the optimal design methodology. For example, the design department can suggest the optimal template based on the design methodology the user has used in the past. Furthermore, the design department can prioritize displaying frequently used functions based on the user's past design history. In addition, the design department can analyze the user's past design history and propose the most efficient design methodology. Thus, by analyzing past design history, the design department can propose the optimal design methodology.

[0065] The design department can determine design priorities based on the user's business processes during the design phase. For example, the design department can analyze the user's business processes and prioritize the design of the most important functions. Furthermore, the design department can automatically suggest necessary functions based on the user's business processes. In addition, the design department can visualize the design progress while considering the user's business processes. This enables efficient design by determining design priorities based on the user's business processes.

[0066] The design department can prioritize the display of relevant design elements during the design process, taking into account the user's geographical location. For example, the design department can prioritize the display of region-specific design elements based on the user's geographical location. Furthermore, the design department can suggest relevant templates, taking the user's geographical location into consideration. In addition, the design department can suggest the optimal design methodology based on the user's geographical location. This enables efficient design by prioritizing the display of relevant design elements while considering the user's geographical location.

[0067] The feedback unit can provide optimal feedback by referring to past feedback history. For example, it can provide optimal feedback based on feedback the user has received in the past. Furthermore, the feedback unit can prioritize displaying frequently used feedback methods based on the user's past feedback history. In addition, the feedback unit can analyze the user's past feedback history and suggest the most efficient feedback method. This allows for the provision of optimal feedback by referring to past feedback history.

[0068] The feedback unit can improve the accuracy of feedback by analyzing the AI ​​agent's operation history during the feedback process. For example, the feedback unit can analyze the AI ​​agent's operation history and provide optimal feedback. Furthermore, the feedback unit can identify frequently occurring problems from the AI ​​agent's operation history and improve the accuracy of feedback. In addition, the feedback unit can propose the most efficient feedback method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, the accuracy of feedback can be improved.

[0069] The feedback unit can prioritize providing relevant feedback by considering the user's geographical location information during the feedback process. For example, the feedback unit can prioritize providing region-specific feedback based on the user's geographical location information. Furthermore, the feedback unit can suggest relevant feedback considering the user's geographical location information. In addition, the feedback unit can suggest the optimal feedback method based on the user's geographical location information. This enables efficient feedback by prioritizing the provision of relevant feedback while considering the user's geographical location information.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The design department designs the AI ​​agent. The design department can design the AI ​​agent using, for example, a drag-and-drop visual programming tool. Alternatively, the design department may have a template department that provides industry-specific customized templates. For example, the design department may have a customization department where users can select a template and customize the AI ​​agent. Step 2: The feedback unit tests the AI ​​agent designed by the design unit. The feedback unit may include, for example, a scenario unit that checks the AI ​​agent's behavior in real time and makes necessary corrections. Step 3: The testing unit automatically tests the AI ​​agent that has been tested by the feedback unit. For example, the testing unit can automatically test the operation of the AI ​​agent and check for any problems. Step 4: The deployment unit deploys the AI ​​agent tested by the testing unit to the cloud infrastructure. The deployment unit may include, for example, an integration unit for integrating with existing systems.

[0072] (Example of form 2) The AI ​​agent construction support platform according to an embodiment of the present invention is a platform that provides a multi-functional environment for facilitating the design, construction, and operation of AI agents. This platform incorporates an intuitive drag-and-drop visual programming tool and industry-specific templates, enabling the development of AI agents regardless of the user's technical skills, thereby addressing a wide range of business needs. For example, the user designs an AI agent using the drag-and-drop visual programming tool. This tool provides industry-specific customized templates, allowing the user to quickly and easily design an AI agent simply by selecting a template. Next, the designed AI agent is tested using a real-time feedback function. This function allows the user to check the AI ​​agent's operation in real time and make necessary corrections immediately. Furthermore, the operation of the AI ​​agent is verified using an automated testing function. This function allows the user to automatically test the AI ​​agent's operation and confirm that there are no problems. Finally, the AI ​​agent is deployed to a cloud platform and put into operation. This platform supports seamless integration with existing application programming interfaces, allowing users to integrate it with existing systems. In this way, the AI ​​agent construction support platform provides an environment in which users can quickly and easily design, build, and operate AI agents, achieving business efficiency and maximizing revenue. This enables the AI ​​agent development support platform to provide users with an environment where they can quickly and easily design, build, and operate AI agents, thereby improving business efficiency and maximizing revenue.

[0073] The AI ​​agent construction support platform according to this embodiment comprises a design unit, a feedback unit, a testing unit, and a deployment unit. The design unit designs the AI ​​agent. The design unit can, for example, design the AI ​​agent using a drag-and-drop visual programming tool. The design unit may also include a template unit that provides industry-specific customized templates. For example, the design unit may include a customization unit that allows users to select a template and customize the AI ​​agent. The feedback unit tests the AI ​​agent designed by the design unit. The feedback unit may, for example, include a scenario unit that checks the operation of the AI ​​agent in real time and makes necessary corrections. The testing unit automatically tests the AI ​​agent tested by the feedback unit. The testing unit can, for example, automatically test the operation of the AI ​​agent and check for any problems. The deployment unit deploys the AI ​​agent tested by the testing unit to a cloud platform. The deployment unit may, for example, include an integration unit for integrating with existing systems. As a result, the AI ​​agent construction support platform according to this embodiment enables efficient design, testing, automated testing, and deployment of AI agents.

[0074] The design department designs AI agents. For example, the design department can design AI agents using a drag-and-drop visual programming tool. This visual programming tool provides an intuitive interface, allowing users to design AI agents without programming expertise. Users can build the AI ​​agent's operation flow by dragging and dropping various components within the tool. For example, users define the AI ​​agent's operation by placing components such as input data processing, conditional branching, and external API calls, and connecting them with lines. The design department can also have a template department that provides industry-specific templates. This allows users to select a template specific to their industry and customize the AI ​​agent based on it. For example, a template for the medical industry would have pre-built functions for patient data management and diagnostic support, allowing users to build an AI agent simply by adding or modifying the necessary functions. Furthermore, the design department can have a customization department where users can select a template and customize the AI ​​agent. In the customization department, users can freely edit each component of the template and optimize the AI ​​agent to their needs. For example, users can change the data processing logic included in the template or add new functions. This allows the design department to provide users with an environment that enables them to design AI agents efficiently and flexibly.

[0075] The feedback unit tests the AI ​​agent designed by the design unit. The feedback unit may include a scenario unit that, for example, checks the AI ​​agent's behavior in real time and makes necessary corrections. In the scenario unit, users can set up behavior scenarios for the AI ​​agent and simulate the AI ​​agent's behavior based on those scenarios. For example, a user can check the AI ​​agent's response to specific input data and evaluate whether the response is as expected. If there is a problem with the AI ​​agent's behavior, the user can make corrections in real time through the scenario unit. This allows the feedback unit to provide a feedback loop for quickly evaluating the AI ​​agent's behavior and making necessary corrections. Furthermore, the feedback unit can collect feedback from users and incorporate it into the AI ​​agent's design. For example, if a user suggests specific improvements to the AI ​​agent's behavior, that suggestion can be fed back to the design unit, which can then modify the AI ​​agent's design based on that suggestion. In this way, the feedback unit can support the design of AI agents that meet user needs and improve the quality of the AI ​​agent.

[0076] The testing department automatically tests AI agents that have been tested by the feedback department. For example, the testing department can automatically test the operation of AI agents and check for any problems. Specifically, the testing department verifies the operation of AI agents based on pre-configured test cases. This allows for automatic verification of whether the AI ​​agents are operating as expected. For example, the testing department provides various input data to the AI ​​agent and verifies its responses. If the AI ​​agent's response is not as expected, the testing department reports the problem and provides feedback to the design department and feedback department. This allows the testing department to automatically verify the quality of AI agents and respond quickly if problems occur. Furthermore, the testing department can conduct load tests and stress tests to evaluate the performance and scalability of AI agents. This allows for prior verification of how much load the AI ​​agent can withstand in a real operating environment. For example, the testing department sends a large number of requests to the AI ​​agent and monitors its response time and resource usage. This allows for the identification of performance bottlenecks in the AI ​​agent and the implementation of necessary improvements. In this way, the testing department can play a crucial role in improving the quality and performance of AI agents.

[0077] The Deployment Unit deploys AI agents tested by the Testing Unit to the cloud infrastructure. The Deployment Unit may also include an Integration Unit for integrating with existing systems. The Integration Unit can perform necessary configurations and adjustments to ensure seamless integration of AI agents with existing systems and services. For example, it can configure AI agents to interact with databases and external APIs, ensuring smooth operation after deployment. Furthermore, the Deployment Unit can provide a deployment pipeline to automate the AI ​​agent deployment process. This allows users to deploy AI agents easily and quickly. For example, the Deployment Unit automates the entire process of building the AI ​​agent code, resolving necessary dependencies, and deploying it to the cloud infrastructure. This significantly reduces deployment effort and prevents deployment errors. Additionally, the Deployment Unit can include functions to support monitoring and maintenance of AI agents after deployment. For example, it can monitor the AI ​​agent's operational status in real time and issue alerts if an anomaly occurs. The Deployment Unit also provides version control and rollback functionality for AI agents, allowing for quick reverting to previous versions in case of problems. This enables the Deployment Unit to support stable operation of AI agents and improve the overall system reliability.

[0078] The design department includes a template department that provides customized templates for each industry. For example, the design department can provide industry-specific templates, enabling users to quickly design AI agents. The template department can provide elements and settings specific to each industry. This allows users to quickly design AI agents by providing industry-specific templates.

[0079] The design department includes a customization department where users can select templates and customize AI agents. For example, the design department allows users to design AI agents tailored to their specific needs by selecting templates and customizing them. The customization department can provide template selection criteria and customizable items, enabling users to select templates and customize AI agents.

[0080] The feedback unit includes a scenario unit that monitors the AI ​​agent's behavior in real time and makes necessary corrections. For example, by monitoring the AI ​​agent's behavior in real time, the feedback unit allows users to check the AI ​​agent's actions in real time and make immediate necessary corrections. For instance, the scenario unit can provide the monitoring tools to be used and the items to be checked. This enables real-time monitoring of the AI ​​agent's behavior and the necessary corrections.

[0081] The deployment unit includes an integration unit for linking with existing systems. For example, by linking with existing systems, the deployment unit can facilitate the operation of the AI ​​agent for users. For instance, the integration unit can provide the types of systems to link with and the linking procedures. This makes it easier to operate the AI ​​agent by linking with existing systems.

[0082] The design team can estimate the user's emotions and adjust the design interface based on those emotions. For example, if the user is stressed, the design team can provide a simple interface and minimize the number of steps required. If the user is relaxed, the design team can provide detailed options and suggest a customizable design approach. Furthermore, if the user is in a hurry, the design team can prioritize voice input to allow for faster design progress. This improves usability by adjusting the design interface according to the user's emotions. 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) or multimodal generation AI.

[0083] The design department can analyze past design history and propose the optimal design methodology. For example, the design department can suggest the optimal template based on the design methodology the user has used in the past. Furthermore, the design department can prioritize displaying frequently used functions based on the user's past design history. In addition, the design department can analyze the user's past design history and propose the most efficient design methodology. Thus, by analyzing past design history, the design department can propose the optimal design methodology.

[0084] The design department can determine design priorities based on the user's business processes during the design phase. For example, the design department can analyze the user's business processes and prioritize the design of the most important functions. Furthermore, the design department can automatically suggest necessary functions based on the user's business processes. In addition, the design department can visualize the design progress while considering the user's business processes. This enables efficient design by determining design priorities based on the user's business processes.

[0085] The design department can estimate the user's emotions and visualize the design progress based on those emotions. For example, if the user is stressed, the design department can display the progress simply to reduce visual burden. If the user is relaxed, the design department can display detailed progress to allow them to grasp the overall picture of the design. Furthermore, if the user is in a hurry, the design department can allow them to quickly check the progress. This improves usability by visualizing the design progress according to the user's emotions. 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) or multimodal generation AI.

[0086] The design department can prioritize the display of relevant design elements during the design process, taking into account the user's geographical location. For example, the design department can prioritize the display of region-specific design elements based on the user's geographical location. Furthermore, the design department can suggest relevant templates, taking the user's geographical location into consideration. In addition, the design department can suggest the optimal design methodology based on the user's geographical location. This enables efficient design by prioritizing the display of relevant design elements while considering the user's geographical location.

[0087] The design department can analyze users' social media activity during the design phase and propose relevant design ideas. For example, the design department can analyze users' social media activity and propose relevant design ideas. Furthermore, the design department can propose optimal templates based on users' social media activity. In addition, the design department can visualize the design progress while considering users' social media activity. This allows them to propose relevant design ideas by analyzing users' social media activity.

[0088] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the user is stressed, the feedback unit can provide simple feedback and minimize the number of steps required. If the user is relaxed, the feedback unit can provide detailed feedback and suggest customizable feedback methods. Furthermore, if the user is in a hurry, the feedback unit can prioritize voice feedback to provide feedback quickly. This improves usability by adjusting the content of feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The feedback unit can provide optimal feedback by referring to past feedback history. For example, it can provide optimal feedback based on feedback the user has received in the past. Furthermore, the feedback unit can prioritize displaying frequently used feedback methods based on the user's past feedback history. In addition, the feedback unit can analyze the user's past feedback history and suggest the most efficient feedback method. This allows for the provision of optimal feedback by referring to past feedback history.

[0090] The feedback unit can improve the accuracy of feedback by analyzing the AI ​​agent's operation history during the feedback process. For example, the feedback unit can analyze the AI ​​agent's operation history and provide optimal feedback. Furthermore, the feedback unit can identify frequently occurring problems from the AI ​​agent's operation history and improve the accuracy of feedback. In addition, the feedback unit can propose the most efficient feedback method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, the accuracy of feedback can be improved.

[0091] The feedback unit can estimate the user's emotions and prioritize feedback based on those emotions. For example, if the user is stressed, the feedback unit can prioritize providing important feedback. If the user is relaxed, the feedback unit can provide detailed feedback and suggest customizable feedback methods. Furthermore, if the user is in a hurry, the feedback unit can provide feedback quickly. This ensures that important feedback is prioritized by prioritizing feedback according to the user's emotions. 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) or multimodal generation AI.

[0092] The feedback unit can prioritize providing relevant feedback by considering the user's geographical location information during the feedback process. For example, the feedback unit can prioritize providing region-specific feedback based on the user's geographical location information. Furthermore, the feedback unit can suggest relevant feedback considering the user's geographical location information. In addition, the feedback unit can suggest the optimal feedback method based on the user's geographical location information. This enables efficient feedback by prioritizing the provision of relevant feedback while considering the user's geographical location information.

[0093] The feedback unit can analyze the user's social media activity and provide relevant feedback during the feedback process. For example, the feedback unit can analyze the user's social media activity and provide relevant feedback. Furthermore, the feedback unit can suggest the optimal feedback method based on the user's social media activity. In addition, the feedback unit can visualize the progress of the feedback process, taking into account the user's social media activity. This allows for the provision of relevant feedback by analyzing the user's social media activity.

[0094] The testing unit can estimate the user's emotions and adjust the test content based on those emotions. For example, if the user is stressed, the testing unit can provide a simple test with minimal steps. If the user is relaxed, the testing unit can provide a more detailed test and suggest a customizable testing method. Furthermore, if the user is in a hurry, the testing unit can prioritize voice tests to allow for faster completion of the test. This improves usability by adjusting the test content according to the user's emotions. 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) or multimodal generation AI.

[0095] The testing unit can propose the optimal testing method by referring to past test history during testing. For example, it can propose the optimal testing method based on tests the user has previously undergone. Furthermore, the testing unit can prioritize displaying frequently used testing methods based on the user's past test history. In addition, the testing unit can analyze the user's past test history and propose the most efficient testing method. Thus, by referring to past test history, the optimal testing method can be proposed.

[0096] The testing department can improve test accuracy by analyzing the AI ​​agent's operation history during testing. For example, the testing department can analyze the AI ​​agent's operation history and propose the optimal testing method. Furthermore, the testing department can identify frequently occurring problems from the AI ​​agent's operation history, thereby improving test accuracy. In addition, the testing department can propose the most efficient testing method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, test accuracy can be improved.

[0097] The testing unit can estimate the user's emotions and prioritize tests based on those emotions. For example, if the user is stressed, the testing unit can prioritize important tests. If the user is relaxed, the testing unit can provide detailed tests and suggest customizable testing methods. Furthermore, if the user is in a hurry, the testing unit can provide tests quickly. This allows for the prioritization of important tests based on the user's emotions. 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) or multimodal generation AI.

[0098] The testing department can prioritize relevant tests during testing by considering the user's geographical location. For example, the testing department can prioritize region-specific tests based on the user's geographical location. Furthermore, the testing department can suggest relevant tests considering the user's geographical location. In addition, the testing department can suggest the optimal testing method based on the user's geographical location. This allows for more efficient testing by prioritizing relevant tests while considering the user's geographical location.

[0099] The testing department can analyze users' social media activity during testing and conduct relevant tests. For example, the testing department can analyze users' social media activity and conduct relevant tests. Furthermore, the testing department can propose optimal testing methods based on users' social media activity. In addition, the testing department can visualize the progress of the tests, taking into account users' social media activity. This allows for the implementation of relevant tests by analyzing users' social media activity.

[0100] The deployment unit can estimate the user's emotions and adjust the deployment timing based on the estimated emotions. For example, if the user is stressed, the deployment unit can delay the deployment to allow the user time to relax. Conversely, if the user is relaxed, the deployment unit can advance the deployment to enable rapid operation. Furthermore, if the user is in a hurry, the deployment unit can optimize the deployment timing to enable rapid operation. This improves usability by adjusting the deployment timing according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0101] The deployment unit can suggest the optimal deployment method by referring to past deployment history during deployment. For example, the deployment unit can suggest the optimal deployment method based on the deployment method the user has used in the past. Furthermore, the deployment unit can prioritize displaying frequently used deployment methods from the user's past deployment history. In addition, the deployment unit can analyze the user's past deployment history and suggest the most efficient deployment method. This allows the system to suggest the optimal deployment method by referring to past deployment history.

[0102] The deployment unit can improve deployment accuracy by analyzing the AI ​​agent's operation history during deployment. For example, the deployment unit can analyze the AI ​​agent's operation history and propose the optimal deployment method. Furthermore, the deployment unit can identify frequently occurring problems from the AI ​​agent's operation history, thereby improving deployment accuracy. In addition, the deployment unit can propose the most efficient deployment method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, deployment accuracy can be improved.

[0103] The deployment unit can estimate the user's emotions and determine deployment priorities based on those emotions. For example, if the user is stressed, the deployment unit can prioritize important deployments. If the user is relaxed, the deployment unit can provide detailed deployments and suggest customizable deployment methods. Furthermore, if the user is in a hurry, the deployment unit can provide rapid deployments. This allows for prioritizing important deployments based on the user's emotions. 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) or multimodal generation AI.

[0104] The deployment unit can prioritize relevant deployments by considering the user's geographical location during deployment. For example, the deployment unit can prioritize region-specific deployments based on the user's geographical location. Furthermore, the deployment unit can propose relevant deployments considering the user's geographical location. In addition, the deployment unit can propose the optimal deployment method based on the user's geographical location. This enables efficient deployment by prioritizing relevant deployments while considering the user's geographical location.

[0105] The deployment unit can analyze users' social media activity during deployment and perform relevant deployments. For example, the deployment unit can analyze users' social media activity and perform relevant deployments. Furthermore, the deployment unit can propose the optimal deployment method based on users' social media activity. In addition, the deployment unit can visualize the deployment progress, taking into account users' social media activity. This allows for the implementation of relevant deployments by analyzing users' social media activity.

[0106] The template section can estimate the user's emotions and select a template based on those emotions. For example, if the user is stressed, the template section can provide a simple template and minimize the number of steps required. If the user is relaxed, the template section can provide a detailed template and suggest a customizable template. Furthermore, if the user is in a hurry, the template section can enable quick template selection. This improves usability by selecting templates according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The template section can suggest the most suitable template by referring to past template usage history during template selection. For example, the template section can suggest the most suitable template based on templates the user has used in the past. Furthermore, the template section can prioritize displaying frequently used templates based on the user's past template usage history. In addition, the template section can analyze the user's past template usage history and suggest the most efficient template. This allows the system to suggest the most suitable template by referring to past template usage history.

[0108] The template section can estimate the user's emotions and prioritize templates based on those emotions. For example, if the user is stressed, the template section can prioritize providing important templates. If the user is relaxed, the template section can provide detailed templates and suggest customizable templates. Furthermore, if the user is in a hurry, the template section can provide templates quickly. This allows for the priority of important templates by prioritizing them according to the user's emotions. 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) or multimodal generation AI.

[0109] The template section can prioritize displaying relevant templates by considering the user's geographical location during template selection. For example, the template section can prioritize displaying region-specific templates based on the user's geographical location. Furthermore, the template section can suggest relevant templates considering the user's geographical location. In addition, the template section can suggest the most suitable template based on the user's geographical location. This enables efficient template selection by prioritizing the display of relevant templates based on the user's geographical location.

[0110] The customization unit can estimate the user's emotions and adjust the customization based on those emotions. For example, if the user is stressed, the customization unit can provide simple customization and minimize the number of steps required. If the user is relaxed, the customization unit can provide detailed customization and suggest customizable options. Furthermore, if the user is in a hurry, the customization unit can enable rapid customization. This improves usability by adjusting the customization content according to the user's emotions. 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) or multimodal generation AI.

[0111] The customization section can suggest the optimal customization method by referring to past customization history during the customization process. For example, it can suggest the optimal customization method based on the customization methods the user has used in the past. Furthermore, the customization section can prioritize displaying frequently used customization methods from the user's past customization history. In addition, the customization section can analyze the user's past customization history and suggest the most efficient customization method. This allows for the suggestion of the optimal customization method by referring to past customization history.

[0112] The customization unit can estimate the user's emotions and determine the priority of customizations based on those emotions. For example, if the user is stressed, the customization unit can prioritize providing important customizations. If the user is relaxed, the customization unit can provide detailed customizations and suggest customizable options. Furthermore, if the user is in a hurry, the customization unit can provide customizations quickly. This allows for the priority of important customizations by determining the priority of customizations according to the user's emotions. 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) or multimodal generation AI.

[0113] The customization department can prioritize relevant customizations by considering the user's geographical location during the customization process. For example, the customization department can prioritize region-specific customizations based on the user's geographical location. Furthermore, the customization department can propose relevant customizations considering the user's geographical location. In addition, the customization department can propose the optimal customization method based on the user's geographical location. This enables efficient customization by prioritizing relevant customizations while considering the user's geographical location.

[0114] The scenario unit can estimate the user's emotions and adjust the scenario content based on those emotions. For example, if the user is stressed, the scenario unit can provide a simple scenario and minimize the number of steps required. If the user is relaxed, the scenario unit can provide a detailed scenario and suggest a customizable scenario. Furthermore, if the user is in a hurry, the scenario unit can enable them to progress through the scenario quickly. This improves usability by adjusting the scenario content according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0115] The scenario department can suggest the optimal scenario when creating a scenario by referring to past scenario history. For example, it can suggest the optimal scenario based on scenarios the user has used in the past. Furthermore, the scenario department can prioritize displaying frequently used scenarios from the user's past scenario history. In addition, the scenario department can analyze the user's past scenario history and suggest the most efficient scenario. This allows for the suggestion of the optimal scenario by referring to past scenario history.

[0116] The scenario unit can estimate the user's emotions and prioritize scenarios based on those emotions. For example, if the user is stressed, the scenario unit can prioritize providing important scenarios. If the user is relaxed, the scenario unit can provide detailed scenarios and suggest customizable scenarios. Furthermore, if the user is in a hurry, the scenario unit can provide scenarios quickly. This allows for the prioritization of important scenarios based on the user's emotions. 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) or multimodal generation AI.

[0117] The scenario creation function can prioritize the creation of relevant scenarios by considering the user's geographical location information. For example, the scenario creation function can prioritize the creation of region-specific scenarios based on the user's geographical location information. Furthermore, the scenario creation function can propose relevant scenarios considering the user's geographical location information. In addition, the scenario creation function can propose the optimal scenario based on the user's geographical location information. This enables efficient scenario creation by prioritizing the creation of relevant scenarios while considering the user's geographical location information.

[0118] The interaction unit can estimate the user's emotions and adjust the interaction content based on the estimated emotions. For example, if the user is stressed, the interaction unit can provide simple interaction content and minimize the number of steps required. If the user is relaxed, the interaction unit can provide detailed interaction content and suggest a customizable interaction method. Furthermore, if the user is in a hurry, the interaction unit can expedite the process. This improves usability by adjusting the interaction content according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0119] The integration unit can propose the optimal integration method by referring to past integration history during integration. For example, the integration unit can propose the optimal integration method based on integration methods previously used by the user. Furthermore, the integration unit can prioritize displaying frequently used integration methods from the user's past integration history. In addition, the integration unit can analyze the user's past integration history and propose the most efficient integration method. Thus, by referring to past integration history, the optimal integration method can be proposed.

[0120] The collaboration unit can improve the accuracy of collaboration by analyzing the AI ​​agent's operation history during collaboration. For example, the collaboration unit can analyze the AI ​​agent's operation history and propose the optimal collaboration method. Furthermore, the collaboration unit can identify frequently occurring problems from the AI ​​agent's operation history and improve the accuracy of collaboration. In addition, the collaboration unit can propose the most efficient collaboration method based on the AI ​​agent's operation history. In this way, the accuracy of collaboration can be improved by analyzing the AI ​​agent's operation history.

[0121] The interaction unit can estimate the user's emotions and determine the priority of interactions based on those emotions. For example, if the user is stressed, the interaction unit can prioritize important interactions. If the user is relaxed, the interaction unit can provide detailed interactions and suggest customizable interaction methods. Furthermore, if the user is in a hurry, the interaction unit can provide interactions quickly. This allows for the priority of important interactions by determining the priority of interactions according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0122] The integration unit can prioritize relevant integrations by considering the user's geographical location information during integration. For example, the integration unit can prioritize region-specific integrations based on the user's geographical location information. Furthermore, the integration unit can propose relevant integrations considering the user's geographical location information. In addition, the integration unit can propose the optimal integration method based on the user's geographical location information. This enables efficient integration by prioritizing relevant integrations while considering the user's geographical location information.

[0123] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0124] The design team can estimate the user's emotions and adjust the design interface based on those emotions. For example, if the user is stressed, the design team can provide a simple interface and minimize the number of steps required. If the user is relaxed, the design team can provide detailed options and suggest a customizable design approach. Furthermore, if the user is in a hurry, the design team can prioritize voice input to allow for faster design progress. This improves usability by adjusting the design interface according to the user's emotions. 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) or multimodal generation AI.

[0125] The design department can analyze past design history and propose the optimal design methodology. For example, the design department can suggest the optimal template based on the design methodology the user has used in the past. Furthermore, the design department can prioritize displaying frequently used functions based on the user's past design history. In addition, the design department can analyze the user's past design history and propose the most efficient design methodology. Thus, by analyzing past design history, the design department can propose the optimal design methodology.

[0126] The design department can determine design priorities based on the user's business processes during the design phase. For example, the design department can analyze the user's business processes and prioritize the design of the most important functions. Furthermore, the design department can automatically suggest necessary functions based on the user's business processes. In addition, the design department can visualize the design progress while considering the user's business processes. This enables efficient design by determining design priorities based on the user's business processes.

[0127] The design department can estimate the user's emotions and visualize the design progress based on those emotions. For example, if the user is stressed, the design department can display the progress simply to reduce visual burden. If the user is relaxed, the design department can display detailed progress to allow them to grasp the overall picture of the design. Furthermore, if the user is in a hurry, the design department can allow them to quickly check the progress. This improves usability by visualizing the design progress according to the user's emotions. 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) or multimodal generation AI.

[0128] The design department can prioritize the display of relevant design elements during the design process, taking into account the user's geographical location. For example, the design department can prioritize the display of region-specific design elements based on the user's geographical location. Furthermore, the design department can suggest relevant templates, taking the user's geographical location into consideration. In addition, the design department can suggest the optimal design methodology based on the user's geographical location. This enables efficient design by prioritizing the display of relevant design elements while considering the user's geographical location.

[0129] The feedback unit can estimate the user's emotions and adjust the content of the feedback based on the estimated emotions. For example, if the user is stressed, the feedback unit can provide simple feedback and minimize the number of steps required. If the user is relaxed, the feedback unit can provide detailed feedback and suggest customizable feedback methods. Furthermore, if the user is in a hurry, the feedback unit can prioritize voice feedback to provide feedback quickly. This improves usability by adjusting the content of feedback according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0130] The feedback unit can provide optimal feedback by referring to past feedback history. For example, it can provide optimal feedback based on feedback the user has received in the past. Furthermore, the feedback unit can prioritize displaying frequently used feedback methods based on the user's past feedback history. In addition, the feedback unit can analyze the user's past feedback history and suggest the most efficient feedback method. This allows for the provision of optimal feedback by referring to past feedback history.

[0131] The feedback unit can improve the accuracy of feedback by analyzing the AI ​​agent's operation history during the feedback process. For example, the feedback unit can analyze the AI ​​agent's operation history and provide optimal feedback. Furthermore, the feedback unit can identify frequently occurring problems from the AI ​​agent's operation history and improve the accuracy of feedback. In addition, the feedback unit can propose the most efficient feedback method based on the AI ​​agent's operation history. Thus, by analyzing the AI ​​agent's operation history, the accuracy of feedback can be improved.

[0132] The feedback unit can estimate the user's emotions and prioritize feedback based on those emotions. For example, if the user is stressed, the feedback unit can prioritize providing important feedback. If the user is relaxed, the feedback unit can provide detailed feedback and suggest customizable feedback methods. Furthermore, if the user is in a hurry, the feedback unit can provide feedback quickly. This ensures that important feedback is prioritized by prioritizing feedback according to the user's emotions. 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) or multimodal generation AI.

[0133] The feedback unit can prioritize providing relevant feedback by considering the user's geographical location information during the feedback process. For example, the feedback unit can prioritize providing region-specific feedback based on the user's geographical location information. Furthermore, the feedback unit can suggest relevant feedback considering the user's geographical location information. In addition, the feedback unit can suggest the optimal feedback method based on the user's geographical location information. This enables efficient feedback by prioritizing the provision of relevant feedback while considering the user's geographical location information.

[0134] The following briefly describes the processing flow for example form 2.

[0135] Step 1: The design department designs the AI ​​agent. The design department can design the AI ​​agent using, for example, a drag-and-drop visual programming tool. Alternatively, the design department may have a template department that provides industry-specific customized templates. For example, the design department may have a customization department where users can select a template and customize the AI ​​agent. Step 2: The feedback unit tests the AI ​​agent designed by the design unit. The feedback unit may include, for example, a scenario unit that checks the AI ​​agent's behavior in real time and makes necessary corrections. Step 3: The testing unit automatically tests the AI ​​agent that has been tested by the feedback unit. For example, the testing unit can automatically test the operation of the AI ​​agent and check for any problems. Step 4: The deployment unit deploys the AI ​​agent tested by the testing unit to the cloud infrastructure. The deployment unit may include, for example, an integration unit for integrating with existing systems.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] Each of the multiple elements described above, including the design unit, feedback unit, test unit, and deployment unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the design unit is implemented by the control unit 46A of the smart device 14, which designs the AI ​​agent using a drag-and-drop visual programming tool. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the operation of the AI ​​agent in real time and makes necessary corrections. The test unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically tests the operation of the AI ​​agent and checks for any problems. The deployment unit is implemented by the specific processing unit 290 of the data processing unit 12, which deploys the AI ​​agent to the cloud platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0140] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] Each of the multiple elements described above, including the design unit, feedback unit, test unit, and deployment unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the design unit is implemented by the control unit 46A of the smart glasses 214, which designs the AI ​​agent using a drag-and-drop visual programming tool. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the operation of the AI ​​agent in real time and makes necessary corrections. The test unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically tests the operation of the AI ​​agent and checks for any problems. The deployment unit is implemented by the specific processing unit 290 of the data processing unit 12, which deploys the AI ​​agent to the cloud platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0156] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] Each of the multiple elements described above, including the design unit, feedback unit, test unit, and deployment unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the design unit is implemented by the control unit 46A of the headset terminal 314, which designs the AI ​​agent using a drag-and-drop visual programming tool. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the operation of the AI ​​agent in real time and makes necessary corrections. The test unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically tests the operation of the AI ​​agent and checks for any problems. The deployment unit is implemented by the specific processing unit 290 of the data processing unit 12, which deploys the AI ​​agent to the cloud platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0172] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.).

[0185] 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.

[0186] 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.

[0187] 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.

[0188] Each of the multiple elements described above, including the design unit, feedback unit, test unit, and deployment unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the design unit is implemented by the control unit 46A of the robot 414, which designs the AI ​​agent using a drag-and-drop visual programming tool. The feedback unit is implemented by the specific processing unit 290 of the data processing unit 12, which checks the operation of the AI ​​agent in real time and makes necessary corrections. The test unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically tests the operation of the AI ​​agent and checks for any problems. The deployment unit is implemented by the specific processing unit 290 of the data processing unit 12, which deploys the AI ​​agent to the cloud platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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."

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] (Note 1) The design department, which designs AI agents, A feedback unit that tests the AI ​​agent designed by the aforementioned design unit, A test unit that automatically tests the AI ​​agent tested by the aforementioned feedback unit, The system includes a deployment unit that deploys the AI ​​agent tested by the test unit to a cloud platform. A system characterized by the following features. (Note 2) The aforementioned design department, It features a template section that provides customized templates for each industry. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned design department, It includes a customization section where users can select templates to customize the AI ​​agent. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned feedback unit is It includes a scenario-based section that monitors the AI ​​agent's behavior in real time and makes necessary corrections. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned deployment unit is It includes an integration section for linking with existing systems. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned design department, It estimates the user's emotions and adjusts the design interface based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned design department, We analyze past design history and propose the optimal design methodology. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned design department, Prioritizing the design based on the user's business processes during the design phase. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned design department, It estimates user emotions and visualizes the design progress based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned design department, During the design phase, relevant design elements are prioritized based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned design department, During the design phase, we analyze users' social media activity and propose relevant design ideas. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned feedback unit is It estimates the user's emotions and adjusts the content of the feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned feedback unit is When providing feedback, we refer to past feedback history to provide the most appropriate feedback. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned feedback unit is During feedback, the AI ​​agent's behavioral history is analyzed to improve the accuracy of the feedback. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned feedback unit is It estimates the user's emotions and prioritizes feedback based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned feedback unit is When providing feedback, we prioritize providing relevant feedback by considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned feedback unit is When providing feedback, we analyze the user's social media activity and provide relevant feedback. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned test unit is The system estimates the user's emotions and adjusts the test content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned test unit is During testing, we refer to past test history to suggest the optimal testing method. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned test unit is During testing, the AI ​​agent's behavior history is analyzed to improve test accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned test unit is We estimate user emotions and determine test priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned test unit is During testing, prioritize tests that take into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned test unit is During testing, we analyze users' social media activity and conduct relevant tests. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned deployment unit is It estimates user sentiment and adjusts deployment timing based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned deployment unit is During deployment, the system will refer to past deployment history to suggest the optimal deployment method. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned deployment unit is During deployment, the AI ​​agent's operational history is analyzed to improve deployment accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned deployment unit is It estimates user sentiment and determines deployment priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned deployment unit is During deployment, prioritize deployments that take into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned deployment unit is During deployment, we analyze users' social media activity and perform relevant deployments. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned template section is The system estimates the user's emotions and selects a template based on those emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned template section is When selecting a template, we refer to past template usage history to suggest the most suitable template. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned template section is It estimates the user's emotions and determines the priority of templates based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned template section is When selecting a template, the system prioritizes displaying templates relevant to the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned customization unit is It estimates the user's emotions and adjusts the customization based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned customization unit is During customization, we refer to past customization history to suggest the optimal customization method. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned customization unit is It estimates the user's emotions and determines the priority of customization based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned customization unit is During customization, the system prioritizes relevant customizations based on the user's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned scenario section is, It estimates the user's emotions and adjusts the scenario content based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned scenario section is, When creating a scenario, the system will refer to past scenario history to suggest the most suitable scenario. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned scenario section is, It estimates user emotions and prioritizes scenarios based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned scenario section is, When creating scenarios, prioritize creating relevant scenarios by considering the user's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 42) The aforementioned linkage unit is, It estimates the user's emotions and adjusts the content of the interaction based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 43) The aforementioned linkage unit is, When integrating, the system will refer to past integration history to propose the most suitable integration method. The system described in Appendix 5, characterized by the features described herein. (Note 44) The aforementioned linkage unit is, During integration, the AI ​​agent's operation history is analyzed to improve the accuracy of the integration. The system described in Appendix 5, characterized by the features described herein. (Note 45) The aforementioned linkage unit is, It estimates the user's emotions and determines the priority of collaborations based on the estimated user emotions. The system described in Appendix 5, characterized by the features described herein. (Note 46) The aforementioned linkage unit is, When integrating, the system prioritizes relevant integrations by considering the user's geographical location. The system described in Appendix 5, characterized by the features described herein. [Explanation of symbols]

[0208] 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 design department that designs AI agents, A feedback unit that tests the AI ​​agent designed by the aforementioned design unit, A test unit that automatically tests the AI ​​agent tested by the feedback unit, The system includes a deployment unit that deploys the AI ​​agent tested by the test unit to a cloud platform. A system characterized by the following features.

2. The aforementioned design department, It features a template section that provides customized templates for each industry. The system according to feature 1.

3. The aforementioned design department, It includes a customization section where users can select templates to customize the AI ​​agent. The system according to feature 1.

4. The aforementioned feedback unit is It includes a scenario-based section that monitors the AI ​​agent's operation in real time and makes necessary corrections. The system according to feature 1.

5. The aforementioned deployment unit is It includes an integration section for linking with existing systems. The system according to feature 1.

6. The aforementioned design department, It estimates the user's emotions and adjusts the design interface based on those estimated emotions. The system according to feature 1.

7. The aforementioned design department, We analyze past design history and propose the optimal design methodology. The system according to feature 1.

8. The aforementioned design department, Prioritizing the design based on the user's business processes during the design phase. The system according to feature 1.

9. The aforementioned design department, It estimates user emotions and visualizes the design progress based on those estimated emotions. The system according to feature 1.

10. The aforementioned design department, During the design phase, relevant design elements are prioritized based on the user's geographical location. The system according to feature 1.

Images