system

Abstract

The system according to this embodiment aims to provide an intuitive GUI-based development environment and automate the development of AI agents, the generation of collaborative operation protocols, and the implementation of security functions. [Solution] The system according to the embodiment comprises a development unit, a selection unit, a cooperation unit, and a security unit. The development unit provides a GUI-based development environment. The selection unit automatically selects and adjusts an appropriate AI model based on the device characteristics from the AI ​​agents designed by the development unit. The cooperation unit automatically generates a cooperative operation protocol between AI agents based on the AI ​​model selected by the selection unit. The security unit automatically implements encryption functions based on security requirements based on the protocol generated by the cooperation unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the development of AI agents, the generation of cooperative operation protocols, and the implementation of security functions are manually performed, resulting in low efficiency and the need for expertise.

[0005] The system according to the embodiment aims to provide an intuitive GUI-based development environment and automate the development of AI agents, the generation of cooperative operation protocols, and the implementation of security functions.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a development unit, a selection unit, a cooperation unit, and a security unit. The development unit provides a GUI-based development environment. The selection unit automatically selects and adjusts an appropriate AI model based on the device characteristics from the AI ​​agents designed by the development unit. The cooperation unit automatically generates a cooperative operation protocol between AI agents based on the AI ​​model selected by the selection unit. The security unit automatically implements encryption functions based on security requirements based on the protocol generated by the cooperation unit. [Effects of the Invention]

[0007] The system according to this embodiment provides an intuitive GUI-based development environment and can automate the development of AI agents, the generation of collaborative operation protocols, and the implementation of security functions. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An integrated platform according to an embodiment of the present invention is an integrated platform that realizes the development of next-generation communication devices with an "AI agent-first" approach. This integrated platform allows device manufacturers to easily implement AI agents optimized for the characteristics of their devices using an intuitive GUI-based development environment. Furthermore, cooperative operation protocols and security functions between AI agents are automatically implemented. This platform consists of the following steps. First, the device manufacturer designs the AI ​​agent using a GUI-based development environment. Development is possible using no-code or low-code methods, and AI agents can be implemented without specialized programming knowledge. For example, functions of the AI ​​agent can be added or settings changed using drag-and-drop operations. Next, the platform automatically selects and optimizes the optimal AI model based on the characteristics of the device. For example, it selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption, and applies lightweighting techniques as needed. This maximizes the performance of the device. Furthermore, the platform automatically generates cooperative operation protocols between AI agents. This facilitates cooperation between multiple devices and enables smooth communication between devices. For example, a system can be built in which multiple IoT devices cooperate to collect and analyze data. Furthermore, the platform automatically implements encryption functions according to security requirements. This ensures secure communication between devices, preventing data leaks and unauthorized access. For example, security is enhanced by encrypting communication data between devices and adding authentication functions. This platform allows device manufacturers to significantly reduce the time and cost required to develop AI agents. It also simplifies the implementation of AI agents, solving the problem of AI engineer shortages and promoting innovation. Moreover, it is expected to accelerate the development of next-generation communication devices and contribute to the realization of a truly Intelligent Connected World.This allows the integrated platform to significantly reduce the time and cost that device manufacturers spend developing AI agents.

[0029] The integrated platform according to this embodiment comprises a development unit, a selection unit, a cooperation unit, and a security unit. The development unit provides a GUI-based development environment. The development unit provides an environment that users can operate intuitively, for example, by providing drag-and-drop functionality. The development unit also provides a real-time preview function, allowing users to immediately verify the operation of the AI ​​agent they have designed. Furthermore, the development unit supports no-code or low-code development, enabling the implementation of AI agents without specialized programming knowledge. For example, the development unit provides templates and wizards to allow users to easily design AI agents. The selection unit automatically selects and optimizes the optimal AI model based on the characteristics of the device. For example, the selection unit selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption. The selection unit also applies lightweighting techniques as needed to maximize the performance of the device. For example, the selection unit uses model compression and quantization techniques to lighten the AI ​​model. The cooperation unit automatically generates cooperative operation protocols between AI agents based on the AI ​​model selected by the selection unit. The cooperation unit generates protocols that facilitate cooperation between multiple devices, for example. For example, the cooperation unit defines communication procedures and data exchange formats to ensure smooth communication between devices. The security unit automatically implements encryption functions according to security requirements based on the protocols generated by the cooperation unit. For example, the security unit encrypts communication data between devices and adds authentication functions. For example, the security unit applies encryption algorithms and key management methods to prevent data leakage and unauthorized access. As a result, the integrated platform according to the embodiment easily implements AI agents optimized for the characteristics of devices, and cooperative operation protocols and security functions are also automatically implemented.

[0030] The development department provides a GUI-based development environment. For example, it offers drag-and-drop functionality, providing an intuitive user experience. Specifically, users can easily place and connect necessary components on the screen through a visual interface. This enables the design of complex AI agents even without specialized programming knowledge. Furthermore, the development department provides a real-time preview function, allowing users to instantly verify the operation of their designed AI agents. For example, when a user changes settings on the GUI, the changes are immediately reflected, allowing real-time verification of the AI ​​agent's operation. In addition, the development department supports no-code or low-code development, enabling the implementation of AI agents without specialized programming knowledge. For instance, the development department provides templates and wizards to facilitate AI agent design. Templates offer common AI agent design patterns, requiring only customization by the user. Wizards guide the user step-by-step, assisting in the design of AI agents by guiding them through the necessary settings in sequence. This allows the development department to provide an environment where users can efficiently design and implement AI agents, significantly simplifying the development process.

[0031] The selection unit automatically selects and optimizes the optimal AI model based on the device's characteristics. For example, the selection unit selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption. Specifically, the selection unit evaluates the device's hardware resources and proposes the most suitable AI model. For example, for devices with limited memory capacity, it selects a model with low memory usage, and for devices with high computing performance, it selects a more complex and high-precision model. The selection unit also applies lightweighting techniques as needed to maximize the device's performance. For example, the selection unit uses model compression and quantization techniques to lighten the AI ​​model. Model compression is a technique that reduces unnecessary parameters to decrease the model size, and quantization is a technique that reduces computational complexity by converting model parameters into low-precision numerical values. This allows the selection unit to efficiently utilize the device's resources and provide the optimal AI model. Furthermore, the selection unit continuously monitors the AI ​​model's performance and can re-select or re-optimize the model as needed. This ensures that the selection unit always provides the optimal AI model and maximizes the device's performance.

[0032] The collaboration unit automatically generates collaborative operation protocols between AI agents based on the AI ​​model selected by the selection unit. For example, the collaboration unit generates protocols that facilitate cooperation between multiple devices. Specifically, it defines communication procedures and data exchange formats to ensure smooth communication between devices. For instance, it adjusts the method and timing of data transmission and reception between devices to maintain data integrity. Furthermore, the collaboration unit generates protocols for AI agents to cooperate in performing tasks. For example, when multiple devices cooperate to monitor an environment, it generates protocols for sharing data collected by each device and making integrated decisions. This allows the collaboration unit to enable multiple devices to cooperate efficiently and perform more advanced tasks. In addition, the collaboration unit can also generate protocols to respond to dynamic environmental changes. For example, in the event of device failure or communication failure, the collaboration unit generates protocols for other devices to take over, improving the overall reliability of the system. This enables the collaboration unit to achieve flexible and reliable collaborative operation, improving the overall system performance.

[0033] The Security Department automatically implements encryption functions according to security requirements based on protocols generated by the Coordination Department. For example, the Security Department encrypts communication data between devices and adds authentication functions. Specifically, the Security Department applies encryption algorithms and key management methods to prevent data leakage and unauthorized access. For instance, the Security Department uses encryption algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman) to encrypt communication data. Furthermore, the Security Department uses a Public Key Infrastructure (PKI) to authenticate devices and ensure reliable communication. In addition, the Security Department manages device security policies and can automatically update security settings as needed. For example, if a new threat is discovered, the Security Department quickly takes countermeasures and updates the device security settings. This ensures that the Security Department always applies the latest security measures and maintains the security of the entire system. Furthermore, the Security Department can collect and analyze security logs to detect abnormal activity. For example, the Security Department analyzes communication logs to detect signs of unauthorized access early and take appropriate measures. This allows the security department to strengthen the overall system security and achieve highly reliable operation.

[0034] The no-code section provides a no-code / low-code development environment. For example, the no-code section defines the scope of tasks that do not require programming, allowing users to easily design AI agents. The no-code section provides templates and wizards, creating an intuitive user environment. For instance, the no-code section features drag-and-drop functionality, allowing users to add features and modify settings for AI agents. It also includes a real-time preview function, enabling users to instantly see how their designed AI agents work. This allows AI agents to be implemented without specialized programming knowledge. Some or all of the above-described processes in the no-code section may be performed using AI, or not. For example, the no-code section can input user input into the AI, which can then suggest appropriate templates and wizards.

[0035] The lightweighting unit automatically applies lightweighting technologies for edge AI. For example, the lightweighting unit uses model compression technology to lighten the AI ​​model. For example, the lightweighting unit uses quantization technology to lighten the AI ​​model. For example, the lightweighting unit uses distillation technology to lighten the AI ​​model. This allows the device performance to be maximized. Some or all of the above processing in the lightweighting unit may be performed using AI, for example, or without AI. For example, the lightweighting unit can input device characteristics into the AI, and the AI ​​can suggest an appropriate lightweighting technology.

[0036] The selection unit selects an AI model that is suitable according to the constraints of the device's memory capacity, computing performance, and power consumption. For example, the selection unit selects an AI model based on the upper limit of the device's memory capacity. For example, the selection unit selects an AI model based on an indicator of the device's computing performance. For example, the selection unit selects an AI model based on a method for measuring the device's power consumption. This makes it possible to select the AI ​​model that is optimal for the characteristics of the device. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input the characteristics of the device into the AI, and the AI ​​can propose an appropriate AI model.

[0037] The coordinating unit generates protocols that facilitate cooperation between multiple devices. The coordinating unit defines communication procedures, for example, to ensure smooth communication between devices. The coordinating unit defines data exchange formats, for example, to facilitate data exchange between devices. The coordinating unit defines synchronization methods, for example, to synchronize the operations of devices. This facilitates cooperation between multiple devices. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input the communication procedures between devices into the AI, which can then generate an appropriate protocol.

[0038] The security unit encrypts communication data between devices and adds authentication functionality. For example, the security unit applies an encryption algorithm to encrypt the communication data between devices. For example, the security unit applies a key management method to securely manage the communication data between devices. For example, the security unit applies an authentication method to authenticate the communication between devices. This ensures that communication between devices is secure and prevents data leakage and unauthorized access. Some or all of the above processes in the security unit may be performed using AI, for example, or without AI. For example, the security unit can input the communication data between devices into the AI, which can then suggest an appropriate encryption algorithm and authentication method.

[0039] The development department analyzes the user's past development history and proposes the most suitable development tools and templates. For example, the development department automatically suggests the most suitable tools based on the development tools the user has used in the past. For example, the development department prioritizes displaying frequently used templates from the user's past project history. For example, the development department analyzes the user's development history and proposes the most suitable toolset based on specific development patterns. This allows the development department to propose the most suitable tools and templates based on the user's past development history. Some or all of the above processes in the development department may be performed using AI, or not. For example, the development department can input the user's development history data into AI, which can then suggest appropriate tools and templates.

[0040] The development department adjusts the difficulty level of the development environment according to the user's skill level. For example, the development department displays only basic functions and simplifies operation for beginner users. For example, the development department provides detailed setting options and a customizable environment for intermediate users. For example, the development department displays all functions and provides a highly flexible development environment for advanced users. This allows the development environment to be tailored to the user's skill level. Some or all of the above processes in the development department may be performed using AI, for example, or not. For example, the development department can input user skill level data into AI, which can then suggest an appropriate development environment.

[0041] The development department provides optimal development resources by considering the user's geographical location. For example, the development department provides information on nearby development communities and events based on the user's location. For example, the development department suggests optimal cloud resources based on the user's geographical location. For example, the development department provides local development resources and support according to the user's location. This allows the development department to provide optimal development resources based on the user's geographical location. Some or all of the above processes in the development department may be performed using AI, or not. For example, the development department can input the user's geographical location into AI, which can then suggest appropriate development resources.

[0042] The development department analyzes users' social media activity and suggests relevant development communities and forums. For example, the development department suggests relevant communities based on the developers and technologies that users follow. For example, the development department analyzes users' social media activity and suggests forums related to technologies they are interested in. For example, the development department suggests relevant development events and workshops based on users' social media posts. This allows the development department to suggest relevant development communities and forums based on users' social media activity. Some or all of the above processes in the development department may be performed using AI, or not. For example, the development department can input user social media data into AI, which can then suggest appropriate communities and forums.

[0043] The selection unit selects the optimal AI model by referring to the device's past performance data. For example, the selection unit selects the optimal AI model based on the device's past memory usage. For example, the selection unit selects the optimal AI model by referring to the device's past computing performance data. For example, the selection unit selects the optimal AI model based on the device's past power consumption data. This allows the selection of the optimal AI model based on the device's past performance data. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input the device's performance data into the AI, which can then propose an appropriate AI model.

[0044] The selection unit selects an AI model based on the device's usage environment. For example, if the device is used outdoors, the selection unit selects a low-power consumption AI model. If the device is used in a high-temperature environment, the selection unit selects a heat-resistant AI model. If the device is used while in transit, the selection unit selects an AI model capable of real-time processing. This allows for the selection of the optimal AI model based on the device's usage environment. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input device usage environment data into the AI, which can then propose an appropriate AI model.

[0045] The selection unit selects an AI model considering the geographical distribution of the devices. For example, if the device is used in an urban area, the selection unit selects an AI model with a high communication speed. For example, if the device is used in a rural area, the selection unit selects an AI model with low power consumption. For example, if the device is used internationally, the selection unit selects a multilingual AI model. This allows for the selection of the optimal AI model based on the geographical distribution of the devices. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input geographical distribution data of the devices into an AI, which can then propose an appropriate AI model.

[0046] The selection unit improves the accuracy of AI model selection by referring to relevant device literature. For example, the selection unit refers to literature on the device's technical specifications and selects the optimal AI model. For example, the selection unit analyzes literature on device use cases and selects an appropriate AI model. For example, the selection unit selects the optimal AI model based on literature on device performance evaluation. This improves the accuracy of AI model selection based on relevant device literature. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input device-related literature data into an AI, which can then propose an appropriate AI model.

[0047] The coordinating unit analyzes the communication history between devices to generate an optimal coordinating operation protocol. For example, the coordinating unit generates an optimal protocol based on the past communication history between devices. For example, the coordinating unit analyzes the communication frequency between devices to generate an efficient protocol. For example, the coordinating unit refers to the communication error history between devices to generate a protocol that avoids errors. This makes it possible to generate an optimal coordinating operation protocol based on the communication history between devices. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input the communication history data between devices into the AI, which can then propose an appropriate protocol.

[0048] The coordinating unit customizes the coordinating operation protocol based on the device usage scenario. For example, if the device is used in a home, the coordinating unit generates a protocol optimized for the home network. For example, if the device is used in a business, the coordinating unit generates a protocol optimized for the business network. For example, if the device is used in a public place, the coordinating unit generates a protocol optimized for the public network. This allows for the provision of the optimal coordinating operation protocol based on the device usage scenario. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input device usage scenario data into the AI, which can then propose an appropriate protocol.

[0049] The coordinating unit generates a coordinating operation protocol considering the geographical distribution of the devices. For example, if the devices are used in urban areas, the coordinating unit generates a protocol with a high communication speed. If the devices are used in rural areas, the coordinating unit generates a protocol with low power consumption. If the devices are used internationally, the coordinating unit generates a multilingual protocol. This allows for the provision of an optimal coordinating operation protocol based on the geographical distribution of the devices. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input geographical distribution data of the devices into the AI, which can then propose an appropriate protocol.

[0050] The coordinating unit improves the accuracy of the coordinating operation protocol by referring to relevant device documentation. For example, the coordinating unit generates an optimal protocol by referring to documentation on the device's technical specifications. For example, the coordinating unit generates an appropriate protocol by analyzing documentation on device use cases. For example, the coordinating unit generates an optimal protocol based on documentation on device performance evaluation. This improves the accuracy of the coordinating operation protocol based on relevant device documentation. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input device documentation data into AI, and the AI ​​can propose an appropriate protocol.

[0051] The security department analyzes past security incidents of a device and implements optimal security features. For example, the security department selects the optimal encryption algorithm based on past security incidents of the device. For example, the security department analyzes past security incidents of the device and implements security features to reinforce vulnerabilities. For example, the security department refers to past security incidents of the device and implements security measures to prevent the recurrence of incidents. This allows the security department to provide optimal security features based on past security incidents of the device. Some or all of the above processes in the security department may be performed using AI, for example, or not using AI. For example, the security department can input past security incident data into AI, and the AI ​​can propose appropriate security features.

[0052] The security department customizes security features based on the device's usage environment. For example, if the device is used in a public place, the security department implements strong authentication features. If the device is used at home, for example, the security department provides simple authentication features. If the device is used within a company, for example, the security department implements security features based on the company's security policy. This allows for the provision of optimal security features based on the device's usage environment. Some or all of the above processing in the security department may be performed using AI, for example, or without AI. For example, the security department can input device usage environment data into the AI, which can then suggest appropriate security features.

[0053] The security unit implements security features considering the geographical distribution of devices. For example, if a device is used in an urban area, the security unit implements security features that enhance communication encryption. For example, if a device is used in a rural area, the security unit implements security features that reduce power consumption. For example, if a device is used internationally, the security unit implements multilingual security features. This allows for the provision of optimal security features based on the geographical distribution of devices. Some or all of the above processing in the security unit may be performed using AI, for example, or without AI. For example, the security unit can input geographical distribution data of devices into an AI, which can then suggest appropriate security features.

[0054] The security department improves the accuracy of security functions by referring to relevant device documentation. For example, the security department implements optimal security functions by referring to documentation on the device's technical specifications. For example, the security department implements appropriate security functions by analyzing documentation on device use cases. For example, the security department implements optimal security functions based on documentation on device performance evaluation. This improves the accuracy of security functions based on relevant device documentation. Some or all of the above processes in the security department may be performed using AI, for example, or without AI. For example, the security department can input device documentation data into AI, which can then propose appropriate security functions.

[0055] The no-code section analyzes the user's past development history and suggests the most suitable no-code tools and templates. For example, the no-code section automatically suggests the best tools based on the no-code tools the user has used in the past. For example, the no-code section prioritizes displaying frequently used templates based on the user's past project history. For example, the no-code section analyzes the user's development history and suggests the best toolset based on specific development patterns. This allows the no-code section to suggest the most suitable no-code tools and templates based on the user's past development history. Some or all of the above processes in the no-code section may be performed using AI, or not. For example, the no-code section can input the user's development history data into AI, which can then suggest appropriate tools and templates.

[0056] The no-code component provides optimal no-code resources considering the user's geographical location. For example, the no-code component provides information on nearby development communities and events based on the user's location. For example, the no-code component suggests optimal cloud resources based on the user's geographical location. For example, the no-code component provides local development resources and support according to the user's location. This enables the provision of optimal no-code resources based on the user's geographical location. Some or all of the above processing in the no-code component may be performed using AI, for example, or without AI. For example, the no-code component can input the user's geographical location information into AI, which can then suggest appropriate no-code resources.

[0057] The lightweighting unit applies the optimal lightweighting technique by referring to the device's past performance data. For example, the lightweighting unit applies the optimal lightweighting technique based on the device's past memory usage. For example, the lightweighting unit applies the optimal lightweighting technique by referring to the device's past computing performance data. For example, the lightweighting unit applies the optimal lightweighting technique based on the device's past power consumption data. This makes it possible to provide the optimal lightweighting technique based on the device's past performance data. Some or all of the above processing in the lightweighting unit may be performed using AI, for example, or without AI. For example, the lightweighting unit can input the device's performance data into AI, and the AI ​​can propose an appropriate lightweighting technique.

[0058] The lightweighting unit applies lightweighting techniques considering the geographical distribution of the devices. For example, if the device is used in an urban area, the lightweighting unit applies lightweighting techniques that enable high communication speeds. For example, if the device is used in a rural area, the lightweighting unit applies lightweighting techniques that enable low power consumption. For example, if the device is used internationally, the lightweighting unit applies lightweighting techniques that support multiple languages. This allows the lightweighting unit to provide the optimal lightweighting technique based on the geographical distribution of the devices. Some or all of the above processing in the lightweighting unit may be performed using AI, for example, or without AI. For example, the lightweighting unit can input geographical distribution data of the devices into an AI, which can then propose an appropriate lightweighting technique.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The no-code component can analyze a user's past development history and suggest the most suitable development tools and templates. For example, it can automatically suggest the best tools based on the development tools the user has used in the past. It can also prioritize displaying frequently used templates based on the user's past project history. Furthermore, it can analyze the user's development history and suggest the optimal toolset based on specific development patterns. This allows for the suggestion of the most suitable tools and templates based on the user's past development history.

[0061] The lightweighting unit can also apply optimal lightweighting techniques by referring to the device's past performance data. For example, it can apply optimal lightweighting techniques based on the device's past memory usage. It can also apply optimal lightweighting techniques by referring to the device's past computing performance data. Furthermore, it can apply optimal lightweighting techniques based on the device's past power consumption data. This allows for the provision of optimal lightweighting techniques based on the device's past performance data.

[0062] The selection unit can also select an AI model based on the device's operating environment. For example, if the device is used outdoors, a low-power consumption AI model can be selected. If the device is used in a high-temperature environment, a heat-resistant AI model can be selected. Furthermore, if the device is used while in transit, an AI model capable of real-time processing can be selected. This allows for the selection of the optimal AI model based on the device's operating environment.

[0063] The coordinating unit can also analyze the communication history between devices and generate an optimal coordinating operation protocol. For example, it can generate an optimal protocol based on past communication history between devices. It can also analyze the communication frequency between devices and generate an efficient protocol. Furthermore, it can refer to the communication error history between devices and generate a protocol that avoids errors. In this way, an optimal coordinating operation protocol can be generated based on the communication history between devices.

[0064] The security department can also analyze past security incidents of a device and implement optimal security features. For example, it can select the optimal encryption algorithm based on past security incidents of the device. It can also analyze past security incidents of the device and implement security features to reinforce vulnerabilities. Furthermore, it can refer to past security incidents of the device and implement security measures to prevent recurrence of incidents. In this way, it can provide optimal security features based on past security incidents of the device.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The development department provides a GUI-based development environment. The development department provides an intuitive environment for users, featuring drag-and-drop functionality and real-time preview capabilities. It also supports no-code or low-code development and provides templates and wizards, allowing AI agents to be implemented even without specialized programming knowledge. Step 2: The selection unit automatically selects and optimizes the optimal AI model based on the device's characteristics. The selection unit selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption, and applies optimization techniques as needed. For example, it optimizes the AI ​​model using model compression or quantization techniques. Step 3: The collaboration unit automatically generates a collaborative operation protocol between AI agents based on the AI ​​model selected by the selection unit. The collaboration unit generates a protocol that facilitates cooperation between multiple devices and defines communication procedures and data exchange formats to ensure smooth communication between devices. Step 4: The security unit automatically implements encryption functions according to security requirements based on the protocol generated by the cooperation unit. The security unit encrypts communication data between devices and adds authentication functions. For example, it applies encryption algorithms and key management methods to prevent data leakage and unauthorized access.

[0067] (Example of form 2) An integrated platform according to an embodiment of the present invention is an integrated platform that realizes the development of next-generation communication devices with an "AI agent-first" approach. This integrated platform allows device manufacturers to easily implement AI agents optimized for the characteristics of their devices using an intuitive GUI-based development environment. Furthermore, cooperative operation protocols and security functions between AI agents are automatically implemented. This platform consists of the following steps. First, the device manufacturer designs the AI ​​agent using a GUI-based development environment. Development is possible using no-code or low-code methods, and AI agents can be implemented without specialized programming knowledge. For example, functions of the AI ​​agent can be added or settings changed using drag-and-drop operations. Next, the platform automatically selects and optimizes the optimal AI model based on the characteristics of the device. For example, it selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption, and applies lightweighting techniques as needed. This maximizes the performance of the device. Furthermore, the platform automatically generates cooperative operation protocols between AI agents. This facilitates cooperation between multiple devices and enables smooth communication between devices. For example, a system can be built in which multiple IoT devices cooperate to collect and analyze data. Furthermore, the platform automatically implements encryption functions according to security requirements. This ensures secure communication between devices, preventing data leaks and unauthorized access. For example, security is enhanced by encrypting communication data between devices and adding authentication functions. This platform allows device manufacturers to significantly reduce the time and cost required to develop AI agents. It also simplifies the implementation of AI agents, solving the problem of AI engineer shortages and promoting innovation. Moreover, it is expected to accelerate the development of next-generation communication devices and contribute to the realization of a truly Intelligent Connected World.This allows the integrated platform to significantly reduce the time and cost that device manufacturers spend developing AI agents.

[0068] The integrated platform according to this embodiment comprises a development unit, a selection unit, a cooperation unit, and a security unit. The development unit provides a GUI-based development environment. The development unit provides an environment that users can operate intuitively, for example, by providing drag-and-drop functionality. The development unit also provides a real-time preview function, allowing users to immediately verify the operation of the AI ​​agent they have designed. Furthermore, the development unit supports no-code or low-code development, enabling the implementation of AI agents without specialized programming knowledge. For example, the development unit provides templates and wizards to allow users to easily design AI agents. The selection unit automatically selects and optimizes the optimal AI model based on the characteristics of the device. For example, the selection unit selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption. The selection unit also applies lightweighting techniques as needed to maximize the performance of the device. For example, the selection unit uses model compression and quantization techniques to lighten the AI ​​model. The cooperation unit automatically generates cooperative operation protocols between AI agents based on the AI ​​model selected by the selection unit. The cooperation unit generates protocols that facilitate cooperation between multiple devices, for example. For example, the cooperation unit defines communication procedures and data exchange formats to ensure smooth communication between devices. The security unit automatically implements encryption functions according to security requirements based on the protocols generated by the cooperation unit. For example, the security unit encrypts communication data between devices and adds authentication functions. For example, the security unit applies encryption algorithms and key management methods to prevent data leakage and unauthorized access. As a result, the integrated platform according to the embodiment easily implements AI agents optimized for the characteristics of devices, and cooperative operation protocols and security functions are also automatically implemented.

[0069] The development department provides a GUI-based development environment. For example, it offers drag-and-drop functionality, providing an intuitive user experience. Specifically, users can easily place and connect necessary components on the screen through a visual interface. This enables the design of complex AI agents even without specialized programming knowledge. Furthermore, the development department provides a real-time preview function, allowing users to instantly verify the operation of their designed AI agents. For example, when a user changes settings on the GUI, the changes are immediately reflected, allowing real-time verification of the AI ​​agent's operation. In addition, the development department supports no-code or low-code development, enabling the implementation of AI agents without specialized programming knowledge. For instance, the development department provides templates and wizards to facilitate AI agent design. Templates offer common AI agent design patterns, requiring only customization by the user. Wizards guide the user step-by-step, assisting in the design of AI agents by guiding them through the necessary settings in sequence. This allows the development department to provide an environment where users can efficiently design and implement AI agents, significantly simplifying the development process.

[0070] The selection unit automatically selects and optimizes the optimal AI model based on the device's characteristics. For example, the selection unit selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption. Specifically, the selection unit evaluates the device's hardware resources and proposes the most suitable AI model. For example, for devices with limited memory capacity, it selects a model with low memory usage, and for devices with high computing performance, it selects a more complex and high-precision model. The selection unit also applies lightweighting techniques as needed to maximize the device's performance. For example, the selection unit uses model compression and quantization techniques to lighten the AI ​​model. Model compression is a technique that reduces unnecessary parameters to decrease the model size, and quantization is a technique that reduces computational complexity by converting model parameters into low-precision numerical values. This allows the selection unit to efficiently utilize the device's resources and provide the optimal AI model. Furthermore, the selection unit continuously monitors the AI ​​model's performance and can re-select or re-optimize the model as needed. This ensures that the selection unit always provides the optimal AI model and maximizes the device's performance.

[0071] The collaboration unit automatically generates collaborative operation protocols between AI agents based on the AI ​​model selected by the selection unit. For example, the collaboration unit generates protocols that facilitate cooperation between multiple devices. Specifically, it defines communication procedures and data exchange formats to ensure smooth communication between devices. For instance, it adjusts the method and timing of data transmission and reception between devices to maintain data integrity. Furthermore, the collaboration unit generates protocols for AI agents to cooperate in performing tasks. For example, when multiple devices cooperate to monitor an environment, it generates protocols for sharing data collected by each device and making integrated decisions. This allows the collaboration unit to enable multiple devices to cooperate efficiently and perform more advanced tasks. In addition, the collaboration unit can also generate protocols to respond to dynamic environmental changes. For example, in the event of device failure or communication failure, the collaboration unit generates protocols for other devices to take over, improving the overall reliability of the system. This enables the collaboration unit to achieve flexible and reliable collaborative operation, improving the overall system performance.

[0072] The Security Department automatically implements encryption functions according to security requirements based on protocols generated by the Coordination Department. For example, the Security Department encrypts communication data between devices and adds authentication functions. Specifically, the Security Department applies encryption algorithms and key management methods to prevent data leakage and unauthorized access. For instance, the Security Department uses encryption algorithms such as AES (Advanced Encryption Standard) and RSA (Rivest-Shamir-Adleman) to encrypt communication data. Furthermore, the Security Department uses a Public Key Infrastructure (PKI) to authenticate devices and ensure reliable communication. In addition, the Security Department manages device security policies and can automatically update security settings as needed. For example, if a new threat is discovered, the Security Department quickly takes countermeasures and updates the device security settings. This ensures that the Security Department always applies the latest security measures and maintains the security of the entire system. Furthermore, the Security Department can collect and analyze security logs to detect abnormal activity. For example, the Security Department analyzes communication logs to detect signs of unauthorized access early and take appropriate measures. This allows the security department to strengthen the overall system security and achieve highly reliable operation.

[0073] The no-code section provides a no-code / low-code development environment. For example, the no-code section defines the scope of tasks that do not require programming, allowing users to easily design AI agents. The no-code section provides templates and wizards, creating an intuitive user environment. For instance, the no-code section features drag-and-drop functionality, allowing users to add features and modify settings for AI agents. It also includes a real-time preview function, enabling users to instantly see how their designed AI agents work. This allows AI agents to be implemented without specialized programming knowledge. Some or all of the above-described processes in the no-code section may be performed using AI, or not. For example, the no-code section can input user input into the AI, which can then suggest appropriate templates and wizards.

[0074] The lightweighting unit automatically applies lightweighting technologies for edge AI. For example, the lightweighting unit uses model compression technology to lighten the AI ​​model. For example, the lightweighting unit uses quantization technology to lighten the AI ​​model. For example, the lightweighting unit uses distillation technology to lighten the AI ​​model. This allows the device performance to be maximized. Some or all of the above processing in the lightweighting unit may be performed using AI, for example, or without AI. For example, the lightweighting unit can input device characteristics into the AI, and the AI ​​can suggest an appropriate lightweighting technology.

[0075] The selection unit selects an AI model that is suitable according to the constraints of the device's memory capacity, computing performance, and power consumption. For example, the selection unit selects an AI model based on the upper limit of the device's memory capacity. For example, the selection unit selects an AI model based on an indicator of the device's computing performance. For example, the selection unit selects an AI model based on a method for measuring the device's power consumption. This makes it possible to select the AI ​​model that is optimal for the characteristics of the device. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input the characteristics of the device into the AI, and the AI ​​can propose an appropriate AI model.

[0076] The coordinating unit generates protocols that facilitate cooperation between multiple devices. The coordinating unit defines communication procedures, for example, to ensure smooth communication between devices. The coordinating unit defines data exchange formats, for example, to facilitate data exchange between devices. The coordinating unit defines synchronization methods, for example, to synchronize the operations of devices. This facilitates cooperation between multiple devices. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input the communication procedures between devices into the AI, which can then generate an appropriate protocol.

[0077] The security unit encrypts communication data between devices and adds authentication functionality. For example, the security unit applies an encryption algorithm to encrypt the communication data between devices. For example, the security unit applies a key management method to securely manage the communication data between devices. For example, the security unit applies an authentication method to authenticate the communication between devices. This ensures that communication between devices is secure and prevents data leakage and unauthorized access. Some or all of the above processes in the security unit may be performed using AI, for example, or without AI. For example, the security unit can input the communication data between devices into the AI, which can then suggest an appropriate encryption algorithm and authentication method.

[0078] The development department estimates the user's emotions and customizes the development environment interface based on the estimated emotions. For example, if the user is stressed, the development department provides a simple interface and minimizes the number of steps required to operate it. For example, if the user is relaxed, the development department provides detailed setting options and suggests a customizable interface. For example, if the user is in a hurry, the development department prioritizes voice input and shortcut keys to enable quick operation. This allows for the provision of an interface that responds to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the development department may be performed using AI or not. For example, the development department can input user emotion data into an AI, which can then suggest an appropriate interface.

[0079] The development department analyzes the user's past development history and proposes the most suitable development tools and templates. For example, the development department automatically suggests the most suitable tools based on the development tools the user has used in the past. For example, the development department prioritizes displaying frequently used templates from the user's past project history. For example, the development department analyzes the user's development history and proposes the most suitable toolset based on specific development patterns. This allows the development department to propose the most suitable tools and templates based on the user's past development history. Some or all of the above processes in the development department may be performed using AI, or not. For example, the development department can input the user's development history data into AI, which can then suggest appropriate tools and templates.

[0080] The development department adjusts the difficulty level of the development environment according to the user's skill level. For example, the development department displays only basic functions and simplifies operation for beginner users. For example, the development department provides detailed setting options and a customizable environment for intermediate users. For example, the development department displays all functions and provides a highly flexible development environment for advanced users. This allows the development environment to be tailored to the user's skill level. Some or all of the above processes in the development department may be performed using AI, for example, or not. For example, the development department can input user skill level data into AI, which can then suggest an appropriate development environment.

[0081] The development department estimates the user's emotions and visualizes the progress of the development process based on the estimated emotions. For example, if the user is stressed, the development department displays the progress simply to reduce visual burden. For example, if the user is relaxed, the development department displays detailed progress to allow the user to grasp the overall picture of the project. For example, if the user is in a hurry, the development department highlights only the important progress to allow for quick review. This enables the visualization of progress in accordance with the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the development department may be performed using AI or not. For example, the development department can input user emotion data into AI, and the AI ​​can suggest an appropriate way to display the progress.

[0082] The development department provides optimal development resources by considering the user's geographical location. For example, the development department provides information on nearby development communities and events based on the user's location. For example, the development department suggests optimal cloud resources based on the user's geographical location. For example, the development department provides local development resources and support according to the user's location. This allows the development department to provide optimal development resources based on the user's geographical location. Some or all of the above processes in the development department may be performed using AI, or not. For example, the development department can input the user's geographical location into AI, which can then suggest appropriate development resources.

[0083] The development department analyzes users' social media activity and suggests relevant development communities and forums. For example, the development department suggests relevant communities based on the developers and technologies that users follow. For example, the development department analyzes users' social media activity and suggests forums related to technologies they are interested in. For example, the development department suggests relevant development events and workshops based on users' social media posts. This allows the development department to suggest relevant development communities and forums based on users' social media activity. Some or all of the above processes in the development department may be performed using AI, or not. For example, the development department can input user social media data into AI, which can then suggest appropriate communities and forums.

[0084] The selection unit estimates the user's emotions and adjusts the AI ​​model selection criteria based on the estimated emotions. For example, if the user is stressed, the selection unit prioritizes a simple and intuitive AI model. If the user is relaxed, the selection unit suggests an AI model with detailed settings. If the user is in a hurry, the selection unit prioritizes an AI model that can be implemented quickly. This provides AI model selection criteria that correspond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI or not using AI. For example, the selection unit can input user emotion data into an AI, which can then suggest appropriate AI model selection criteria.

[0085] The selection unit selects the optimal AI model by referring to the device's past performance data. For example, the selection unit selects the optimal AI model based on the device's past memory usage. For example, the selection unit selects the optimal AI model by referring to the device's past computing performance data. For example, the selection unit selects the optimal AI model based on the device's past power consumption data. This allows the selection of the optimal AI model based on the device's past performance data. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input the device's performance data into the AI, which can then propose an appropriate AI model.

[0086] The selection unit selects an AI model based on the device's usage environment. For example, if the device is used outdoors, the selection unit selects a low-power consumption AI model. If the device is used in a high-temperature environment, the selection unit selects a heat-resistant AI model. If the device is used while in transit, the selection unit selects an AI model capable of real-time processing. This allows for the selection of the optimal AI model based on the device's usage environment. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input device usage environment data into the AI, which can then propose an appropriate AI model.

[0087] The selection unit estimates the user's emotions and adjusts the order in which it displays the AI ​​model selection results based on the estimated user emotions. For example, if the user is stressed, the selection unit will first display a simple and intuitive AI model. If the user is relaxed, the selection unit will first display an AI model with detailed settings. If the user is in a hurry, the selection unit will first display an AI model that can be quickly implemented. This allows the system to provide an AI model selection result that is appropriate to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI or not using AI. For example, the selection unit can input user emotion data into an AI, which can then suggest an order in which it will display the selection results for an appropriate AI model.

[0088] The selection unit selects an AI model considering the geographical distribution of the devices. For example, if the device is used in an urban area, the selection unit selects an AI model with a high communication speed. For example, if the device is used in a rural area, the selection unit selects an AI model with low power consumption. For example, if the device is used internationally, the selection unit selects a multilingual AI model. This allows for the selection of the optimal AI model based on the geographical distribution of the devices. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input geographical distribution data of the devices into an AI, which can then propose an appropriate AI model.

[0089] The selection unit improves the accuracy of AI model selection by referring to relevant device literature. For example, the selection unit refers to literature on the device's technical specifications and selects the optimal AI model. For example, the selection unit analyzes literature on device use cases and selects an appropriate AI model. For example, the selection unit selects the optimal AI model based on literature on device performance evaluation. This improves the accuracy of AI model selection based on relevant device literature. Some or all of the above processing in the selection unit may be performed using AI, or not using AI. For example, the selection unit can input device-related literature data into an AI, which can then propose an appropriate AI model.

[0090] The collaborative unit estimates the user's emotions and adjusts the method for generating collaborative action protocols based on the estimated user emotions. For example, if the user is stressed, the collaborative unit generates a simple and intuitive protocol. For example, if the user is relaxed, the collaborative unit generates a protocol with detailed settings. For example, if the user is in a hurry, the collaborative unit generates a protocol that can be implemented quickly. This provides a method for generating collaborative action protocols that respond to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the collaborative unit may be performed using AI, for example, or not using AI. For example, the collaborative unit can input user emotion data into an AI, which can then suggest an appropriate method for generating protocols.

[0091] The coordinating unit analyzes the communication history between devices to generate an optimal coordinating operation protocol. For example, the coordinating unit generates an optimal protocol based on the past communication history between devices. For example, the coordinating unit analyzes the communication frequency between devices to generate an efficient protocol. For example, the coordinating unit refers to the communication error history between devices to generate a protocol that avoids errors. This makes it possible to generate an optimal coordinating operation protocol based on the communication history between devices. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input the communication history data between devices into the AI, which can then propose an appropriate protocol.

[0092] The coordinating unit customizes the coordinating operation protocol based on the device usage scenario. For example, if the device is used in a home, the coordinating unit generates a protocol optimized for the home network. For example, if the device is used in a business, the coordinating unit generates a protocol optimized for the business network. For example, if the device is used in a public place, the coordinating unit generates a protocol optimized for the public network. This allows for the provision of the optimal coordinating operation protocol based on the device usage scenario. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input device usage scenario data into the AI, which can then propose an appropriate protocol.

[0093] The collaborative unit estimates the user's emotions and adjusts the display method of the collaborative action protocol based on the estimated user emotions. For example, if the user is stressed, the collaborative unit provides a simple and intuitive display method. For example, if the user is relaxed, the collaborative unit provides a display method that includes detailed information. For example, if the user is in a hurry, the collaborative unit provides a display method that gets straight to the point. This allows for the display method of the collaborative action protocol to be tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the collaborative unit may be performed using AI, for example, or not using AI. For example, the collaborative unit can input user emotion data into an AI, which can then suggest an appropriate display method.

[0094] The coordinating unit generates a coordinating operation protocol considering the geographical distribution of the devices. For example, if the devices are used in urban areas, the coordinating unit generates a protocol with a high communication speed. If the devices are used in rural areas, the coordinating unit generates a protocol with low power consumption. If the devices are used internationally, the coordinating unit generates a multilingual protocol. This allows for the provision of an optimal coordinating operation protocol based on the geographical distribution of the devices. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input geographical distribution data of the devices into the AI, which can then propose an appropriate protocol.

[0095] The coordinating unit improves the accuracy of the coordinating operation protocol by referring to relevant device documentation. For example, the coordinating unit generates an optimal protocol by referring to documentation on the device's technical specifications. For example, the coordinating unit generates an appropriate protocol by analyzing documentation on device use cases. For example, the coordinating unit generates an optimal protocol based on documentation on device performance evaluation. This improves the accuracy of the coordinating operation protocol based on relevant device documentation. Some or all of the above processing in the coordinating unit may be performed using AI, for example, or without AI. For example, the coordinating unit can input device documentation data into AI, and the AI ​​can propose an appropriate protocol.

[0096] The security unit estimates the user's emotions and adjusts the implementation of security features based on the estimated emotions. For example, if the user is stressed, the security unit provides simple and intuitive security settings. If the user is relaxed, the security unit provides detailed security setting options. If the user is in a hurry, the security unit provides security features that can be set quickly. This allows for the implementation of security features that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the security unit may be performed using AI or not. For example, the security unit can input user emotion data into an AI, which can then suggest appropriate security settings.

[0097] The security department analyzes past security incidents of a device and implements optimal security features. For example, the security department selects the optimal encryption algorithm based on past security incidents of the device. For example, the security department analyzes past security incidents of the device and implements security features to reinforce vulnerabilities. For example, the security department refers to past security incidents of the device and implements security measures to prevent the recurrence of incidents. This allows the security department to provide optimal security features based on past security incidents of the device. Some or all of the above processes in the security department may be performed using AI, for example, or not using AI. For example, the security department can input past security incident data into AI, and the AI ​​can propose appropriate security features.

[0098] The security department customizes security features based on the device's usage environment. For example, if the device is used in a public place, the security department implements strong authentication features. If the device is used at home, for example, the security department provides simple authentication features. If the device is used within a company, for example, the security department implements security features based on the company's security policy. This allows for the provision of optimal security features based on the device's usage environment. Some or all of the above processing in the security department may be performed using AI, for example, or without AI. For example, the security department can input device usage environment data into the AI, which can then suggest appropriate security features.

[0099] The security unit estimates the user's emotions and prioritizes security features based on the estimated emotions. For example, if the user is stressed, the security unit prioritizes implementing basic security features. If the user is relaxed, the security unit prioritizes implementing detailed security features. If the user is in a hurry, the security unit prioritizes implementing security features that can be set up quickly. This provides a priority of security features according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the security unit may be performed using AI or not. For example, the security unit can input user emotion data into an AI, which can then suggest an appropriate priority for security features.

[0100] The security unit implements security features considering the geographical distribution of devices. For example, if a device is used in an urban area, the security unit implements security features that enhance communication encryption. For example, if a device is used in a rural area, the security unit implements security features that reduce power consumption. For example, if a device is used internationally, the security unit implements multilingual security features. This allows for the provision of optimal security features based on the geographical distribution of devices. Some or all of the above processing in the security unit may be performed using AI, for example, or without AI. For example, the security unit can input geographical distribution data of devices into an AI, which can then suggest appropriate security features.

[0101] The security department improves the accuracy of security functions by referring to relevant device documentation. For example, the security department implements optimal security functions by referring to documentation on the device's technical specifications. For example, the security department implements appropriate security functions by analyzing documentation on device use cases. For example, the security department implements optimal security functions based on documentation on device performance evaluation. This improves the accuracy of security functions based on relevant device documentation. Some or all of the above processes in the security department may be performed using AI, for example, or without AI. For example, the security department can input device documentation data into AI, which can then propose appropriate security functions.

[0102] The no-code component estimates the user's emotions and customizes the interface of the no-code development environment based on the estimated emotions. For example, if the user is stressed, the no-code component provides a simple interface and minimizes the number of steps required to operate it. For example, if the user is relaxed, the no-code component provides detailed configuration options and suggests a customizable interface. For example, if the user is in a hurry, the no-code component prioritizes voice input and shortcut keys to enable quick operation. This allows for the provision of a no-code development environment interface that responds to the user's emotions. Emotion estimation is achieved using emotion estimation functionality, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the no-code component may be performed using AI or not. For example, the no-code component can input user emotion data into an AI, which can then suggest an appropriate interface.

[0103] The no-code section analyzes the user's past development history and suggests the most suitable no-code tools and templates. For example, the no-code section automatically suggests the best tools based on the no-code tools the user has used in the past. For example, the no-code section prioritizes displaying frequently used templates based on the user's past project history. For example, the no-code section analyzes the user's development history and suggests the best toolset based on specific development patterns. This allows the no-code section to suggest the most suitable no-code tools and templates based on the user's past development history. Some or all of the above processes in the no-code section may be performed using AI, or not. For example, the no-code section can input the user's development history data into AI, which can then suggest appropriate tools and templates.

[0104] The no-code component estimates the user's emotions and visualizes the progress of the no-code development process based on the estimated emotions. For example, if the user is stressed, the no-code component displays the progress simply to reduce visual burden. For example, if the user is relaxed, the no-code component displays detailed progress to allow the user to grasp the overall picture of the project. For example, if the user is in a hurry, the no-code component highlights only the important progress for quick review. This allows for the visualization of the progress of the no-code development process in accordance with the user's emotions. Emotion estimation is achieved using emotion estimation functionality, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the no-code component may be performed using AI or not. For example, the no-code component can input user emotion data into AI, which can then suggest an appropriate way to display the progress.

[0105] The no-code component provides optimal no-code resources considering the user's geographical location. For example, the no-code component provides information on nearby development communities and events based on the user's location. For example, the no-code component suggests optimal cloud resources based on the user's geographical location. For example, the no-code component provides local development resources and support according to the user's location. This enables the provision of optimal no-code resources based on the user's geographical location. Some or all of the above processing in the no-code component may be performed using AI, for example, or without AI. For example, the no-code component can input the user's geographical location information into AI, which can then suggest appropriate no-code resources.

[0106] The optimization unit estimates the user's emotions and adjusts the application method of optimization techniques based on the estimated user emotions. For example, if the user is stressed, the optimization unit applies a simple and intuitive optimization technique. For example, if the user is relaxed, the optimization unit applies an optimization technique that allows for detailed settings. For example, if the user is in a hurry, the optimization unit prioritizes an optimization technique that can be applied quickly. This allows for the application of optimization techniques in accordance with the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input user emotion data into an AI, which can then suggest an appropriate method for applying optimization techniques.

[0107] The lightweighting unit applies the optimal lightweighting technique by referring to the device's past performance data. For example, the lightweighting unit applies the optimal lightweighting technique based on the device's past memory usage. For example, the lightweighting unit applies the optimal lightweighting technique by referring to the device's past computing performance data. For example, the lightweighting unit applies the optimal lightweighting technique based on the device's past power consumption data. This makes it possible to provide the optimal lightweighting technique based on the device's past performance data. Some or all of the above processing in the lightweighting unit may be performed using AI, for example, or without AI. For example, the lightweighting unit can input the device's performance data into AI, and the AI ​​can propose an appropriate lightweighting technique.

[0108] The optimization unit estimates the user's emotions and adjusts the order in which the results of optimization techniques are displayed based on the estimated emotions. For example, if the user is stressed, the optimization unit first displays the results of simple and intuitive optimization techniques. For example, if the user is relaxed, the optimization unit first displays the results of optimization techniques that allow for detailed settings. For example, if the user is in a hurry, the optimization unit first displays the results of optimization techniques that can be applied quickly. This allows the optimization unit to provide results of optimization techniques that are tailored to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI, for example, or not using AI. For example, the optimization unit can input user emotion data into an AI, which can then suggest an appropriate display order for the application results.

[0109] The lightweighting unit applies lightweighting techniques considering the geographical distribution of the devices. For example, if the device is used in an urban area, the lightweighting unit applies lightweighting techniques that enable high communication speeds. For example, if the device is used in a rural area, the lightweighting unit applies lightweighting techniques that enable low power consumption. For example, if the device is used internationally, the lightweighting unit applies lightweighting techniques that support multiple languages. This allows the lightweighting unit to provide the optimal lightweighting technique based on the geographical distribution of the devices. Some or all of the above processing in the lightweighting unit may be performed using AI, for example, or without AI. For example, the lightweighting unit can input geographical distribution data of the devices into an AI, which can then propose an appropriate lightweighting technique.

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

[0111] The development team can also estimate user emotions and customize the development environment interface based on those emotions. For example, if a user is stressed, a simple interface can be provided with minimal steps. If a user is relaxed, detailed settings options can be offered, and a customizable interface can be suggested. Furthermore, if a user is in a hurry, voice input or shortcut keys can be prioritized to allow for quick operation. This allows for the provision of an interface that responds to the user's emotions.

[0112] The no-code component can analyze a user's past development history and suggest the most suitable development tools and templates. For example, it can automatically suggest the best tools based on the development tools the user has used in the past. It can also prioritize displaying frequently used templates based on the user's past project history. Furthermore, it can analyze the user's development history and suggest the optimal toolset based on specific development patterns. This allows for the suggestion of the most suitable tools and templates based on the user's past development history.

[0113] The lightweighting unit can also apply optimal lightweighting techniques by referring to the device's past performance data. For example, it can apply optimal lightweighting techniques based on the device's past memory usage. It can also apply optimal lightweighting techniques by referring to the device's past computing performance data. Furthermore, it can apply optimal lightweighting techniques based on the device's past power consumption data. This allows for the provision of optimal lightweighting techniques based on the device's past performance data.

[0114] The selection unit can also select an AI model based on the device's operating environment. For example, if the device is used outdoors, a low-power consumption AI model can be selected. If the device is used in a high-temperature environment, a heat-resistant AI model can be selected. Furthermore, if the device is used while in transit, an AI model capable of real-time processing can be selected. This allows for the selection of the optimal AI model based on the device's operating environment.

[0115] The coordinating unit can also analyze the communication history between devices and generate an optimal coordinating operation protocol. For example, it can generate an optimal protocol based on past communication history between devices. It can also analyze the communication frequency between devices and generate an efficient protocol. Furthermore, it can refer to the communication error history between devices and generate a protocol that avoids errors. In this way, an optimal coordinating operation protocol can be generated based on the communication history between devices.

[0116] The security department can also analyze past security incidents of a device and implement optimal security features. For example, it can select the optimal encryption algorithm based on past security incidents of the device. It can also analyze past security incidents of the device and implement security features to reinforce vulnerabilities. Furthermore, it can refer to past security incidents of the device and implement security measures to prevent recurrence of incidents. In this way, it can provide optimal security features based on past security incidents of the device.

[0117] The development team can also estimate user emotions and visualize the progress of the development process based on those emotions. For example, if a user is stressed, the progress can be displayed simply to reduce visual burden. If a user is relaxed, detailed progress can be displayed to give them an overview of the project. Furthermore, if a user is in a hurry, only important progress can be highlighted for quick review. This makes it possible to visualize progress in a way that is tailored to the user's emotions.

[0118] The selection unit can also estimate the user's emotions and adjust the AI ​​model selection criteria based on those emotions. For example, if the user is stressed, a simple and intuitive AI model can be prioritized. If the user is relaxed, an AI model with detailed settings can be suggested. Furthermore, if the user is in a hurry, an AI model that can be implemented quickly can be prioritized. This allows for the provision of AI model selection criteria tailored to the user's emotions.

[0119] The collaborative unit can also estimate the user's emotions and adjust the method of generating collaborative action protocols based on those estimated emotions. For example, if the user is stressed, it can generate a simple and intuitive protocol. If the user is relaxed, it can generate a protocol with detailed settings. Furthermore, if the user is in a hurry, it can generate a protocol that can be implemented quickly. This provides a method for generating collaborative action protocols that respond to the user's emotions.

[0120] The security department can also estimate the user's emotions and adjust the implementation of security features based on those emotions. For example, if the user is stressed, it can provide simple and intuitive security settings. If the user is relaxed, it can provide more detailed security setting options. Furthermore, if the user is in a hurry, it can provide security features that can be set up quickly. This allows for the implementation of security features in a way that is tailored to the user's emotions.

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

[0122] Step 1: The development department provides a GUI-based development environment. The development department provides an intuitive environment for users, featuring drag-and-drop functionality and real-time preview capabilities. It also supports no-code or low-code development and provides templates and wizards, allowing AI agents to be implemented even without specialized programming knowledge. Step 2: The selection unit automatically selects and optimizes the optimal AI model based on the device's characteristics. The selection unit selects an appropriate AI model according to constraints such as the device's memory capacity, computing performance, and power consumption, and applies optimization techniques as needed. For example, it optimizes the AI ​​model using model compression or quantization techniques. Step 3: The collaboration unit automatically generates a collaborative operation protocol between AI agents based on the AI ​​model selected by the selection unit. The collaboration unit generates a protocol that facilitates cooperation between multiple devices and defines communication procedures and data exchange formats to ensure smooth communication between devices. Step 4: The security unit automatically implements encryption functions according to security requirements based on the protocol generated by the cooperation unit. The security unit encrypts communication data between devices and adds authentication functions. For example, it applies encryption algorithms and key management methods to prevent data leakage and unauthorized access.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the development unit, selection unit, cooperation unit, and security unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the development unit is implemented by the control unit 46A of the smart device 14 and provides a GUI-based development environment. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically selects and optimizes the optimal AI model based on the device characteristics. The cooperation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates a cooperative operation protocol between AI agents. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically implements encryption functions according to security requirements. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the development unit, selection unit, cooperation unit, and security unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the development unit is implemented by the control unit 46A of the smart glasses 214 and provides a GUI-based development environment. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically selects and optimizes the optimal AI model based on the characteristics of the device. The cooperation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates a cooperative operation protocol between AI agents. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically implements encryption functions according to security requirements. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the development unit, selection unit, cooperation unit, and security unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the development unit is implemented by the control unit 46A of the headset terminal 314 and provides a GUI-based development environment. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically selects and optimizes the optimal AI model based on the characteristics of the device. The cooperation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates a cooperative operation protocol between AI agents. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically implements encryption functions according to security requirements. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

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

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the development unit, selection unit, cooperation unit, and security unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the development unit is implemented by the control unit 46A of the robot 414 and provides a GUI-based development environment. The selection unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically selects and optimizes the optimal AI model based on the characteristics of the device. The cooperation unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically generates a cooperative operation protocol between AI agents. The security unit is implemented by the specific processing unit 290 of the data processing unit 12 and automatically implements encryption functions according to security requirements. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) The development department provides a GUI-based development environment, A selection unit automatically selects and adjusts an appropriate AI model based on the device characteristics from the AI ​​agent designed by the aforementioned development unit, A cooperation unit that automatically generates a cooperative operation protocol between AI agents based on the AI ​​model selected by the selection unit, The system includes a security unit that automatically implements encryption functions based on security requirements, using a protocol generated by the aforementioned coordination unit. A system characterized by the following features. (Note 2) It includes a no-code section that provides a no-code / low-code development environment. The system described in Appendix 1, characterized by the features described herein. (Note 3) It features a lightweighting unit that automatically applies lightweighting technology for edge AI. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned selection unit is Select an AI model that is suitable according to the device's memory capacity, computing performance, and power consumption constraints. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned coordination unit is Generate a protocol that facilitates communication between multiple devices. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned security unit is Encrypt communication data between devices and add authentication functionality. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned development department, It estimates user emotions and customizes the development environment interface based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned development department, We analyze the user's past development history and suggest the most suitable development tools and templates. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned development department, The difficulty level of the development environment is adjusted according to the user's skill level. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned development department, It estimates user emotions and visualizes the progress of the development process based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned development department, Providing optimal development resources while considering the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned development department, Analyze users' social media activity and suggest relevant development communities and forums. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned selection unit is It estimates the user's emotions and adjusts the selection criteria for the AI ​​model based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned selection unit is The optimal AI model is selected by referencing the device's past performance data. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned selection unit is Select an AI model based on the device's usage environment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned selection unit is It estimates the user's emotions and adjusts the order in which the AI ​​model selection results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned selection unit is Select an AI model considering the geographical distribution of devices. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned selection unit is Improve the accuracy of AI model selection by referring to relevant device literature. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned coordination unit is It estimates the user's emotions and adjusts the method of generating collaborative behavior protocols based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned coordination unit is Analyze the communication history between devices to generate the optimal cooperative operation protocol. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned coordination unit is Customize the cooperative operation protocol based on the device usage scenario. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned coordination unit is It estimates the user's emotions and adjusts how the collaborative behavior protocol is displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned coordination unit is Generate a cooperative operation protocol that takes into account the geographical distribution of devices. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned coordination unit is Referencing relevant device documentation improves the accuracy of the cooperative operation protocol. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned security unit is It estimates user sentiment and adjusts the implementation of security features based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned security unit is Analyze past security incidents on devices to implement optimal security features. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned security unit is Customize security features based on the device's usage environment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned security unit is It estimates user sentiment and prioritizes security features based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned security unit is Implement security features that take into account the geographical distribution of devices. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned security unit is Referencing relevant documentation for the device improves the accuracy of security features. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned no-code section is It estimates user emotions and customizes the interface of the no-code development environment based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned no-code section is We analyze the user's past development history and suggest the most suitable no-code tools and templates. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned no-code section is It estimates user emotions and visualizes the progress of the no-code development process based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned no-code section is Provides optimal no-code resources considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned lightweight section is It estimates the user's emotions and adjusts how optimization techniques are applied based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned lightweight section is Referencing the device's historical performance data will apply the most suitable optimization techniques. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned lightweight section is It estimates the user's emotions and adjusts the order in which the results of optimization techniques are displayed based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 38) The aforementioned lightweight section is Applying weight reduction techniques while considering the geographical distribution of devices The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

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

Claims

1. The development department provides a GUI-based development environment, A selection unit automatically selects and adjusts an appropriate AI model based on the device characteristics from the AI ​​agent designed by the aforementioned development unit, A cooperation unit that automatically generates a cooperative operation protocol between AI agents based on the AI ​​model selected by the selection unit, The system includes a security unit that automatically implements encryption functions based on security requirements, using a protocol generated by the aforementioned coordination unit. A system characterized by the following features.

2. It includes a no-code section that provides a no-code / low-code development environment. The system according to feature 1.

3. It features a lightweighting unit that automatically applies lightweighting technology for edge AI. The system according to feature 1.

4. The aforementioned selection unit is Select an AI model that is suitable according to the constraints of the device's memory capacity, computing performance, and power consumption. The system according to feature 1.

5. The aforementioned coordination unit is Generate a protocol that facilitates communication between multiple devices. The system according to feature 1.

6. The aforementioned security unit is Encrypt communication data between devices and add authentication functionality. The system according to feature 1.

7. The aforementioned development department, It estimates user emotions and customizes the development environment interface based on those estimated emotions. The system according to feature 1.

8. The aforementioned development department, We analyze the user's past development history and suggest the most suitable development tools and templates. The system according to feature 1.

9. The aforementioned development department, The difficulty level of the development environment is adjusted according to the user's skill level. The system according to feature 1.

10. The aforementioned development department, It estimates user emotions and visualizes the progress of the development process based on those estimated emotions. The system according to feature 1.

Images