system

Abstract

The system according to this embodiment aims to simplify the creation and management of agents and to efficiently perform specific tasks. [Solution] The system according to the embodiment comprises a selection unit, a pasting unit, a confirmation unit, an execution unit, and an output unit. The selection unit selects an agent. The pasting unit pastes input data to the agent selected by the selection unit. The confirmation unit confirms the execution plan of the agent based on the input data pasted by the pasting unit. The execution unit executes prompts based on the execution plan confirmed by the confirmation unit. The output unit outputs the results of the prompts executed by the execution unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, there is a problem that the creation and management of agents are complicated, and it is difficult to efficiently use and provide agents for executing specific tasks.

[0005] The system according to the embodiment aims to simplify the creation and management of agents and efficiently execute specific tasks.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a selection unit, a pasting unit, a confirmation unit, an execution unit, and an output unit. The selection unit selects an agent. The pasting unit pastes input data to the agent selected by the selection unit. The confirmation unit confirms the execution plan of the agent based on the input data pasted by the pasting unit. The execution unit executes prompts based on the execution plan confirmed by the confirmation unit. The output unit outputs the results of the prompts executed by the execution unit. [Effects of the Invention]

[0007] The system according to this embodiment simplifies the creation and management of agents and enables the efficient execution of specific tasks. [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 such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An agent platform system according to an embodiment of the present invention is a platform that can utilize and provide agents that perform various tasks. This agent platform system allows users to select an agent, paste input data, review the agent's execution plan, and execute prompts to deploy a specific combination of APIs and execute tasks. Outputs are displayed in communication tools, UIs, chatbots, etc. Furthermore, the creation of RAGs (Retrieval Augmented Generations) is also possible. General engineers can contribute to the creation of new agents by providing APIs, provided they have the necessary I / O. Agents are issued via FAST APIs, etc., making them available for use by others. Revenue sharing is provided to the creator based on usage. This platform supports the efficiency improvements and process automation of small and medium-sized enterprises, compensating for the lack of IT resources and enabling cost-effective business improvements. It also provides development engineers with a source of income as a side job and opportunities to utilize and improve their skills through agent development. For example, in the agent platform system, a user selects an agent and pastes input data. Next, they review the agent's execution plan and execute prompts. The agent deploys a specific combination of APIs and executes tasks. Outputs are displayed in communication tools, UIs, chatbots, etc. Furthermore, the creation of RAGs is also possible. General engineers can contribute to the creation of new agents by providing APIs, provided they have the necessary I / O. Agents are issued via FAST APIs, making them available for use by others. Revenue sharing is provided to the creators based on usage. This allows the agent platform system to support small and medium-sized enterprises in improving operational efficiency and automating processes, compensating for IT resource shortages and enabling cost-effective business improvements. It also provides development engineers with a source of income as a side job and offers them opportunities to utilize and improve their skills through agent development.

[0029] The agent platform system according to the embodiment comprises a selection unit, a pasting unit, a confirmation unit, an execution unit, and an output unit. The selection unit selects an agent. The selection unit provides, for example, an interface for the user to select an agent. The selection unit can also recommend the most suitable agent to the user based on the type and function of the agent. For example, the selection unit recommends the most suitable agent based on the user's past selection history and current task. The selection unit can also use AI to assist in agent selection. For example, the selection unit analyzes the user's selection history and uses AI to recommend the most suitable agent. The pasting unit pastes input data to the agent selected by the selection unit. The pasting unit provides, for example, an interface for the user to paste input data. The pasting unit can also suggest the most suitable pasting method based on the format and content of the input data. For example, the pasting unit suggests the most suitable pasting method based on the format of the user's input data. The pasting unit can also use AI to assist in pasting input data. For example, the pasting unit analyzes the user's input data and uses AI to suggest the most suitable pasting method. The confirmation unit confirms the agent's execution plan based on the input data pasted by the pasting unit. The verification unit provides, for example, an interface for the user to verify the agent's execution plan. The verification unit can also suggest the optimal verification method based on the content and progress of the execution plan. For example, the verification unit suggests the optimal verification method based on the content of the user's execution plan. The verification unit can also use AI to assist in verifying the execution plan. For example, the verification unit analyzes the user's execution plan and suggests the optimal verification method using AI. The execution unit executes prompts based on the execution plan verified by the verification unit. The execution unit provides, for example, an interface for the user to execute prompts. The execution unit can also suggest the optimal execution method based on the content and execution method of the prompts. For example, the execution unit suggests the optimal execution method based on the content of the user's prompts. The execution unit can also use AI to assist in executing prompts.For example, the execution unit analyzes the user's prompts and uses AI to suggest the optimal execution method. The output unit outputs the results of the prompts executed by the execution unit. The output unit provides, for example, an interface for the user to review the output. The output unit can also suggest the optimal display method based on the format and content of the output. For example, the output unit suggests the optimal display method based on the format of the user's output. The output unit can also use AI to assist in displaying the output. For example, the output unit analyzes the user's output and uses AI to suggest the optimal display method. As a result, the agent platform system according to the embodiment can efficiently perform a series of steps from agent selection to output.

[0030] The selection unit selects an agent. For example, the selection unit provides an interface for the user to select an agent. Specifically, the selection unit provides a visual interface that allows the user to easily compare the types and functions of agents. For example, it displays a list of agent features and functions, allowing the user to view detailed information about each agent. The selection unit can also recommend the most suitable agent based on the user's past selection history and current task. For example, it analyzes the user's past agent selection history and recommends the agent best suited to the current task. Furthermore, the selection unit can use AI to assist in agent selection. For example, it uses AI to analyze the user's selection history and current task and recommend the most suitable agent. The AI ​​learns the user's selection patterns and task content, enabling more accurate recommendations. This allows the selection unit to help users select agents efficiently and improve work efficiency.

[0031] The pasting unit pastes the input data to the agent selected by the selection unit. The pasting unit provides, for example, an interface for the user to paste the input data. Specifically, the pasting unit provides an interface that allows the user to easily drag and drop the input data, making data pasting intuitive. The pasting unit can also suggest the optimal pasting method based on the format and content of the input data. For example, the pasting unit can automatically recognize the format of the data entered by the user and suggest the optimal pasting method. Furthermore, the pasting unit can use AI to assist in pasting input data. For example, the pasting unit can analyze the user's input data with AI and suggest the optimal pasting method. The AI ​​can learn the content and format of the data and provide a more efficient pasting method. In this way, the pasting unit can help the user paste input data efficiently and improve work efficiency.

[0032] The verification unit verifies the agent's execution plan based on the input data pasted by the pasting unit. The verification unit provides, for example, an interface for the user to verify the agent's execution plan. Specifically, the verification unit visually displays the agent's execution plan, allowing the user to grasp the plan's content and progress at a glance. The verification unit can also suggest the optimal verification method based on the content and progress of the execution plan. For example, the verification unit can automatically analyze the user's execution plan and suggest the optimal verification method. Furthermore, the verification unit can use AI to assist in verifying the execution plan. For example, the verification unit can analyze the user's execution plan with AI and suggest the optimal verification method. The AI ​​can learn the plan's content and progress and provide a more efficient verification method. In this way, the verification unit can help users efficiently verify the agent's execution plan and improve work efficiency.

[0033] The execution unit executes prompts based on the execution plan confirmed by the verification unit. The execution unit provides, for example, an interface for the user to execute prompts. Specifically, the execution unit provides buttons and command input fields that allow the user to easily execute prompts, making the execution operation intuitive. The execution unit can also suggest the optimal execution method based on the content and method of execution of the prompt. For example, the execution unit can automatically analyze the content of the user's prompt and suggest the optimal execution method. Furthermore, the execution unit can use AI to assist in the execution of prompts. For example, the execution unit can analyze the user's prompt with AI and suggest the optimal execution method. The AI ​​can learn the content and method of execution of prompts and provide more efficient execution methods. In this way, the execution unit can help the user execute prompts efficiently and improve work efficiency.

[0034] The output unit outputs the results of prompts executed by the execution unit. The output unit provides, for example, an interface for the user to review the output. Specifically, the output unit visually displays the execution results so that the user can grasp the results at a glance. The output unit can also suggest the optimal display method based on the format and content of the output. For example, the output unit can automatically analyze the format of the user's output and suggest the optimal display method. Furthermore, the output unit can use AI to assist in displaying the output. For example, the output unit can analyze the user's output with AI and suggest the optimal display method. The AI ​​can learn the content and format of the output and provide a more efficient display method. In this way, the output unit can help the user efficiently review the execution results and improve work efficiency.

[0035] The output unit can display the output through communication tools, UIs, chatbots, etc. For example, the output unit can display the output in a chat application. The output unit can also send the output via email. The output unit can also display the output through a web interface. For example, the output unit can display the output in a web browser. The output unit can also display the output through a mobile interface. For example, the output unit can display the output in a smartphone app. The output unit can also display the output using a chatbot with conversational AI. For example, the output unit can display the output in a script-based chatbot. This improves user convenience by displaying the output in a variety of ways.

[0036] The execution unit can deploy specific combinations of APIs to perform tasks. For example, the execution unit can deploy combinations of REST APIs. It can also deploy combinations of SOAP APIs. It can also deploy combinations of GraphQL APIs. For example, the execution unit can retrieve data using a REST API and send data using a SOAP API. It can also retrieve data using a GraphQL API and send data using a REST API. By deploying combinations of APIs, the execution unit can efficiently perform complex tasks. This means that task execution is made more efficient by deploying specific combinations of APIs.

[0037] The output unit can create RAGs. The output unit can collect data using, for example, information acquisition methods. The output unit can also generate data using generation algorithms. The output unit can also create RAGs by combining information acquisition and generation. For example, the output unit can collect data using web scraping and generate data using natural language generation algorithms. The output unit can also acquire data using APIs and generate data using generation AI. By creating RAGs, the output unit can streamline information acquisition and generation. Thus, creating RAGs streamlines information acquisition and generation.

[0038] The execution unit can contribute to the creation of new agents by utilizing APIs provided by general engineers. For example, the execution unit can use open-source APIs. The execution unit can also use commercial APIs. The execution unit can create new agents using APIs provided by engineers. For example, the execution unit can create new agents using open-source APIs. The execution unit can also create new agents using commercial APIs. By utilizing APIs, the execution unit can streamline the creation of new agents. This facilitates the creation of new agents by utilizing APIs provided by general engineers.

[0039] The output unit can issue agents using FAST APIs, etc., making them available for use by others. For example, the output unit can issue agents using FAST APIs. The output unit can also issue agents using REST APIs. The output unit can also issue agents using GraphQL APIs. For example, the output unit can issue agents using FAST APIs, making them available for use by others. The output unit can also issue agents using REST APIs, making them available for use by others. By issuing agents using APIs, the output unit can expand the range of agent usage. This expands the range of agent usage by making agents available to others.

[0040] The selection function can analyze the user's past agent selection history and recommend the most suitable agent based on their preferences. For example, it can prioritize displaying agents that the user has frequently used in the past. The selection function can also recommend agents suitable for specific tasks based on the user's past selection history. The selection function can also analyze the user's selection history and suggest agents suitable for similar tasks. In this way, by analyzing past selection history, it can recommend the most suitable agent to the user.

[0041] The selection section can prioritize displaying agents that are highly relevant to the user's current tasks and projects. For example, it can prioritize displaying agents related to the user's current project. The selection section can also recommend the most suitable agent based on the user's task content. The selection section can also suggest appropriate agents according to the progress of the user's project. This improves the user's work efficiency by prioritizing the display of agents relevant to the current task or project.

[0042] The selection section can prioritize displaying region-specific agents by considering the user's geographical location. For example, if the user is in a specific region, the selection section will display agents specialized for that region. The selection section can also recommend agents that provide region-specific services based on the user's geographical location. The selection section can also prioritize displaying region-related agents by considering the user's location. This allows for the priority display of region-specific agents by considering geographical location.

[0043] The selection unit can analyze a user's social media activity and recommend relevant agents. For example, the selection unit can display agents related to topics the user has shown interest in on social media. The selection unit can also recommend agents that the user might be interested in based on their social media activity. The selection unit can also analyze a user's social media activity history and suggest relevant agents. In this way, by analyzing social media activity, it can recommend agents relevant to the user.

[0044] The pasting function can analyze the user's past pasting history and suggest the optimal pasting method. For example, it might prioritize suggesting pasting methods previously used by the user. It can also suggest methods suitable for specific tasks based on the user's past pasting history. Furthermore, it can analyze the user's pasting history and suggest the most efficient method. This allows it to suggest the optimal pasting method by analyzing past pasting history.

[0045] The paste function can automatically adjust the format of input data based on the user's current tasks and projects. For example, it can automatically apply a format relevant to the user's current project. It can also suggest the optimal data format based on the user's task content. Furthermore, it can automatically adjust the format appropriately according to the user's project progress. This improves work efficiency by adjusting the input data format based on current tasks and projects.

[0046] The attachment section can prioritize suggesting region-specific input data formats by considering the user's geographical location information. For example, if the user is in a specific region, the attachment section will suggest a data format specific to that region. The attachment section can also prioritize displaying region-specific formats based on the user's geographical location information. The attachment section can also suggest region-related data formats by considering the user's location information. In this way, by considering geographical location information, it can suggest region-specific input data formats.

[0047] The pasting unit can analyze the user's social media activity and automatically retrieve relevant input data. For example, the pasting unit can automatically retrieve and paste data shared by the user on social media. The pasting unit can also automatically retrieve relevant data from the user's social media activity. The pasting unit can analyze the user's social media activity history and suggest relevant data. This allows for the automatic retrieval of relevant input data by analyzing social media activity.

[0048] The verification unit can analyze the verification history of past execution plans and propose the optimal verification method. For example, the verification unit can prioritize suggesting verification methods that the user has used in the past. The verification unit can also suggest methods suitable for specific tasks based on the user's past verification history. The verification unit can also analyze the user's verification history and propose the most efficient method. In this way, by analyzing past verification history, it can propose the optimal verification method.

[0049] The verification unit can automatically adjust the level of detail in the execution plan based on the user's current tasks and projects. For example, the verification unit can automatically apply the level of detail relevant to the user's current project. The verification unit can also suggest the optimal level of detail based on the user's task content. The verification unit can also automatically adjust the level of detail to an appropriate level depending on the progress of the user's project. This improves work efficiency by adjusting the level of detail in the execution plan based on the current tasks and projects.

[0050] The verification unit can prioritize the review of region-specific execution plans by considering the user's geographical location information. For example, if the user is in a specific region, the verification unit will review the execution plan tailored to that region. The verification unit can also prioritize the display of region-specific plans based on the user's geographical location information. The verification unit can also review region-related execution plans by considering the user's location information. This allows for the priority review of region-specific execution plans by considering geographical location information.

[0051] The verification unit can analyze a user's social media activity and automatically retrieve relevant action plans. For example, the verification unit can automatically retrieve and verify plans shared by a user on social media. The verification unit can also automatically retrieve relevant plans from a user's social media activity. The verification unit can also analyze a user's social media activity history and suggest relevant plans. In this way, relevant action plans can be automatically retrieved by analyzing social media activity.

[0052] The execution unit can analyze past prompt execution history and propose the optimal execution method. For example, the execution unit prioritizes suggesting prompts previously used by the user. It can also suggest prompts suitable for specific tasks based on the user's past execution history. Furthermore, it can analyze the user's execution history and propose the most efficient prompt. This allows it to suggest the optimal execution method by analyzing past execution history.

[0053] The execution unit can automatically adjust the execution order of prompts based on the user's current tasks and projects. For example, the execution unit will prioritize prompts related to the user's current project. The execution unit can also suggest the optimal execution order based on the user's tasks. The execution unit can also automatically adjust the execution order appropriately according to the progress of the user's projects. This improves work efficiency by adjusting the execution order of prompts based on the current tasks and projects.

[0054] The execution unit can prioritize executing region-specific prompts by considering the user's geographical location. For example, if the user is in a specific region, the execution unit will execute region-specific prompts. The execution unit can also prioritize displaying region-specific prompts based on the user's geographical location. The execution unit can also execute region-related prompts by considering the user's location. This allows for the priority execution of region-specific prompts by considering geographical location.

[0055] The execution unit can analyze a user's social media activity and automatically retrieve relevant prompts. For example, the execution unit can automatically retrieve data shared by a user on social media and execute prompts. The execution unit can also automatically retrieve relevant prompts from a user's social media activity. The execution unit can also analyze a user's social media activity history and suggest relevant prompts. This allows for the automatic retrieval of relevant prompts by analyzing social media activity.

[0056] The output unit can analyze past output display history and propose the optimal display method. For example, the output unit can prioritize suggesting display methods previously used by the user. The output unit can also suggest display methods suitable for specific tasks based on the user's past display history. The output unit can analyze the user's display history and propose the most efficient display method. In this way, by analyzing past display history, it can propose the optimal display method.

[0057] The output unit can automatically adjust the output format based on the user's current tasks and projects. For example, it can automatically apply a format relevant to the user's current project. It can also suggest the optimal output format based on the user's task content. Furthermore, it can automatically adjust the format appropriately according to the user's project progress. This improves work efficiency by adjusting the output format based on current tasks and projects.

[0058] The output section can prioritize displaying region-specific outputs by considering the user's geographical location. For example, if the user is in a specific region, the output section will display outputs specific to that region. The output section can also prioritize displaying region-specific outputs based on the user's geographical location. The output section can also display region-related outputs by considering the user's location. This allows for the priority display of region-specific outputs by considering geographical location.

[0059] The output unit can analyze a user's social media activity and automatically retrieve relevant outputs. For example, the output unit can automatically retrieve data shared by a user on social media and display it as an output. The output unit can also automatically retrieve relevant outputs from a user's social media activity. Furthermore, the output unit can analyze a user's social media activity history and suggest relevant outputs. This allows for the automatic retrieval of relevant outputs by analyzing social media activity.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The selection section can prioritize displaying region-specific agents by considering the user's geographical location. For example, if the user is in a specific region, the selection section will display agents specialized for that region. The selection section can also recommend agents that provide region-specific services based on the user's geographical location. The selection section can also prioritize displaying region-related agents by considering the user's location. This allows for the priority display of region-specific agents by considering geographical location.

[0062] The pasting function can analyze the user's past pasting history and suggest the optimal pasting method. For example, it might prioritize suggesting pasting methods previously used by the user. It can also suggest methods suitable for specific tasks based on the user's past pasting history. Furthermore, it can analyze the user's pasting history and suggest the most efficient method. This allows it to suggest the optimal pasting method by analyzing past pasting history.

[0063] The verification unit can analyze the verification history of past execution plans and propose the optimal verification method. For example, the verification unit can prioritize suggesting verification methods that the user has used in the past. The verification unit can also suggest methods suitable for specific tasks based on the user's past verification history. The verification unit can also analyze the user's verification history and propose the most efficient method. In this way, by analyzing past verification history, it can propose the optimal verification method.

[0064] The execution unit can analyze past prompt execution history and propose the optimal execution method. For example, the execution unit prioritizes suggesting prompts previously used by the user. It can also suggest prompts suitable for specific tasks based on the user's past execution history. Furthermore, it can analyze the user's execution history and propose the most efficient prompt. This allows it to suggest the optimal execution method by analyzing past execution history.

[0065] The output unit can analyze past output display history and propose the optimal display method. For example, the output unit can prioritize suggesting display methods previously used by the user. The output unit can also suggest display methods suitable for specific tasks based on the user's past display history. The output unit can analyze the user's display history and propose the most efficient display method. In this way, by analyzing past display history, it can propose the optimal display method.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The selection unit selects an agent. The selection unit provides an interface for the user to select an agent and can recommend the most suitable agent based on the agent's type and functions. For example, the selection unit can recommend the most suitable agent based on the user's past selection history and current task, and can also use AI to assist in agent selection. Step 2: The paste unit pastes the input data to the agent selected by the selection unit. The paste unit provides an interface for the user to paste the input data and can suggest the optimal pasting method based on the format and content of the input data. For example, the paste unit can suggest the optimal pasting method based on the format of the user's input data and can also use AI to assist in pasting the input data. Step 3: The verification unit verifies the agent's execution plan based on the input data pasted by the pasting unit. The verification unit provides an interface for the user to verify the agent's execution plan and can suggest the optimal verification method based on the content and progress of the execution plan. For example, the verification unit can suggest the optimal verification method based on the content of the user's execution plan and can also use AI to assist in verifying the execution plan. Step 4: The execution unit executes prompts based on the execution plan confirmed by the verification unit. The execution unit provides an interface for the user to execute prompts and can suggest the optimal execution method based on the content and method of execution of the prompts. For example, the execution unit can suggest the optimal execution method based on the content of the user's prompts and can also use AI to assist in executing prompts. Step 5: The output unit outputs the results of the prompts executed by the execution unit. The output unit provides an interface for the user to review the output and can suggest the optimal display method based on the format and content of the output. For example, the output unit can suggest the optimal display method based on the format of the user's output and can also use AI to assist in displaying the output.

[0068] (Example of form 2) An agent platform system according to an embodiment of the present invention is a platform that can utilize and provide agents that perform various tasks. This agent platform system allows users to select an agent, paste input data, review the agent's execution plan, and execute prompts to deploy a specific combination of APIs and execute tasks. Outputs are displayed in communication tools, UIs, chatbots, etc. Furthermore, the creation of RAGs (Retrieval Augmented Generations) is also possible. General engineers can contribute to the creation of new agents by providing APIs, provided they have the necessary I / O. Agents are issued via FAST APIs, etc., making them available for use by others. Revenue sharing is provided to the creator based on usage. This platform supports the efficiency improvements and process automation of small and medium-sized enterprises, compensating for the lack of IT resources and enabling cost-effective business improvements. It also provides development engineers with a source of income as a side job and opportunities to utilize and improve their skills through agent development. For example, in the agent platform system, a user selects an agent and pastes input data. Next, they review the agent's execution plan and execute prompts. The agent deploys a specific combination of APIs and executes tasks. Outputs are displayed in communication tools, UIs, chatbots, etc. Furthermore, the creation of RAGs is also possible. General engineers can contribute to the creation of new agents by providing APIs, provided they have the necessary I / O. Agents are issued via FAST APIs, making them available for use by others. Revenue sharing is provided to the creators based on usage. This allows the agent platform system to support small and medium-sized enterprises in improving operational efficiency and automating processes, compensating for IT resource shortages and enabling cost-effective business improvements. It also provides development engineers with a source of income as a side job and offers them opportunities to utilize and improve their skills through agent development.

[0069] The agent platform system according to the embodiment comprises a selection unit, a pasting unit, a confirmation unit, an execution unit, and an output unit. The selection unit selects an agent. The selection unit provides, for example, an interface for the user to select an agent. The selection unit can also recommend the most suitable agent to the user based on the type and function of the agent. For example, the selection unit recommends the most suitable agent based on the user's past selection history and current task. The selection unit can also use AI to assist in agent selection. For example, the selection unit analyzes the user's selection history and uses AI to recommend the most suitable agent. The pasting unit pastes input data to the agent selected by the selection unit. The pasting unit provides, for example, an interface for the user to paste input data. The pasting unit can also suggest the most suitable pasting method based on the format and content of the input data. For example, the pasting unit suggests the most suitable pasting method based on the format of the user's input data. The pasting unit can also use AI to assist in pasting input data. For example, the pasting unit analyzes the user's input data and uses AI to suggest the most suitable pasting method. The confirmation unit confirms the agent's execution plan based on the input data pasted by the pasting unit. The verification unit provides, for example, an interface for the user to verify the agent's execution plan. The verification unit can also suggest the optimal verification method based on the content and progress of the execution plan. For example, the verification unit suggests the optimal verification method based on the content of the user's execution plan. The verification unit can also use AI to assist in verifying the execution plan. For example, the verification unit analyzes the user's execution plan and suggests the optimal verification method using AI. The execution unit executes prompts based on the execution plan verified by the verification unit. The execution unit provides, for example, an interface for the user to execute prompts. The execution unit can also suggest the optimal execution method based on the content and execution method of the prompts. For example, the execution unit suggests the optimal execution method based on the content of the user's prompts. The execution unit can also use AI to assist in executing prompts.For example, the execution unit analyzes the user's prompts and uses AI to suggest the optimal execution method. The output unit outputs the results of the prompts executed by the execution unit. The output unit provides, for example, an interface for the user to review the output. The output unit can also suggest the optimal display method based on the format and content of the output. For example, the output unit suggests the optimal display method based on the format of the user's output. The output unit can also use AI to assist in displaying the output. For example, the output unit analyzes the user's output and uses AI to suggest the optimal display method. As a result, the agent platform system according to the embodiment can efficiently perform a series of steps from agent selection to output.

[0070] The selection unit selects an agent. For example, the selection unit provides an interface for the user to select an agent. Specifically, the selection unit provides a visual interface that allows the user to easily compare the types and functions of agents. For example, it displays a list of agent features and functions, allowing the user to view detailed information about each agent. The selection unit can also recommend the most suitable agent based on the user's past selection history and current task. For example, it analyzes the user's past agent selection history and recommends the agent best suited to the current task. Furthermore, the selection unit can use AI to assist in agent selection. For example, it uses AI to analyze the user's selection history and current task and recommend the most suitable agent. The AI ​​learns the user's selection patterns and task content, enabling more accurate recommendations. This allows the selection unit to help users select agents efficiently and improve work efficiency.

[0071] The pasting unit pastes the input data to the agent selected by the selection unit. The pasting unit provides, for example, an interface for the user to paste the input data. Specifically, the pasting unit provides an interface that allows the user to easily drag and drop the input data, making data pasting intuitive. The pasting unit can also suggest the optimal pasting method based on the format and content of the input data. For example, the pasting unit can automatically recognize the format of the data entered by the user and suggest the optimal pasting method. Furthermore, the pasting unit can use AI to assist in pasting input data. For example, the pasting unit can analyze the user's input data with AI and suggest the optimal pasting method. The AI ​​can learn the content and format of the data and provide a more efficient pasting method. In this way, the pasting unit can help the user paste input data efficiently and improve work efficiency.

[0072] The verification unit verifies the agent's execution plan based on the input data pasted by the pasting unit. The verification unit provides, for example, an interface for the user to verify the agent's execution plan. Specifically, the verification unit visually displays the agent's execution plan, allowing the user to grasp the plan's content and progress at a glance. The verification unit can also suggest the optimal verification method based on the content and progress of the execution plan. For example, the verification unit can automatically analyze the user's execution plan and suggest the optimal verification method. Furthermore, the verification unit can use AI to assist in verifying the execution plan. For example, the verification unit can analyze the user's execution plan with AI and suggest the optimal verification method. The AI ​​can learn the plan's content and progress and provide a more efficient verification method. In this way, the verification unit can help users efficiently verify the agent's execution plan and improve work efficiency.

[0073] The execution unit executes prompts based on the execution plan confirmed by the verification unit. The execution unit provides, for example, an interface for the user to execute prompts. Specifically, the execution unit provides buttons and command input fields that allow the user to easily execute prompts, making the execution operation intuitive. The execution unit can also suggest the optimal execution method based on the content and method of execution of the prompt. For example, the execution unit can automatically analyze the content of the user's prompt and suggest the optimal execution method. Furthermore, the execution unit can use AI to assist in the execution of prompts. For example, the execution unit can analyze the user's prompt with AI and suggest the optimal execution method. The AI ​​can learn the content and method of execution of prompts and provide more efficient execution methods. In this way, the execution unit can help the user execute prompts efficiently and improve work efficiency.

[0074] The output unit outputs the results of prompts executed by the execution unit. The output unit provides, for example, an interface for the user to review the output. Specifically, the output unit visually displays the execution results so that the user can grasp the results at a glance. The output unit can also suggest the optimal display method based on the format and content of the output. For example, the output unit can automatically analyze the format of the user's output and suggest the optimal display method. Furthermore, the output unit can use AI to assist in displaying the output. For example, the output unit can analyze the user's output with AI and suggest the optimal display method. The AI ​​can learn the content and format of the output and provide a more efficient display method. In this way, the output unit can help the user efficiently review the execution results and improve work efficiency.

[0075] The output unit can display the output through communication tools, UIs, chatbots, etc. For example, the output unit can display the output in a chat application. The output unit can also send the output via email. The output unit can also display the output through a web interface. For example, the output unit can display the output in a web browser. The output unit can also display the output through a mobile interface. For example, the output unit can display the output in a smartphone app. The output unit can also display the output using a chatbot with conversational AI. For example, the output unit can display the output in a script-based chatbot. This improves user convenience by displaying the output in a variety of ways.

[0076] The execution unit can deploy specific combinations of APIs to perform tasks. For example, the execution unit can deploy combinations of REST APIs. It can also deploy combinations of SOAP APIs. It can also deploy combinations of GraphQL APIs. For example, the execution unit can retrieve data using a REST API and send data using a SOAP API. It can also retrieve data using a GraphQL API and send data using a REST API. By deploying combinations of APIs, the execution unit can efficiently perform complex tasks. This means that task execution is made more efficient by deploying specific combinations of APIs.

[0077] The output unit can create RAGs. The output unit can collect data using, for example, information acquisition methods. The output unit can also generate data using generation algorithms. The output unit can also create RAGs by combining information acquisition and generation. For example, the output unit can collect data using web scraping and generate data using natural language generation algorithms. The output unit can also acquire data using APIs and generate data using generation AI. By creating RAGs, the output unit can streamline information acquisition and generation. Thus, creating RAGs streamlines information acquisition and generation.

[0078] The execution unit can contribute to the creation of new agents by utilizing APIs provided by general engineers. For example, the execution unit can use open-source APIs. The execution unit can also use commercial APIs. The execution unit can create new agents using APIs provided by engineers. For example, the execution unit can create new agents using open-source APIs. The execution unit can also create new agents using commercial APIs. By utilizing APIs, the execution unit can streamline the creation of new agents. This facilitates the creation of new agents by utilizing APIs provided by general engineers.

[0079] The output unit can issue agents using FAST APIs, etc., making them available for use by others. For example, the output unit can issue agents using FAST APIs. The output unit can also issue agents using REST APIs. The output unit can also issue agents using GraphQL APIs. For example, the output unit can issue agents using FAST APIs, making them available for use by others. The output unit can also issue agents using REST APIs, making them available for use by others. By issuing agents using APIs, the output unit can expand the range of agent usage. This expands the range of agent usage by making agents available to others.

[0080] The selection unit can estimate the user's emotions and adjust the order in which it presents agent options based on the estimated emotions. For example, if the user is stressed, the selection unit may prioritize displaying simple agents. If the user is relaxed, the selection unit may also prioritize displaying agents with more detailed functions. If the user is in a hurry, the selection unit may also prioritize displaying agents that can complete tasks quickly. This improves user convenience by adjusting agent options 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.

[0081] The selection function can analyze the user's past agent selection history and recommend the most suitable agent based on their preferences. For example, it can prioritize displaying agents that the user has frequently used in the past. The selection function can also recommend agents suitable for specific tasks based on the user's past selection history. The selection function can also analyze the user's selection history and suggest agents suitable for similar tasks. In this way, by analyzing past selection history, it can recommend the most suitable agent to the user.

[0082] The selection section can prioritize displaying agents that are highly relevant to the user's current tasks and projects. For example, it can prioritize displaying agents related to the user's current project. The selection section can also recommend the most suitable agent based on the user's task content. The selection section can also suggest appropriate agents according to the progress of the user's project. This improves the user's work efficiency by prioritizing the display of agents relevant to the current task or project.

[0083] The selection unit can estimate the user's emotions and filter agent options based on those emotions. For example, if the user is stressed, the selection unit will only display simple agents. If the user is relaxed, the selection unit can also display agents with more detailed features. If the user is in a hurry, the selection unit can also display only agents that can complete tasks quickly. This improves user convenience by filtering agent options 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.

[0084] The selection section can prioritize displaying region-specific agents by considering the user's geographical location. For example, if the user is in a specific region, the selection section will display agents specialized for that region. The selection section can also recommend agents that provide region-specific services based on the user's geographical location. The selection section can also prioritize displaying region-related agents by considering the user's location. This allows for the priority display of region-specific agents by considering geographical location.

[0085] The selection unit can analyze a user's social media activity and recommend relevant agents. For example, the selection unit can display agents related to topics the user has shown interest in on social media. The selection unit can also recommend agents that the user might be interested in based on their social media activity. The selection unit can also analyze a user's social media activity history and suggest relevant agents. In this way, by analyzing social media activity, it can recommend agents relevant to the user.

[0086] The pasting unit can estimate the user's emotions and adjust the pasting method of input data based on the estimated emotions. For example, if the user is stressed, the pasting unit can provide a simple pasting method. If the user is relaxed, the pasting unit can also provide detailed pasting options. If the user is in a hurry, the pasting unit can also provide a method to quickly paste data. This improves user convenience by adjusting the pasting method of input data 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0087] The pasting function can analyze the user's past pasting history and suggest the optimal pasting method. For example, it might prioritize suggesting pasting methods previously used by the user. It can also suggest methods suitable for specific tasks based on the user's past pasting history. Furthermore, it can analyze the user's pasting history and suggest the most efficient method. This allows it to suggest the optimal pasting method by analyzing past pasting history.

[0088] The paste function can automatically adjust the format of input data based on the user's current tasks and projects. For example, it can automatically apply a format relevant to the user's current project. It can also suggest the optimal data format based on the user's task content. Furthermore, it can automatically adjust the format appropriately according to the user's project progress. This improves work efficiency by adjusting the input data format based on current tasks and projects.

[0089] The pasting unit can estimate the user's emotions and adjust the timing of pasting input data based on the estimated emotions. For example, if the user is feeling stressed, the pasting unit may delay the pasting time. If the user is relaxed, the pasting unit may also speed up the pasting time. If the user is in a hurry, the pasting unit may also provide a time to quickly paste the data. This improves user convenience by adjusting the timing of pasting input data 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 may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0090] The attachment section can prioritize suggesting region-specific input data formats by considering the user's geographical location information. For example, if the user is in a specific region, the attachment section will suggest a data format specific to that region. The attachment section can also prioritize displaying region-specific formats based on the user's geographical location information. The attachment section can also suggest region-related data formats by considering the user's location information. In this way, by considering geographical location information, it can suggest region-specific input data formats.

[0091] The pasting unit can analyze the user's social media activity and automatically retrieve relevant input data. For example, the pasting unit can automatically retrieve and paste data shared by the user on social media. The pasting unit can also automatically retrieve relevant data from the user's social media activity. The pasting unit can analyze the user's social media activity history and suggest relevant data. This allows for the automatic retrieval of relevant input data by analyzing social media activity.

[0092] The confirmation unit can estimate the user's emotions and adjust the execution plan confirmation method based on the estimated user emotions. For example, if the user is stressed, the confirmation unit can provide a simple confirmation method. If the user is relaxed, the confirmation unit can also provide detailed confirmation options. If the user is in a hurry, the confirmation unit can also provide a quick confirmation method. This improves user convenience by adjusting the execution plan confirmation method 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0093] The verification unit can analyze the verification history of past execution plans and propose the optimal verification method. For example, the verification unit can prioritize suggesting verification methods that the user has used in the past. The verification unit can also suggest methods suitable for specific tasks based on the user's past verification history. The verification unit can also analyze the user's verification history and propose the most efficient method. In this way, by analyzing past verification history, it can propose the optimal verification method.

[0094] The verification unit can automatically adjust the level of detail in the execution plan based on the user's current tasks and projects. For example, the verification unit can automatically apply the level of detail relevant to the user's current project. The verification unit can also suggest the optimal level of detail based on the user's task content. The verification unit can also automatically adjust the level of detail to an appropriate level depending on the progress of the user's project. This improves work efficiency by adjusting the level of detail in the execution plan based on the current tasks and projects.

[0095] The confirmation unit can estimate the user's emotions and adjust the timing of the execution plan confirmation based on the estimated emotions. For example, if the user is feeling stressed, the confirmation unit may delay the confirmation timing. If the user is relaxed, the confirmation unit may also speed up the confirmation timing. If the user is in a hurry, the confirmation unit may also provide a time for quick confirmation. This improves user convenience by adjusting the timing of the execution plan confirmation 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 may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0096] The verification unit can prioritize the review of region-specific execution plans by considering the user's geographical location information. For example, if the user is in a specific region, the verification unit will review the execution plan tailored to that region. The verification unit can also prioritize the display of region-specific plans based on the user's geographical location information. The verification unit can also review region-related execution plans by considering the user's location information. This allows for the priority review of region-specific execution plans by considering geographical location information.

[0097] The verification unit can analyze a user's social media activity and automatically retrieve relevant action plans. For example, the verification unit can automatically retrieve and verify plans shared by a user on social media. The verification unit can also automatically retrieve relevant plans from a user's social media activity. The verification unit can also analyze a user's social media activity history and suggest relevant plans. In this way, relevant action plans can be automatically retrieved by analyzing social media activity.

[0098] The execution unit can estimate the user's emotions and adjust how prompts are executed based on the estimated emotions. For example, if the user is stressed, the execution unit will execute a simple prompt. If the user is relaxed, the execution unit can also execute a more detailed prompt. If the user is in a hurry, the execution unit can provide a prompt that can be executed quickly. This improves user convenience by adjusting how prompts are executed 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.

[0099] The execution unit can analyze past prompt execution history and propose the optimal execution method. For example, the execution unit prioritizes suggesting prompts previously used by the user. It can also suggest prompts suitable for specific tasks based on the user's past execution history. Furthermore, it can analyze the user's execution history and propose the most efficient prompt. This allows it to suggest the optimal execution method by analyzing past execution history.

[0100] The execution unit can automatically adjust the execution order of prompts based on the user's current tasks and projects. For example, the execution unit will prioritize prompts related to the user's current project. The execution unit can also suggest the optimal execution order based on the user's tasks. The execution unit can also automatically adjust the execution order appropriately according to the progress of the user's projects. This improves work efficiency by adjusting the execution order of prompts based on the current tasks and projects.

[0101] The execution unit can estimate the user's emotions and adjust the timing of prompt execution based on the estimated emotions. For example, if the user is stressed, the execution unit may delay the execution timing. If the user is relaxed, the execution unit may also speed up the execution timing. If the user is in a hurry, the execution unit may also provide a timing for quick execution. This improves user convenience by adjusting the timing of prompt execution 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.

[0102] The execution unit can prioritize executing region-specific prompts by considering the user's geographical location. For example, if the user is in a specific region, the execution unit will execute region-specific prompts. The execution unit can also prioritize displaying region-specific prompts based on the user's geographical location. The execution unit can also execute region-related prompts by considering the user's location. This allows for the priority execution of region-specific prompts by considering geographical location.

[0103] The execution unit can analyze a user's social media activity and automatically retrieve relevant prompts. For example, the execution unit can automatically retrieve data shared by a user on social media and execute prompts. The execution unit can also automatically retrieve relevant prompts from a user's social media activity. The execution unit can also analyze a user's social media activity history and suggest relevant prompts. This allows for the automatic retrieval of relevant prompts by analyzing social media activity.

[0104] The output unit can estimate the user's emotions and adjust the display method of the output based on the estimated emotions. For example, if the user is stressed, the output unit can provide a simple display method. If the user is relaxed, the output unit can also provide detailed display options. If the user is in a hurry, the output unit can also provide a display method that allows for quick review. This improves user convenience by adjusting the display method of the output 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0105] The output unit can analyze past output display history and propose the optimal display method. For example, the output unit can prioritize suggesting display methods previously used by the user. The output unit can also suggest display methods suitable for specific tasks based on the user's past display history. The output unit can analyze the user's display history and propose the most efficient display method. In this way, by analyzing past display history, it can propose the optimal display method.

[0106] The output unit can automatically adjust the output format based on the user's current tasks and projects. For example, it can automatically apply a format relevant to the user's current project. It can also suggest the optimal output format based on the user's task content. Furthermore, it can automatically adjust the format appropriately according to the user's project progress. This improves work efficiency by adjusting the output format based on current tasks and projects.

[0107] The output unit can estimate the user's emotions and adjust the timing of the output display based on the estimated emotions. For example, if the user is stressed, the output unit may delay the display timing. If the user is relaxed, the output unit may also speed up the display timing. If the user is in a hurry, the output unit may also provide a timing for quick review. By adjusting the timing of the output display according to the user's emotions, user convenience is improved. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0108] The output section can prioritize displaying region-specific outputs by considering the user's geographical location. For example, if the user is in a specific region, the output section will display outputs specific to that region. The output section can also prioritize displaying region-specific outputs based on the user's geographical location. The output section can also display region-related outputs by considering the user's location. This allows for the priority display of region-specific outputs by considering geographical location.

[0109] The output unit can analyze a user's social media activity and automatically retrieve relevant outputs. For example, the output unit can automatically retrieve data shared by a user on social media and display it as an output. The output unit can also automatically retrieve relevant outputs from a user's social media activity. Furthermore, the output unit can analyze a user's social media activity history and suggest relevant outputs. This allows for the automatic retrieval of relevant outputs by analyzing social media activity.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The selection unit can estimate the user's emotions and adjust the order in which it presents agent options based on the estimated emotions. For example, if the user is stressed, the selection unit may prioritize displaying simple agents. If the user is relaxed, the selection unit may also prioritize displaying agents with more detailed functions. If the user is in a hurry, the selection unit may also prioritize displaying agents that can complete tasks quickly. This improves user convenience by adjusting agent options 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.

[0112] The selection section can prioritize displaying region-specific agents by considering the user's geographical location. For example, if the user is in a specific region, the selection section will display agents specialized for that region. The selection section can also recommend agents that provide region-specific services based on the user's geographical location. The selection section can also prioritize displaying region-related agents by considering the user's location. This allows for the priority display of region-specific agents by considering geographical location.

[0113] The pasting unit can estimate the user's emotions and adjust the pasting method of input data based on the estimated emotions. For example, if the user is stressed, the pasting unit can provide a simple pasting method. If the user is relaxed, the pasting unit can also provide detailed pasting options. If the user is in a hurry, the pasting unit can also provide a method to quickly paste data. This improves user convenience by adjusting the pasting method of input data 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0114] The pasting function can analyze the user's past pasting history and suggest the optimal pasting method. For example, it might prioritize suggesting pasting methods previously used by the user. It can also suggest methods suitable for specific tasks based on the user's past pasting history. Furthermore, it can analyze the user's pasting history and suggest the most efficient method. This allows it to suggest the optimal pasting method by analyzing past pasting history.

[0115] The confirmation unit can estimate the user's emotions and adjust the execution plan confirmation method based on the estimated user emotions. For example, if the user is stressed, the confirmation unit can provide a simple confirmation method. If the user is relaxed, the confirmation unit can also provide detailed confirmation options. If the user is in a hurry, the confirmation unit can also provide a quick confirmation method. This improves user convenience by adjusting the execution plan confirmation method 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0116] The verification unit can analyze the verification history of past execution plans and propose the optimal verification method. For example, the verification unit can prioritize suggesting verification methods that the user has used in the past. The verification unit can also suggest methods suitable for specific tasks based on the user's past verification history. The verification unit can also analyze the user's verification history and propose the most efficient method. In this way, by analyzing past verification history, it can propose the optimal verification method.

[0117] The execution unit can estimate the user's emotions and adjust how prompts are executed based on the estimated emotions. For example, if the user is stressed, the execution unit will execute a simple prompt. If the user is relaxed, the execution unit can also execute a more detailed prompt. If the user is in a hurry, the execution unit can provide a prompt that can be executed quickly. This improves user convenience by adjusting how prompts are executed 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.

[0118] The execution unit can analyze past prompt execution history and propose the optimal execution method. For example, the execution unit prioritizes suggesting prompts previously used by the user. It can also suggest prompts suitable for specific tasks based on the user's past execution history. Furthermore, it can analyze the user's execution history and propose the most efficient prompt. This allows it to suggest the optimal execution method by analyzing past execution history.

[0119] The output unit can estimate the user's emotions and adjust the display method of the output based on the estimated emotions. For example, if the user is stressed, the output unit can provide a simple display method. If the user is relaxed, the output unit can also provide detailed display options. If the user is in a hurry, the output unit can also provide a display method that allows for quick review. This improves user convenience by adjusting the display method of the output 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 is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0120] The output unit can analyze past output display history and propose the optimal display method. For example, the output unit can prioritize suggesting display methods previously used by the user. The output unit can also suggest display methods suitable for specific tasks based on the user's past display history. The output unit can analyze the user's display history and propose the most efficient display method. In this way, by analyzing past display history, it can propose the optimal display method.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The selection unit selects an agent. The selection unit provides an interface for the user to select an agent and can recommend the most suitable agent based on the agent's type and functions. For example, the selection unit can recommend the most suitable agent based on the user's past selection history and current task, and can also use AI to assist in agent selection. Step 2: The paste unit pastes the input data to the agent selected by the selection unit. The paste unit provides an interface for the user to paste the input data and can suggest the optimal pasting method based on the format and content of the input data. For example, the paste unit can suggest the optimal pasting method based on the format of the user's input data and can also use AI to assist in pasting the input data. Step 3: The verification unit verifies the agent's execution plan based on the input data pasted by the pasting unit. The verification unit provides an interface for the user to verify the agent's execution plan and can suggest the optimal verification method based on the content and progress of the execution plan. For example, the verification unit can suggest the optimal verification method based on the content of the user's execution plan and can also use AI to assist in verifying the execution plan. Step 4: The execution unit executes prompts based on the execution plan confirmed by the verification unit. The execution unit provides an interface for the user to execute prompts and can suggest the optimal execution method based on the content and method of execution of the prompts. For example, the execution unit can suggest the optimal execution method based on the content of the user's prompts and can also use AI to assist in executing prompts. Step 5: The output unit outputs the results of the prompts executed by the execution unit. The output unit provides an interface for the user to review the output and can suggest the optimal display method based on the format and content of the output. For example, the output unit can suggest the optimal display method based on the format of the user's output and can also use AI to assist in displaying the output.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the selection unit, pasting unit, confirmation unit, execution unit, and output unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the selection unit is implemented by the control unit 46A of the smart device 14 and provides an interface for the user to select an agent. The pasting unit is implemented by the control unit 46A of the smart device 14 and provides an interface for the user to paste input data. The confirmation unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for confirming the execution plan of the agent. The execution unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for executing prompts. The output unit is implemented by the control unit 46A of the smart device 14 and provides an interface for outputting the results of prompts. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the selection unit, pasting unit, confirmation unit, execution unit, and output unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the selection unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for the user to select an agent. The pasting unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for the user to paste input data. The confirmation unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for confirming the execution plan of the agent. The execution unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for executing prompts. The output unit is implemented by the control unit 46A of the smart glasses 214 and provides an interface for outputting the results of prompts. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the selection unit, pasting unit, confirmation unit, execution unit, and output unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the selection unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface for the user to select an agent. The pasting unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface for the user to paste input data. The confirmation unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for confirming the execution plan of the agent. The execution unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for executing prompts. The output unit is implemented by the control unit 46A of the headset terminal 314 and provides an interface for outputting the results of prompts. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] Each of the multiple elements described above, including the selection unit, pasting unit, confirmation unit, execution unit, and output unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the selection unit is implemented by the control unit 46A of the robot 414 and provides an interface for the user to select an agent. The pasting unit is implemented by the control unit 46A of the robot 414 and provides an interface for the user to paste input data. The confirmation unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for confirming the execution plan of the agent. The execution unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides an interface for executing prompts. The output unit is implemented by the control unit 46A of the robot 414 and provides an interface for outputting the results of prompts. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Note 1) A selection section for selecting an agent, A pasting unit that pastes input data onto the agent selected by the selection unit, A confirmation unit that checks the execution plan of the agent based on the input data pasted by the pasting unit, An execution unit that executes a prompt based on the execution plan confirmed by the verification unit, The system comprises an output unit that outputs the result of a prompt executed by the execution unit. A system characterized by the following features. (Note 2) The output unit is, Display the output using communication tools, UI, chatbots, etc. The system described in Appendix 1, characterized by the features described herein. (Note 3) The execution unit is, Deploy a specific combination of APIs and execute the task. The system described in Appendix 1, characterized by the features described herein. (Note 4) The output unit is, Create a RAG The system described in Appendix 1, characterized by the features described herein. (Note 5) The execution unit is, Contribute to the creation of new agents by utilizing APIs provided by general engineers. The system described in Appendix 1, characterized by the features described herein. (Note 6) The output unit is, Agents are issued via FAST API and other means, making them available for use by others. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned selection unit is It estimates the user's emotions and adjusts the order in which the agent presents options based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned selection unit is By analyzing past agent selection history, the system recommends the most suitable agent based on the user's preferences. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned selection unit is Based on the user's current tasks and projects, the system prioritizes displaying the most relevant agents. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned selection unit is It estimates the user's emotions and filters the agent's options based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned selection unit is The system prioritizes displaying region-specific agents, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned selection unit is Analyze users' social media activity and recommend relevant agents. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned adhesive portion is, It estimates the user's emotions and adjusts how input data is pasted based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned adhesive portion is, We analyze past input data pasting history and suggest the optimal pasting method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned adhesive portion is, The system automatically adjusts the format of input data based on the user's current tasks and projects. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned adhesive portion is, It estimates the user's emotions and adjusts the timing of pasting input data based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned adhesive portion is, The system prioritizes suggesting region-specific input data formats, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned adhesive portion is, Analyze users' social media activity and automatically retrieve relevant input data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned verification unit is The system estimates the user's emotions and adjusts the execution plan review process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned verification unit is We analyze the history of past implementation plan verifications and propose the optimal verification method. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned verification unit is The level of detail in the execution plan is automatically adjusted based on the user's current tasks and projects. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned verification unit is The system estimates the user's emotions and adjusts the timing of execution plan confirmations based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned verification unit is Prioritize reviewing region-specific action plans, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned verification unit is Analyze users' social media activity and automatically retrieve relevant action plans. The system described in Appendix 1, characterized by the features described herein. (Note 25) The execution unit is, It estimates the user's emotions and adjusts how prompts are executed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The execution unit is, It analyzes past prompt execution history and suggests the optimal execution method. The system described in Appendix 1, characterized by the features described herein. (Note 27) The execution unit is, The system automatically adjusts the order in which prompts are executed based on the user's current tasks and projects. The system described in Appendix 1, characterized by the features described herein. (Note 28) The execution unit is, It estimates the user's emotions and adjusts the timing of prompt execution based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The execution unit is, The system prioritizes region-specific prompts based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 30) The execution unit is, Analyze users' social media activity and automatically retrieve relevant prompts. The system described in Appendix 1, characterized by the features described herein. (Note 31) The output unit is, It estimates the user's emotions and adjusts how the output is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The output unit is, We analyze past output display history and propose the optimal display method. The system described in Appendix 1, characterized by the features described herein. (Note 33) The output unit is, The output format is automatically adjusted based on the user's current tasks and project content. The system described in Appendix 1, characterized by the features described herein. (Note 34) The output unit is, It estimates the user's emotions and adjusts the timing of output display based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The output unit is, The system prioritizes displaying region-specific output, taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 36) The output unit is, Analyze users' social media activity and automatically retrieve relevant outputs. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A selection section for selecting an agent, A pasting unit that pastes input data onto the agent selected by the selection unit, A confirmation unit that checks the execution plan of the agent based on the input data pasted by the pasting unit, An execution unit that executes a prompt based on the execution plan confirmed by the verification unit, The system comprises an output unit that outputs the result of a prompt executed by the execution unit. A system characterized by the following features.

2. The output unit is, Display the output using communication tools, UI, chatbots, etc. The system according to feature 1.

3. The execution unit is, Deploy a specific combination of APIs and execute the task. The system according to feature 1.

4. The output unit is, Create a RAG The system according to feature 1.

5. The execution unit is, Contribute to the creation of new agents by utilizing APIs provided by general engineers. The system according to feature 1.

6. The output unit is, Agents are issued via FAST API and other means, making them available for use by others. The system according to feature 1.

7. The aforementioned selection unit is It estimates the user's emotions and adjusts the order in which the agent presents options based on the estimated user emotions. The system according to feature 1.

8. The aforementioned selection unit is By analyzing past agent selection history, the system recommends the most suitable agent based on the user's preferences. The system according to feature 1.

Images