system

Abstract

The system according to this embodiment aims to efficiently select and coordinate AI agents specialized in specific fields and to facilitate smooth communication among these agents. [Solution] The system according to the embodiment comprises a selection unit, an adjustment unit, a communication unit, and a reward calculation unit. The selection unit selects a base model of an AI agent specialized in a particular field. The adjustment unit performs individual adjustments to the base model selected by the selection unit. The communication unit facilitates communication between the AI ​​agents adjusted by the adjustment unit to advance the project. The reward calculation unit calculates a reward based on the results of the project advanced by the communication unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have presented challenges in efficiently selecting and coordinating AI agents specialized in specific fields, as well as facilitating communication between these agents.

[0005] The system according to this embodiment aims to efficiently select and coordinate AI agents specialized in specific fields and to facilitate smooth communication among these agents. [Means for solving the problem]

[0006] The system according to the embodiment includes a selection unit, an adjustment unit, a communication unit, and a reward calculation unit. The selection unit selects a base model for an AI agent specialized in a specialized field. The adjustment unit performs individual adjustments to the base model selected by the selection unit. The communication unit allows the AI ​​agents adjusted by the adjustment unit to communicate with each other and progress the project. The reward calculation unit calculates a reward based on the results of the project progressed by the communication unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently select and adjust AI agents specialized in specialized fields, and can facilitate communication between the agents. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

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

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The AI ​​agent system according to an embodiment of the present invention allows users to select a specialized base model for an AI agent and individually optimize the agent. Using this system, a single CEO can manage a company. First, a user selects a specialized base model for an AI agent. For example, AI agents specialized in areas such as marketing, finance, and human resources are available. Next, the selected base model is individually optimized to meet the needs of the user's company. This allows the AI ​​agent to be optimized for the company's specific tasks and perform them efficiently. Furthermore, AI agents communicate with each other and discuss projects together. For example, a marketing agent and a finance agent can collaborate to develop a new product launch strategy. In this way, AI agents collaborate to solve advanced problems. AI agents also receive training modules to upgrade their capabilities and acquire new skills. For example, learning the latest marketing techniques and financial analysis techniques can enable them to perform more advanced tasks. The system's costs can be set up as a monthly base fee or a performance-based model. For example, introducing a system in which AI agents are paid based on their performance can improve cost-effectiveness. In this way, by utilizing AI agents specializing in specific fields, it becomes possible to streamline corporate management and lead a company to success even with just one CEO. Thus, AI agent systems can streamline corporate management and lead a company to success even with just one CEO.

[0029] The AI ​​agent system according to this embodiment comprises a selection unit, an adjustment unit, a communication unit, and a reward calculation unit. The selection unit selects a base model of an AI agent specialized in a particular field. For example, AI agents specialized in fields such as marketing, finance, and human resources are available. The selection unit allows the user to select the most suitable one from these base models. The adjustment unit performs individual adjustments to the base model selected by the selection unit. For example, the adjustment unit adjusts the parameters of the AI ​​agent to match the user's company needs. The adjustment unit ensures that the AI ​​agent is optimized for the company's specific tasks. The communication unit is the department responsible for facilitating communication between the AI ​​agents adjusted by the adjustment unit and advancing the project. For example, the communication unit enables a marketing agent and a finance agent to collaborate in formulating a market launch strategy for a new product. The communication unit exchanges information using data exchange protocols between agents. For example, protocols such as HTTP and WebSocket can be used. The communication unit manages the decision-making process between agents. For example, a voting system or a consensus algorithm can be used. The reward calculation unit calculates rewards based on the results of the project advanced by the communication unit. For example, the compensation calculation unit calculates compensation based on performance evaluation criteria. The compensation calculation unit sets the calculation method for performance-based compensation. For example, it can perform calculations based on KPIs or project success rates. As a result, the AI ​​agent system according to this embodiment can streamline corporate management and enable even a single CEO to lead the company to success.

[0030] The selection unit can present each agent's areas of expertise and past performance. For example, the selection unit can display each agent's areas of expertise, such as natural language processing or image recognition. The selection unit can also display each agent's past performance, such as project success rates or past deliverables. By presenting each agent's areas of expertise and past performance, it makes it easier for the user to select the optimal base model. Some or all of the processing described above in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the agents' areas of expertise and past performance into an AI model and recommend the optimal base model.

[0031] The communication unit can exchange information using data exchange protocols between agents. For example, the communication unit can exchange information using data exchange protocols such as HTTP or WebSocket. For instance, the communication unit can send and receive data between agents using the HTTP protocol. Furthermore, the communication unit can exchange data in real time using the WebSocket protocol. This enables efficient data exchange by using data exchange protocols between agents. Some or all of the above-described processes in the communication unit may be performed using AI, or not. For example, the communication unit can input data exchange protocols into an AI model and select the optimal protocol.

[0032] The communications department can manage the decision-making process between agents. The communications department can manage the decision-making process between agents using, for example, a voting system or a consensus algorithm. For example, the communications department can make decisions between agents using a voting system. Alternatively, the communications department can make decisions between agents using a consensus algorithm. This allows for smoother project progress by managing the decision-making process between agents. Some or all of the above processes in the communications department may be performed using, for example, AI, or not. For example, the communications department can input the decision-making process into an AI model and select the optimal procedure.

[0033] The adjustment unit provides training modules, enabling the AI ​​agent to acquire new skills. The adjustment unit provides training modules such as online courses and on-the-job training. For example, the adjustment unit provides online courses, enabling the AI ​​agent to acquire new skills. The adjustment unit also provides on-the-job training, allowing the AI ​​agent to acquire new skills through actual work. Thus, by providing training modules, the AI ​​agent acquires new skills and its capabilities improve. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input training modules into an AI model and select the optimal training method.

[0034] The adjustment unit can manage the frequency and method of training. The adjustment unit manages the frequency of training, for example, weekly or monthly. For example, the adjustment unit can set a schedule for weekly training. The adjustment unit can also set a schedule for monthly training. Furthermore, the adjustment unit manages the training method, such as simulation or on-the-job training. For example, the adjustment unit can conduct training using simulation. The adjustment unit can also conduct training using on-the-job training. In this way, by managing the frequency and method of training, efficient skill acquisition is possible. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input the frequency and method of training into an AI model and select the optimal schedule and method.

[0035] The reward calculation unit can set a calculation method for the performance-based reward. The reward calculation unit performs calculations based on, for example, KPIs or the success rate of the project. For example, the reward calculation unit can calculate the reward based on KPIs. The reward calculation unit can also calculate the reward based on the success rate of the project. By setting a calculation method for the performance-based reward, fair reward calculation becomes possible. Some or all of the above-mentioned processing in the reward calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reward calculation unit can input the calculation method for the performance-based reward into an AI model and select the optimal calculation method.

[0036] The reward calculation unit can calculate the reward based on a specific example of the achievement. The reward calculation unit calculates the reward based on a specific example of the achievement, such as the completion of a project or the achievement of a goal. For example, the reward calculation unit can calculate the reward based on the completion of a project. The reward calculation unit can also calculate the reward based on the achievement of a goal. This enables accurate reward calculation by calculating the reward based on a specific example of the achievement. Some or all of the above-described processing in the reward calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reward calculation unit can input a specific example of the achievement into an AI model and calculate an optimal reward.

[0037] The selection unit can analyze past selection history and automatically suggest an appropriate base model based on the user's preferences. For example, the selection unit can suggest a similar model based on a base model previously selected by the user. For example, the selection unit can suggest a model suitable for a specific task based on the user's past selection history. The selection unit can also analyze the user's preference patterns and automatically suggest the most suitable base model. In this way, a base model based on the user's preferences can be suggested by analyzing the past selection history. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the past selection history into an AI model to suggest an optimal base model. Furthermore, the selection unit can develop a base model suggestion algorithm based on the user's preference pattern. For example, the selection unit can analyze the user's preference pattern and build a feedback loop to suggest an optimal base model.

[0038] When selecting a base model, the selection unit can perform filtering based on the user's company's current challenges and goals. The selection unit, for example, filters for the optimal base model based on the user's company's current challenges. For example, the selection unit can prioritize displaying base models highly relevant to the user's company's goals. The selection unit can also select an appropriate base model based on the user's company's business operations. This allows for filtering based on the company's challenges and goals to select the optimal base model. Some or all of the above-described processing in the selection unit can be performed using, for example, AI, or can be performed without AI. For example, the selection unit can input the company's challenges and goals into an AI model and filter for the optimal base model. Furthermore, the selection unit can develop an algorithm for selecting a base model based on the company's challenges and goals. For example, the selection unit can build a feedback loop for selecting the optimal base model based on the company's challenges and goals.

[0039] When selecting a base model, the selection unit can display highly relevant models taking into account the user's geographical location information. The selection unit, for example, displays base models suitable for region-specific business operations based on the user's geographical location information. For example, the selection unit can propose base models suitable for regional market trends taking into account the user's geographical location information. The selection unit can also preferentially display base models that comply with local laws and regulations based on the user's geographical location information. This allows for selection of a base model suitable for region-specific business operations by taking into account the geographical location information. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input geographical location information into an AI model and propose an optimal base model. Furthermore, the selection unit can develop an algorithm for selecting a base model based on the geographical location information. For example, the selection unit can establish a feedback loop for selecting an optimal base model based on the geographical location information.

[0040] When selecting a base model, the selection unit can analyze the user's social media activity and recommend a relevant model. For example, the selection unit can propose a base model suitable for the user's business field of interest based on the user's social media activity. For example, the selection unit can analyze the user's social media posts and propose an optimal base model. The selection unit can also propose a highly relevant base model based on the user's social media activity history. By analyzing social media activity, a base model based on the user's interests can be proposed. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without AI. For example, the selection unit can input social media activity into an AI model and propose an optimal base model. Furthermore, the selection unit can develop an algorithm for selecting a base model based on social media activity. For example, the selection unit can establish a feedback loop for selecting an optimal base model based on social media activity.

[0041] During adjustment, the adjustment unit can select an appropriate adjustment method by referring to the user's company's past business data. The adjustment unit, for example, analyzes the user's company's past business data and selects an optimal adjustment method. For example, the adjustment unit can propose an adjustment method suitable for a specific business from the user's company's past business data. The adjustment unit can also select an efficient adjustment method based on the user's company's past business data. This allows the optimal adjustment method to be selected by referring to the past business data. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input past business data into an AI model and select an optimal adjustment method. Furthermore, the adjustment unit can develop an algorithm for selecting an adjustment method based on past business data. For example, the adjustment unit can build a feedback loop for selecting an optimal adjustment method based on past business data.

[0042] During adjustment, the adjustment unit can optimize the adjustment method based on the user's company's current business situation. The adjustment unit, for example, analyzes the user's company's current business situation and customizes the optimal adjustment method. For example, the adjustment unit can provide an adjustment method suitable for a specific business based on the user's company's current business situation. The adjustment unit can also customize an efficient adjustment method taking into account the user's company's current business situation. This enables efficient optimization by customizing the optimization method based on the current business situation. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without AI. For example, the adjustment unit can input the current business situation into an AI model and select the optimal adjustment method. Furthermore, the adjustment unit can develop an algorithm for selecting the adjustment method based on the current business situation. For example, the adjustment unit can establish a feedback loop for selecting the optimal adjustment method based on the current business situation.

[0043] During adjustment, the adjustment unit can select an appropriate adjustment method by taking into account the user's geographical location information. The adjustment unit, for example, selects an adjustment method suitable for a region-specific business based on the user's geographical location information. For example, the adjustment unit can propose an adjustment method suitable for a region's market trends by taking into account the user's geographical location information. The adjustment unit can also select an adjustment method that complies with local laws and regulations based on the user's geographical location information. In this way, an adjustment method suitable for a region-specific business can be selected by taking into account the geographical location information. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input the geographical location information into an AI model and select an optimal adjustment method. Furthermore, the adjustment unit can develop an algorithm for selecting an adjustment method based on the geographical location information. For example, the adjustment unit can build a feedback loop for selecting an optimal adjustment method based on the geographical location information.

[0044] During adjustment, the adjustment unit can analyze the user's social media activity and suggest adjustment measures. For example, the adjustment unit can suggest adjustment measures appropriate for the user's business field of interest based on the user's social media activity. For example, the adjustment unit can analyze the content of the user's social media posts and suggest optimal adjustment measures. The adjustment unit can also suggest highly relevant adjustment measures based on the user's social media activity history. By analyzing social media activity, adjustment measures based on the user's interests can be suggested. Some or all of the above-described processing in the adjustment unit can be performed using, for example, AI, or can be performed without AI. For example, the adjustment unit can input social media activity into an AI model and suggest optimal adjustment measures. Furthermore, the adjustment unit can develop an algorithm for selecting adjustment measures based on social media activity. For example, the adjustment unit can build a feedback loop for selecting optimal adjustment measures based on social media activity.

[0045] The communication department can select an appropriate communication method by referring to past interactions between agents during communication. For example, the communication department can analyze past interactions between agents and select the optimal communication method. For example, the communication department can propose a communication method suitable for a specific project based on past interactions between agents. The communication department can also select an efficient communication method based on past interactions between agents. In this way, the optimal communication method can be selected by referring to past interactions. Some or all of the above processing in the communication department may be performed using AI, for example, or without AI. For example, the communication department can input past interactions into an AI model and select the optimal communication method. Furthermore, the communication department can develop an algorithm for selecting a communication method based on past interactions. For example, the communication department can build a feedback loop for selecting the optimal communication method based on past interactions.

[0046] The communication unit can optimize the means of communication based on the current project status between agents during communication. For example, the communication unit can analyze the current project status between agents and customize the optimal means of communication. For example, the communication unit can provide a communication means suitable for a specific project based on the current project status between agents. The communication unit can also customize an efficient means of communication taking into account the current project status between agents. This enables efficient communication by customizing the means of communication based on the current project status. Some or all of the above-described processing in the communication unit can be performed using, for example, AI, or without AI. For example, the communication unit can input the current project status into an AI model and select the optimal means of communication. Furthermore, the communication unit can develop an algorithm for selecting the communication means based on the current project status. For example, the communication unit can create a feedback loop for selecting the optimal means of communication based on the current project status.

[0047] The communication unit can select an appropriate communication method during communication by taking into account the agent's geographical location information. For example, the communication unit selects a communication method suitable for a region-specific task based on the agent's geographical location information. For example, the communication unit can propose a communication method suitable for a region's market trends by taking into account the agent's geographical location information. The communication unit can also select a communication method that complies with local laws and regulations based on the agent's geographical location information. In this way, a communication method suitable for a region-specific task can be selected by taking into account the geographical location information. Some or all of the above-described processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can input the geographical location information into an AI model to select an optimal communication method. Furthermore, the communication unit can develop an algorithm for selecting a communication method based on the geographical location information. For example, the communication unit can build a feedback loop for selecting an optimal communication method based on the geographical location information.

[0048] The communication unit can recommend a means of communication by analyzing the agent's social media activity during communication. For example, the communication unit can suggest a communication means suitable for the agent's field of interest based on the agent's social media activity. For example, the communication unit can analyze the content of the agent's social media posts and suggest the optimal communication means. The communication unit can also suggest highly relevant communication means based on the agent's social media activity history. In this way, by analyzing social media activity, it is possible to suggest a communication means based on the agent's interests. Some or all of the above-described processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can input social media activity into an AI model to suggest the optimal communication means. Furthermore, the communication unit can develop an algorithm for selecting a communication means based on social media activity. For example, the communication unit can create a feedback loop for selecting the optimal communication means based on social media activity.

[0049] The reward calculation unit can select an appropriate reward calculation method by referring to past performance data when calculating rewards. The reward calculation unit, for example, analyzes the user's company's past performance data and selects the optimal reward calculation method. For example, the reward calculation unit can propose a reward calculation method suitable for a specific task based on the user's company's past performance data. The reward calculation unit can also select an efficient reward calculation method based on the user's company's past performance data. This allows the optimal reward calculation method to be selected by referring to the past performance data. Some or all of the above-described processing in the reward calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the reward calculation unit can input past performance data into an AI model and select the optimal reward calculation method. Furthermore, the reward calculation unit can develop an algorithm for selecting a reward calculation method based on past performance data. For example, the reward calculation unit can build a feedback loop for selecting the optimal reward calculation method based on past performance data.

[0050] The compensation calculation unit can optimize the compensation calculation means based on the current project status when calculating the compensation. The compensation calculation unit, for example, analyzes the current project status and customizes the optimal compensation calculation means. For example, the compensation calculation unit can provide a compensation calculation means suitable for a specific task based on the current project status. The compensation calculation unit can also customize an efficient compensation calculation means taking the current project status into consideration. Customizing the compensation calculation means based on the current project status thereby enables efficient compensation calculation. Some or all of the above-described processing in the compensation calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the compensation calculation unit can input the current project status into an AI model and select the optimal compensation calculation means. Furthermore, the compensation calculation unit can develop an algorithm for selecting the compensation calculation means based on the current project status. For example, the compensation calculation unit can establish a feedback loop for selecting the optimal compensation calculation means based on the current project status.

[0051] The compensation calculation unit can select an appropriate compensation calculation method when calculating compensation, taking geographical location information into consideration. For example, the compensation calculation unit can select a compensation calculation method suitable for region-specific tasks based on the user's geographical location information. For example, the compensation calculation unit can propose a compensation calculation method suitable for regional market trends, taking the user's geographical location information into consideration. The compensation calculation unit can also select a compensation calculation method that complies with regional laws and regulations based on the user's geographical location information. In this way, by considering geographical location information, a compensation calculation method suitable for region-specific tasks can be selected. Some or all of the above processing in the compensation calculation unit may be performed using AI, for example, or without using AI. For example, the compensation calculation unit can input geographical location information into an AI model and select the optimal compensation calculation method. Furthermore, the compensation calculation unit can develop an algorithm for selecting a compensation calculation method based on geographical location information. For example, the compensation calculation unit can build a feedback loop for selecting the optimal compensation calculation method based on geographical location information.

[0052] The reward calculation unit can analyze social media activity and recommend a reward calculation method during the reward calculation process. For example, the reward calculation unit can propose a reward calculation method suitable for the user's areas of interest based on their social media activity. For example, the reward calculation unit can analyze the content of the user's social media posts and propose the optimal reward calculation method. The reward calculation unit can also propose a highly relevant reward calculation method based on the user's social media activity history. In this way, by analyzing social media activity, it is possible to propose a reward calculation method based on the user's interests. Some or all of the above processing in the reward calculation unit may be performed using AI, for example, or without AI. For example, the reward calculation unit can input social media activity into an AI model and propose the optimal reward calculation method. Furthermore, the reward calculation unit can develop an algorithm for selecting a reward calculation method based on social media activity. For example, the reward calculation unit can build a feedback loop for selecting the optimal reward calculation method based on social media activity.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] The selection unit can recommend the optimal base model based on the user's company's growth stage. For example, it can recommend a model that enables rapid time to market to a startup company, a model that enables efficient resource management to a mid-sized company, and a model that can manage complex business processes to a large company. By providing the optimal base model according to the company's growth stage, it is possible to provide support that meets the company's needs. Some or all of the above processing in the selection unit may be performed using AI, for example, or not using AI. For example, the selection unit can input the company's growth stage into an AI model and recommend the optimal base model.

[0055] The adjustment unit can optimize the adjustment method based on the industry characteristics of the user's company. For example, it can provide an adjustment method that improves production efficiency for the manufacturing industry, and an adjustment method that improves customer satisfaction for the service industry. It can also provide an adjustment method that promotes technological innovation for the IT industry. This allows the business efficiency of a company to be improved by providing the optimal adjustment method according to the industry characteristics. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input industry characteristics into an AI model and select the optimal adjustment method.

[0056] The communication unit can use natural language processing technology to make dialogue between agents more natural. For example, in dialogue between agents, it can understand the context and generate appropriate responses. It can also analyze the dialogue history between agents and refer to the content of past dialogues to enable more effective communication. Furthermore, it can properly understand and use technical terms and industry-specific language in dialogue between agents. This makes communication between agents smoother and improves the efficiency of project progress. Some or all of the above-mentioned processing in the communication unit may be performed using, for example, AI, or may be performed without using AI.

[0057] The remuneration calculation unit can optimize the remuneration calculation method based on the financial situation of the user's company. For example, it provides a calculation method that sets a higher performance-based remuneration when the financial situation is good, and emphasizes fixed remuneration when the financial situation is tight. It can also adjust the timing of remuneration payments based on the company's cash flow. Furthermore, it can set remuneration calculation standards based on the company's financial goals. This enables flexible remuneration calculation according to the company's financial situation and supports the company's management. Some or all of the above-mentioned processing in the remuneration calculation unit may be performed, for example, using AI, or may be performed without using AI.

[0058] The adjustment unit can optimize the adjustment method based on the user's company's future goals. For example, if a company is entering a new market, it can provide an adjustment method appropriate for that market. If a company is developing a new product, it can provide an adjustment method appropriate for that product development. Furthermore, if a company is aiming to reduce costs, it can also provide an adjustment method for efficient resource management. This makes it possible to support the growth of a company by providing an optimal adjustment method according to the company's future goals. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input the company's future goals into an AI model and select the optimal adjustment method.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The selection unit selects a base model for an AI agent specialized in a specific domain. For example, AI agents specialized in domains such as marketing, finance, and human resources are available, and the user can select the most appropriate one from these base models. Step 2: The tuning unit performs individual tuning on the base model selected by the selection unit. For example, the tuning unit adjusts the parameters of the AI ​​agent to suit the needs of the user's company, so that the AI ​​agent is optimized for the company's specific business. Step 3: The communication section allows the AI ​​agents coordinated by the coordination section to communicate with each other and progress the project. For example, it allows the marketing agent and the finance agent to cooperate to plan a new product launch strategy, and exchanges information using a data exchange protocol between agents (such as HTTP or WebSocket). It also manages the decision-making procedures between agents, and can use a voting system or consensus algorithm. Step 4: The compensation calculation unit calculates compensation based on the results of the project conducted by the communications unit. For example, compensation can be calculated based on performance evaluation criteria, KPI-based calculations, or project success rate calculations.

[0061] (Example 2) The AI ​​agent system according to an embodiment of the present invention allows users to select a specialized base model for an AI agent and individually optimize the agent. Using this system, a single CEO can manage a company. First, a user selects a specialized base model for an AI agent. For example, AI agents specialized in areas such as marketing, finance, and human resources are available. Next, the selected base model is individually optimized to meet the needs of the user's company. This allows the AI ​​agent to be optimized for the company's specific tasks and perform them efficiently. Furthermore, AI agents communicate with each other and discuss projects together. For example, a marketing agent and a finance agent can collaborate to develop a new product launch strategy. In this way, AI agents collaborate to solve advanced problems. AI agents also receive training modules to upgrade their capabilities and acquire new skills. For example, learning the latest marketing techniques and financial analysis techniques can enable them to perform more advanced tasks. The system's costs can be set up as a monthly base fee or a performance-based model. For example, introducing a system in which AI agents are paid based on their performance can improve cost-effectiveness. In this way, by utilizing AI agents specializing in specific fields, it becomes possible to streamline corporate management and lead a company to success even with just one CEO. Thus, AI agent systems can streamline corporate management and lead a company to success even with just one CEO.

[0062] The AI ​​agent system according to this embodiment comprises a selection unit, an adjustment unit, a communication unit, and a reward calculation unit. The selection unit selects a base model of an AI agent specialized in a particular field. For example, AI agents specialized in fields such as marketing, finance, and human resources are available. The selection unit allows the user to select the most suitable one from these base models. The adjustment unit performs individual adjustments to the base model selected by the selection unit. For example, the adjustment unit adjusts the parameters of the AI ​​agent to match the user's company needs. The adjustment unit ensures that the AI ​​agent is optimized for the company's specific tasks. The communication unit is the department responsible for facilitating communication between the AI ​​agents adjusted by the adjustment unit and advancing the project. For example, the communication unit enables a marketing agent and a finance agent to collaborate in formulating a market launch strategy for a new product. The communication unit exchanges information using data exchange protocols between agents. For example, protocols such as HTTP and WebSocket can be used. The communication unit manages the decision-making process between agents. For example, a voting system or a consensus algorithm can be used. The reward calculation unit calculates rewards based on the results of the project advanced by the communication unit. For example, the compensation calculation unit calculates compensation based on performance evaluation criteria. The compensation calculation unit sets the calculation method for performance-based compensation. For example, it can perform calculations based on KPIs or project success rates. As a result, the AI ​​agent system according to this embodiment can streamline corporate management and enable even a single CEO to lead the company to success.

[0063] The selection unit can present each agent's areas of expertise and past performance. For example, the selection unit can display each agent's areas of expertise, such as natural language processing or image recognition. The selection unit can also display each agent's past performance, such as project success rates or past deliverables. By presenting each agent's areas of expertise and past performance, it makes it easier for the user to select the optimal base model. Some or all of the processing described above in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the agents' areas of expertise and past performance into an AI model and recommend the optimal base model.

[0064] The communication unit can exchange information using data exchange protocols between agents. For example, the communication unit can exchange information using data exchange protocols such as HTTP or WebSocket. For instance, the communication unit can send and receive data between agents using the HTTP protocol. Furthermore, the communication unit can exchange data in real time using the WebSocket protocol. This enables efficient data exchange by using data exchange protocols between agents. Some or all of the above-described processes in the communication unit may be performed using AI, or not. For example, the communication unit can input data exchange protocols into an AI model and select the optimal protocol.

[0065] The communications department can manage the decision-making process between agents. The communications department can manage the decision-making process between agents using, for example, a voting system or a consensus algorithm. For example, the communications department can make decisions between agents using a voting system. Alternatively, the communications department can make decisions between agents using a consensus algorithm. This allows for smoother project progress by managing the decision-making process between agents. Some or all of the above processes in the communications department may be performed using, for example, AI, or not. For example, the communications department can input the decision-making process into an AI model and select the optimal procedure.

[0066] The adjustment unit provides training modules, enabling the AI ​​agent to acquire new skills. The adjustment unit provides training modules such as online courses and on-the-job training. For example, the adjustment unit provides online courses, enabling the AI ​​agent to acquire new skills. The adjustment unit also provides on-the-job training, allowing the AI ​​agent to acquire new skills through actual work. Thus, by providing training modules, the AI ​​agent acquires new skills and its capabilities improve. Some or all of the above processes in the adjustment unit may be performed using AI, for example, or without AI. For example, the adjustment unit can input training modules into an AI model and select the optimal training method.

[0067] The adjustment unit can manage the frequency and method of training. The adjustment unit manages the frequency of training, for example, weekly or monthly. For example, the adjustment unit can set a schedule for weekly training. The adjustment unit can also set a schedule for monthly training. Furthermore, the adjustment unit manages the training method, such as simulation or on-the-job training. For example, the adjustment unit can conduct training using simulation. The adjustment unit can also conduct training using on-the-job training. In this way, by managing the frequency and method of training, efficient skill acquisition is possible. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input the frequency and method of training into an AI model and select the optimal schedule and method.

[0068] The reward calculation unit can set a calculation method for the performance-based reward. The reward calculation unit performs calculations based on, for example, KPIs or the success rate of the project. For example, the reward calculation unit can calculate the reward based on KPIs. The reward calculation unit can also calculate the reward based on the success rate of the project. By setting a calculation method for the performance-based reward, fair reward calculation becomes possible. Some or all of the above-mentioned processing in the reward calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reward calculation unit can input the calculation method for the performance-based reward into an AI model and select the optimal calculation method.

[0069] The reward calculation unit can calculate the reward based on a specific example of the achievement. The reward calculation unit calculates the reward based on a specific example of the achievement, such as the completion of a project or the achievement of a goal. For example, the reward calculation unit can calculate the reward based on the completion of a project. The reward calculation unit can also calculate the reward based on the achievement of a goal. This enables accurate reward calculation by calculating the reward based on a specific example of the achievement. Some or all of the above-described processing in the reward calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reward calculation unit can input a specific example of the achievement into an AI model and calculate an optimal reward.

[0070] The selection unit can estimate the user's emotions and recommend an appropriate base model based on the estimated user emotions. For example, if the user is feeling stressed, the selection unit can recommend a simple and intuitive base model. For example, if the user is relaxed, the selection unit can recommend a base model that allows for detailed customization. Furthermore, if the user is in a hurry, the selection unit can recommend a base model that can be quickly set up. This improves user satisfaction by recommending the optimal base model based on the user's emotions. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without AI. For example, the selection unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions. Furthermore, the selection unit can develop an algorithm for recommending the optimal base model based on the estimated user emotions. For example, the selection unit can recommend a base model based on an emotion score, thereby improving user satisfaction.

[0071] The selection unit can analyze past selection history and automatically suggest an appropriate base model based on the user's preferences. For example, the selection unit can suggest a similar model based on a base model previously selected by the user. For example, the selection unit can suggest a model suitable for a specific task based on the user's past selection history. The selection unit can also analyze the user's preference patterns and automatically suggest the most suitable base model. In this way, a base model based on the user's preferences can be suggested by analyzing the past selection history. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the past selection history into an AI model to suggest an optimal base model. Furthermore, the selection unit can develop a base model suggestion algorithm based on the user's preference pattern. For example, the selection unit can analyze the user's preference pattern and build a feedback loop to suggest an optimal base model.

[0072] When selecting a base model, the selection unit can perform filtering based on the user's company's current challenges and goals. The selection unit, for example, filters for the optimal base model based on the user's company's current challenges. For example, the selection unit can prioritize displaying base models highly relevant to the user's company's goals. The selection unit can also select an appropriate base model based on the user's company's business operations. This allows for filtering based on the company's challenges and goals to select the optimal base model. Some or all of the above-described processing in the selection unit can be performed using, for example, AI, or can be performed without AI. For example, the selection unit can input the company's challenges and goals into an AI model and filter for the optimal base model. Furthermore, the selection unit can develop an algorithm for selecting a base model based on the company's challenges and goals. For example, the selection unit can build a feedback loop for selecting the optimal base model based on the company's challenges and goals.

[0073] The selection unit can estimate the user's emotions and optimize the display order of options based on the estimated user emotions. For example, if the user is feeling stressed, the selection unit can display simple and intuitive options at the top. For example, if the user is relaxed, the selection unit can display options that allow for detailed customization at the top. Furthermore, if the user is in a hurry, the selection unit can display options that can be quickly set at the top. This makes it easier for the user to make a selection by adjusting the display order of options based on the user's emotions. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions. Furthermore, the selection unit can develop an algorithm for optimizing the display order of options based on the estimated user emotions. For example, the selection unit can optimize the display order of options based on emotion scores, making it easier for the user to make a selection.

[0074] When selecting a base model, the selection unit can display highly relevant models taking into account the user's geographical location information. The selection unit, for example, displays base models suitable for region-specific business operations based on the user's geographical location information. For example, the selection unit can propose base models suitable for regional market trends taking into account the user's geographical location information. The selection unit can also preferentially display base models that comply with local laws and regulations based on the user's geographical location information. This allows for selection of a base model suitable for region-specific business operations by taking into account the geographical location information. Some or all of the above-described processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input geographical location information into an AI model and propose an optimal base model. Furthermore, the selection unit can develop an algorithm for selecting a base model based on the geographical location information. For example, the selection unit can establish a feedback loop for selecting an optimal base model based on the geographical location information.

[0075] When selecting a base model, the selection unit can analyze the user's social media activity and recommend a relevant model. For example, the selection unit can propose a base model suitable for the user's business field of interest based on the user's social media activity. For example, the selection unit can analyze the user's social media posts and propose an optimal base model. The selection unit can also propose a highly relevant base model based on the user's social media activity history. By analyzing social media activity, a base model based on the user's interests can be proposed. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without AI. For example, the selection unit can input social media activity into an AI model and propose an optimal base model. Furthermore, the selection unit can develop an algorithm for selecting a base model based on social media activity. For example, the selection unit can establish a feedback loop for selecting an optimal base model based on social media activity.

[0076] The adjustment unit can estimate the user's emotions and optimize the adjustment method based on the estimated user emotions. For example, if the user is feeling stressed, the adjustment unit can provide a simple and intuitive optimization method. For example, if the user is relaxed, the adjustment unit can provide a detailed customizable optimization method. Furthermore, if the user is in a hurry, the adjustment unit can provide a quickly set optimization method. This improves user satisfaction by adjusting the optimization method based on the user's emotions. Some or all of the above-described processing in the adjustment unit can be performed using, for example, AI, or can be performed without using AI. For example, the adjustment unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions. Furthermore, the adjustment unit can develop an algorithm for adjusting the optimization method based on the estimated user emotions. For example, the adjustment unit can adjust the optimization method based on the emotion score to improve user satisfaction.

[0077] During adjustment, the adjustment unit can select an appropriate adjustment method by referring to the user's company's past business data. The adjustment unit, for example, analyzes the user's company's past business data and selects an optimal adjustment method. For example, the adjustment unit can propose an adjustment method suitable for a specific business from the user's company's past business data. The adjustment unit can also select an efficient adjustment method based on the user's company's past business data. This allows the optimal adjustment method to be selected by referring to the past business data. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input past business data into an AI model and select an optimal adjustment method. Furthermore, the adjustment unit can develop an algorithm for selecting an adjustment method based on past business data. For example, the adjustment unit can build a feedback loop for selecting an optimal adjustment method based on past business data.

[0078] During adjustment, the adjustment unit can optimize the adjustment method based on the user's company's current business situation. The adjustment unit, for example, analyzes the user's company's current business situation and customizes the optimal adjustment method. For example, the adjustment unit can provide an adjustment method suitable for a specific business based on the user's company's current business situation. The adjustment unit can also customize an efficient adjustment method taking into account the user's company's current business situation. This enables efficient optimization by customizing the optimization method based on the current business situation. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without AI. For example, the adjustment unit can input the current business situation into an AI model and select the optimal adjustment method. Furthermore, the adjustment unit can develop an algorithm for selecting the adjustment method based on the current business situation. For example, the adjustment unit can establish a feedback loop for selecting the optimal adjustment method based on the current business situation.

[0079] The adjustment unit can estimate the user's emotions and optimize the adjustment priorities based on the estimated user emotions. For example, if the user is feeling stressed, the adjustment unit can prioritize optimizing important tasks. For example, if the user is relaxed, the adjustment unit can prioritize optimizing detailed tasks. Furthermore, if the user is in a hurry, the adjustment unit can prioritize optimizing tasks that can be completed quickly. This improves user satisfaction by determining the optimization priorities based on the user's emotions. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without AI. For example, the adjustment unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions. Furthermore, the adjustment unit can develop an algorithm for determining the optimization priorities based on the estimated user emotions. For example, the adjustment unit determines the optimization priorities based on the emotion scores, thereby improving user satisfaction.

[0080] During adjustment, the adjustment unit can select an appropriate adjustment method by taking into account the user's geographical location information. The adjustment unit, for example, selects an adjustment method suitable for a region-specific business based on the user's geographical location information. For example, the adjustment unit can propose an adjustment method suitable for a region's market trends by taking into account the user's geographical location information. The adjustment unit can also select an adjustment method that complies with local laws and regulations based on the user's geographical location information. In this way, an adjustment method suitable for a region-specific business can be selected by taking into account the geographical location information. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input the geographical location information into an AI model and select an optimal adjustment method. Furthermore, the adjustment unit can develop an algorithm for selecting an adjustment method based on the geographical location information. For example, the adjustment unit can build a feedback loop for selecting an optimal adjustment method based on the geographical location information.

[0081] During adjustment, the adjustment unit can analyze the user's social media activity and suggest adjustment measures. For example, the adjustment unit can suggest adjustment measures appropriate for the user's business field of interest based on the user's social media activity. For example, the adjustment unit can analyze the content of the user's social media posts and suggest optimal adjustment measures. The adjustment unit can also suggest highly relevant adjustment measures based on the user's social media activity history. By analyzing social media activity, adjustment measures based on the user's interests can be suggested. Some or all of the above-described processing in the adjustment unit can be performed using, for example, AI, or can be performed without AI. For example, the adjustment unit can input social media activity into an AI model and suggest optimal adjustment measures. Furthermore, the adjustment unit can develop an algorithm for selecting adjustment measures based on social media activity. For example, the adjustment unit can build a feedback loop for selecting optimal adjustment measures based on social media activity.

[0082] The communication unit can estimate the user's emotions and optimize the communication method between agents based on the estimated emotions. For example, if the user is stressed, the communication unit can provide a simple and intuitive communication method. For example, if the user is relaxed, the communication unit can provide a communication method that includes detailed information. Furthermore, if the user is in a hurry, the communication unit can provide a communication method that allows for quick information sharing. By adjusting the communication method based on the user's emotions, user satisfaction is improved. Some or all of the above processing in the communication unit may be performed using AI, for example, or not using AI. For example, the communication unit can use technologies such as facial recognition and voice analysis to estimate the user's emotions. In addition, the communication unit can develop algorithms to optimize the communication method based on the estimated user emotions. For example, the communication unit can optimize the communication method based on the emotion score to improve user satisfaction.

[0083] The communication department can select an appropriate communication method by referring to past interactions between agents during communication. For example, the communication department can analyze past interactions between agents and select the optimal communication method. For example, the communication department can propose a communication method suitable for a specific project based on past interactions between agents. The communication department can also select an efficient communication method based on past interactions between agents. In this way, the optimal communication method can be selected by referring to past interactions. Some or all of the above processing in the communication department may be performed using AI, for example, or without AI. For example, the communication department can input past interactions into an AI model and select the optimal communication method. Furthermore, the communication department can develop an algorithm for selecting a communication method based on past interactions. For example, the communication department can build a feedback loop for selecting the optimal communication method based on past interactions.

[0084] The communication unit can optimize the means of communication based on the current project status between agents during communication. For example, the communication unit can analyze the current project status between agents and customize the optimal means of communication. For example, the communication unit can provide a communication means suitable for a specific project based on the current project status between agents. The communication unit can also customize an efficient means of communication taking into account the current project status between agents. This enables efficient communication by customizing the means of communication based on the current project status. Some or all of the above-described processing in the communication unit can be performed using, for example, AI, or without AI. For example, the communication unit can input the current project status into an AI model and select the optimal means of communication. Furthermore, the communication unit can develop an algorithm for selecting the communication means based on the current project status. For example, the communication unit can create a feedback loop for selecting the optimal means of communication based on the current project status.

[0085] The communication unit can estimate a user's emotions and optimize the priority of communication between agents based on the estimated user emotions. For example, if a user is feeling stressed, the communication unit can prioritize sharing important information. For example, if a user is relaxed, the communication unit can prioritize sharing detailed information. Furthermore, if a user is in a hurry, the communication unit can prioritize providing information that can be shared quickly. This improves user satisfaction by determining communication priorities based on the user's emotions. Some or all of the above-described processing in the communication unit may be performed using, for example, AI, or may be performed without AI. For example, the communication unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions. Furthermore, the communication unit can develop an algorithm for optimizing communication priorities based on the estimated user emotions. For example, the communication unit optimizes communication priorities based on emotion scores, thereby improving user satisfaction.

[0086] The communication unit can select an appropriate communication method during communication by taking into account the agent's geographical location information. For example, the communication unit selects a communication method suitable for a region-specific task based on the agent's geographical location information. For example, the communication unit can propose a communication method suitable for a region's market trends by taking into account the agent's geographical location information. The communication unit can also select a communication method that complies with local laws and regulations based on the agent's geographical location information. In this way, a communication method suitable for a region-specific task can be selected by taking into account the geographical location information. Some or all of the above-described processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can input the geographical location information into an AI model to select an optimal communication method. Furthermore, the communication unit can develop an algorithm for selecting a communication method based on the geographical location information. For example, the communication unit can build a feedback loop for selecting an optimal communication method based on the geographical location information.

[0087] The communication unit can recommend a means of communication by analyzing the agent's social media activity during communication. For example, the communication unit can suggest a communication means suitable for the agent's field of interest based on the agent's social media activity. For example, the communication unit can analyze the content of the agent's social media posts and suggest the optimal communication means. The communication unit can also suggest highly relevant communication means based on the agent's social media activity history. In this way, by analyzing social media activity, it is possible to suggest a communication means based on the agent's interests. Some or all of the above-described processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can input social media activity into an AI model to suggest the optimal communication means. Furthermore, the communication unit can develop an algorithm for selecting a communication means based on social media activity. For example, the communication unit can create a feedback loop for selecting the optimal communication means based on social media activity.

[0088] The reward calculation unit can estimate the user's emotions and optimize the reward calculation method based on the estimated user emotions. For example, if the user is feeling stressed, the reward calculation unit can provide a simple and intuitive reward calculation method. For example, if the user is relaxed, the reward calculation unit can provide a detailed customizable reward calculation method. Furthermore, if the user is in a hurry, the reward calculation unit can provide a reward calculation method that can be calculated quickly. This improves user satisfaction by adjusting the reward calculation method based on the user's emotions. Some or all of the above-described processing in the reward calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the reward calculation unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions. Furthermore, the reward calculation unit can develop an algorithm for optimizing the reward calculation method based on the estimated user emotions. For example, the reward calculation unit optimizes the reward calculation method based on the emotion score, thereby improving user satisfaction.

[0089] The reward calculation unit can select an appropriate reward calculation method by referring to past performance data when calculating rewards. The reward calculation unit, for example, analyzes the user's company's past performance data and selects the optimal reward calculation method. For example, the reward calculation unit can propose a reward calculation method suitable for a specific task based on the user's company's past performance data. The reward calculation unit can also select an efficient reward calculation method based on the user's company's past performance data. This allows the optimal reward calculation method to be selected by referring to the past performance data. Some or all of the above-described processing in the reward calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the reward calculation unit can input past performance data into an AI model and select the optimal reward calculation method. Furthermore, the reward calculation unit can develop an algorithm for selecting a reward calculation method based on past performance data. For example, the reward calculation unit can build a feedback loop for selecting the optimal reward calculation method based on past performance data.

[0090] The compensation calculation unit can optimize the compensation calculation means based on the current project status when calculating the compensation. The compensation calculation unit, for example, analyzes the current project status and customizes the optimal compensation calculation means. For example, the compensation calculation unit can provide a compensation calculation means suitable for a specific task based on the current project status. The compensation calculation unit can also customize an efficient compensation calculation means taking the current project status into consideration. Customizing the compensation calculation means based on the current project status thereby enables efficient compensation calculation. Some or all of the above-described processing in the compensation calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the compensation calculation unit can input the current project status into an AI model and select the optimal compensation calculation means. Furthermore, the compensation calculation unit can develop an algorithm for selecting the compensation calculation means based on the current project status. For example, the compensation calculation unit can establish a feedback loop for selecting the optimal compensation calculation means based on the current project status.

[0091] The reward calculation unit can estimate the user's emotions and optimize the priority of reward calculation based on the estimated user emotions. For example, when the user is feeling stressed, the reward calculation unit can prioritize important reward calculations. For example, when the user is relaxed, the reward calculation unit can prioritize detailed reward calculations. Furthermore, when the user is in a hurry, the reward calculation unit can prioritize reward calculations that can be calculated quickly. This improves user satisfaction by determining the priority of reward calculations based on the user's emotions. Some or all of the above-described processing in the reward calculation unit may be performed using, for example, AI, or may be performed without AI. For example, the reward calculation unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions. Furthermore, the reward calculation unit can develop an algorithm for optimizing the priority of reward calculations based on the estimated user emotions. For example, the reward calculation unit optimizes the priority of reward calculations based on emotion scores, thereby improving user satisfaction.

[0092] The reward calculation unit can select an appropriate reward calculation method by taking geographical location information into consideration when calculating rewards. The reward calculation unit, for example, selects a reward calculation method suitable for a region-specific task based on the user's geographical location information. For example, the reward calculation unit can propose a reward calculation method suitable for a region's market trends by taking the user's geographical location information into consideration. The reward calculation unit can also select a reward calculation method that complies with local laws and regulations based on the user's geographical location information. This allows for the selection of a reward calculation method suitable for a region-specific task by taking the geographical location information into consideration. Some or all of the above-described processing in the reward calculation unit can be performed using, for example, AI, or without AI. For example, the reward calculation unit can input geographical location information into an AI model and select an optimal reward calculation method. Furthermore, the reward calculation unit can develop an algorithm for selecting a reward calculation method based on the geographical location information. For example, the reward calculation unit can establish a feedback loop for selecting an optimal reward calculation method based on the geographical location information.

[0093] The reward calculation unit can analyze social media activity and recommend a reward calculation method when calculating the reward. For example, the reward calculation unit can suggest a reward calculation method suitable for the user's field of interest based on the user's social media activity. For example, the reward calculation unit can analyze the user's social media posts and suggest an optimal reward calculation method. The reward calculation unit can also suggest a highly relevant reward calculation method based on the user's social media activity history. By analyzing social media activity, reward calculation methods based on the user's interests can be suggested. Some or all of the above-described processing in the reward calculation unit can be performed using, for example, AI, or without AI. For example, the reward calculation unit can input social media activity into an AI model and suggest an optimal reward calculation method. Furthermore, the reward calculation unit can develop an algorithm for selecting a reward calculation method based on the social media activity. For example, the reward calculation unit can create a feedback loop for selecting an optimal reward calculation method based on the social media activity. === Hard Collateral 1-1 === Each of the multiple elements, including the selection unit, adjustment unit, communication unit, and reward calculation unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the selection unit is realized by the control unit 46A of the smart device 14 and allows a user to select a base model of an AI agent specialized in a specialized field. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs individual adjustments to the selected base model. The communication unit is realized, for example, by the control unit 46A of the smart device 14 and allows the adjusted AI agents to communicate with each other and progress the project. The reward calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a reward based on the results of the project. === Hard Collateral 1-2 === Each of the multiple elements, including the selection unit, adjustment unit, communication unit, and reward calculation unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the selection unit is realized by the control unit 46A of the smart glasses 214 and allows a user to select a base model of an AI agent specialized in a specialized field. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs individual adjustments to the selected base model. The communication unit is realized, for example, by the control unit 46A of the smart glasses 214 and allows the adjusted AI agents to communicate with each other and progress the project. The reward calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a reward based on the results of the project. === Hard Collateral 1-3 === Each of the multiple elements, including the selection unit, adjustment unit, communication unit, and reward calculation unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the selection unit is realized by the control unit 46A of the headset-type terminal 314 and allows a user to select a base model of an AI agent specialized in a specialized field. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs individual adjustments to the selected base model. The communication unit is realized, for example, by the control unit 46A of the headset-type terminal 314 and allows the adjusted AI agents to communicate with each other and progress the project. The reward calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a reward based on the results of the project. === Hard Collateral 1-4 === Each of the multiple elements, including the selection unit, adjustment unit, communication unit, and reward calculation unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the selection unit is realized by the control unit 46A of the robot 414 and allows a user to select a base model of an AI agent specialized in a specialized field. The adjustment unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and performs individual adjustments to the selected base model. The communication unit is realized, for example, by the control unit 46A of the robot 414 and allows the adjusted AI agents to communicate with each other and progress the project. The reward calculation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and calculates a reward based on the results of the project.

[0094] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0095] The selection unit can recommend the optimal base model based on the growth stage of the user's company. For example, it can recommend a model that enables rapid market entry to a startup company, and a model that enables efficient resource management to a medium-sized company. It can also recommend a model that can manage complex business processes to a large company. This makes it possible to provide support that meets the needs of the company by providing the optimal base model according to the company's growth stage. Some or all of the above-mentioned processing by the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can input the company's growth stage into an AI model and recommend the optimal base model.

[0096] The adjustment unit can optimize the adjustment method based on the industry characteristics of the user's company. For example, it can provide an adjustment method that improves production efficiency for the manufacturing industry, and an adjustment method that improves customer satisfaction for the service industry. It can also provide an adjustment method that promotes technological innovation for the IT industry. This allows the business efficiency of a company to be improved by providing the optimal adjustment method according to the industry characteristics. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input industry characteristics into an AI model and select the optimal adjustment method.

[0097] The communication unit can use natural language processing technology to make dialogue between agents more natural. For example, in dialogue between agents, it can understand the context and generate appropriate responses. It can also analyze the dialogue history between agents and refer to the content of past dialogues to enable more effective communication. Furthermore, it can properly understand and use technical terms and industry-specific language in dialogue between agents. This makes communication between agents smoother and improves the efficiency of project progress. Some or all of the above-mentioned processing in the communication unit may be performed using, for example, AI, or may be performed without using AI.

[0098] The remuneration calculation unit can optimize the remuneration calculation method based on the financial situation of the user's company. For example, it provides a calculation method that sets a higher performance-based remuneration when the financial situation is good, and emphasizes fixed remuneration when the financial situation is tight. It can also adjust the timing of remuneration payments based on the company's cash flow. Furthermore, it can set remuneration calculation standards based on the company's financial goals. This enables flexible remuneration calculation according to the company's financial situation and supports the company's management. Some or all of the above-mentioned processing in the remuneration calculation unit may be performed, for example, using AI, or may be performed without using AI.

[0099] The selection unit can estimate the user's emotions and dynamically change the interface design based on the estimated user emotions. For example, if the user is feeling stressed, the design can be changed to a simple and intuitive one. If the user is relaxed, the design can be changed to one that displays detailed information. Also, if the user is in a hurry, the design can be changed to one that allows for quick operation. This provides an optimal interface according to the user's emotions, improving user operability and increasing satisfaction. Some or all of the above-mentioned processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions.

[0100] The adjustment unit can estimate the user's emotions and adjust the difficulty of the training module based on the estimated user's emotions. For example, if the user is feeling stressed, an easy training module can be provided. If the user is relaxed, a more difficult training module can be provided. Also, if the user is in a hurry, a training module that can be completed in a short time can be provided. In this way, by providing the optimal training module according to the user's emotions, the user's learning efficiency improves and satisfaction increases. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions.

[0101] The communication unit can estimate the user's emotions and adjust the frequency of communication between agents based on the estimated user emotions. For example, if the user is feeling stressed, the communication frequency can be reduced. If the user is relaxed, the communication frequency can be increased. Also, if the user is in a hurry, the communication frequency can be increased to quickly share information. This provides an optimal communication frequency according to the user's emotions, thereby reducing user stress and improving satisfaction. Some or all of the above-mentioned processing in the communication unit may be performed using, for example, AI, or may be performed without using AI. For example, the communication unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions.

[0102] The reward calculation unit can estimate the user's emotions and adjust the timing of reward payment based on the estimated user emotions. For example, if the user is stressed, the reward can be paid quickly. If the user is relaxed, the normal payment schedule can be followed. Also, if the user is in a hurry, the reward can be paid immediately. This improves user satisfaction and motivation by providing the optimal reward payment timing according to the user's emotions. Some or all of the above-mentioned processing in the reward calculation unit may be performed using, for example, AI, or may be performed without using AI. For example, the reward calculation unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions.

[0103] The selection unit can estimate the user's emotions and optimize the display order of options based on the estimated user emotions. For example, if the user is feeling stressed, simple and intuitive options can be displayed at the top. If the user is relaxed, options that can be customized in detail can be displayed at the top. Also, if the user is in a hurry, options that can be quickly set can be displayed at the top. This makes it easier for the user to make a selection by adjusting the display order of options based on the user's emotions. Some or all of the above-described processing in the selection unit may be performed using, for example, AI, or may be performed without using AI. For example, the selection unit can use technologies such as facial expression recognition and voice analysis to estimate the user's emotions.

[0104] The adjustment unit can optimize the adjustment method based on the user's company's future goals. For example, if a company is entering a new market, it can provide an adjustment method appropriate for that market. If a company is developing a new product, it can provide an adjustment method appropriate for that product development. Furthermore, if a company is aiming to reduce costs, it can also provide an adjustment method for efficient resource management. This makes it possible to support the growth of a company by providing an optimal adjustment method according to the company's future goals. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input the company's future goals into an AI model and select the optimal adjustment method.

[0105] The processing flow of the second embodiment will be briefly explained below.

[0106] Step 1: The selection unit selects a base model for an AI agent specialized in a specific domain. For example, AI agents specialized in domains such as marketing, finance, and human resources are available, and the user can select the most appropriate one from these base models. Step 2: The tuning unit performs individual tuning on the base model selected by the selection unit. For example, the tuning unit adjusts the parameters of the AI ​​agent to suit the needs of the user's company, so that the AI ​​agent is optimized for the company's specific business. Step 3: The communication section allows the AI ​​agents coordinated by the coordination section to communicate with each other and progress the project. For example, it allows the marketing agent and the finance agent to cooperate to plan a new product launch strategy, and exchanges information using a data exchange protocol between agents (such as HTTP or WebSocket). It also manages the decision-making procedures between agents, and can use a voting system or consensus algorithm. Step 4: The Remuneration Calculation Department calculates the remuneration based on the results of the project conducted by the Communication Department. For example, the remuneration can be calculated based on the evaluation criteria of the results, KPIs, or the success rate of the project.

[0107] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0108] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0109] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0110] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0111] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0112] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0113] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0122] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0125] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0127] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0128] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0129] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0130] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0131] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to 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 imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0134] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0141] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0145] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0146] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0147] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to 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 imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0149] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0150] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0151] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0152] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0154] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0155] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0156] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0157] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0158] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0159] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0160] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0161] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0162] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0163] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0164] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0165] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0166] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0167] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0168] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0169] 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.

[0170] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0171] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0172] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0173] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0174] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0175] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0176] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0177] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0178] [Explanation of symbols]

[0179] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A selection unit that selects a base model of an AI agent specialized in a specialized field; an adjustment unit that performs individual adjustment on the base model selected by the selection unit; a communication unit for allowing the AI ​​agents adjusted by the adjustment unit to communicate with each other and progress the project; a reward calculation unit that calculates a reward based on the results of the project conducted by the communication unit; Equipped with A system characterized by:

2. The selection unit Show each agent their areas of expertise and past performance 2. The system of claim 1.

3. The communication unit Exchange information using a data exchange protocol between agents 2. The system of claim 1.

4. The communication unit Manage decision-making procedures among agents 2. The system of claim 1.

5. The adjustment unit Providing training modules to help AI agents learn new skills 2. The system of claim 1.

6. The adjustment unit Manage training frequency and methods 2. The system of claim 1.

7. The remuneration calculation unit Set the calculation method for performance-based compensation 2. The system of claim 1.

8. The remuneration calculation unit Calculate rewards based on specific examples of success 2. The system of claim 1.

Images