system

Abstract

The system according to this embodiment aims to seamlessly link different generative AI systems to achieve efficient resource utilization and high-quality content generation. [Solution] The system according to the embodiment comprises a protocol definition unit, a task allocation unit, an error detection unit, and a content provision unit. The protocol definition unit defines a common communication protocol and data format. The task allocation unit allocates tasks according to the area of ​​expertise of each generating AI based on the protocol defined by the protocol definition unit. The error detection unit verifies the results of the tasks allocated by the task allocation unit, detects errors, and corrects them. The content provision unit provides the user with the results after correcting the errors detected by the error detection unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to cooperate between different generation AI systems, and there are problems in efficient use of resources and generation of high-quality content.

[0005] The system according to the embodiment aims to seamlessly cooperate different generation AI systems and achieve efficient resource utilization and high-quality content generation.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a protocol definition unit, a task allocation unit, an error detection unit, and a content provision unit. The protocol definition unit defines a common communication protocol and data format. The task allocation unit allocates tasks to each generating AI according to its area of ​​expertise, based on the protocol defined by the protocol definition unit. The error detection unit verifies the results of the tasks allocated by the task allocation unit, detects errors, and corrects them. The content provision unit provides the user with the results after the errors detected by the error detection unit have been corrected. [Effects of the Invention]

[0007] The system according to this embodiment can seamlessly link different generative AI systems, enabling efficient resource utilization and high-quality content generation. [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, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The generative AI-to-generative AI interface standardization system according to an embodiment of the present invention is a mechanism for seamlessly linking different generative AI systems. This generative AI-to-generative AI interface standardization system includes a protocol definition unit that defines a common communication protocol and data format, a task distribution unit that distributes tasks according to the strengths of each generative AI, an error detection unit that verifies the results of tasks, detects and corrects errors, and a content provision unit that provides high-quality content to users. This enables the meshing of generative AIs, which is expected to lead to efficient resource utilization and improved creativity. For example, the protocol definition unit defines a common communication protocol to facilitate communication between different generative AI systems. The task distribution unit distributes tasks according to the strengths of each generative AI. The error detection unit detects errors by having multiple generative AIs cooperate to verify each other's results. The content provision unit provides users with high-quality and diverse content. As a result, users can access high-quality and diverse content and enjoy a richer experience. In addition, it reduces power consumption due to excessive GPU use and carbon dioxide (CO2) emissions from the operation of the cooling system, mitigating the problem of increasing burden on the global environment. This enables the sustainable operation of generative AI and contributes to solving environmental problems. The generative AI-to-generative AI interface standardization system allows for seamless integration of different generative AI systems, resulting in efficient resource utilization and enhanced creativity.

[0029] The generative AI-to-generative AI interface standardization system according to the embodiment comprises a protocol definition unit, a task allocation unit, an error detection unit, and a content provision unit. The protocol definition unit defines common communication protocols and data formats. The protocol definition unit can define communication protocols such as HTTP, WebSocket, and MQTT. The protocol definition unit can also define data formats such as JSON, XML, and CSV. The protocol definition unit defines common protocols to facilitate communication between generative AI systems. For example, the protocol definition unit uses standardized protocols to streamline data exchange between different generative AI systems. The task allocation unit allocates tasks according to the expertise of each generative AI. For example, the task allocation unit can allocate tasks based on areas of expertise such as image generation, text generation, and speech generation. The task allocation unit appropriately distributes tasks to efficiently utilize the resources of the generative AIs. For example, the task allocation unit distributes image-related tasks to generative AIs specialized in image generation and text-related tasks to generative AIs specialized in text generation. The error detection unit verifies the task results, detects errors, and corrects them. The error detection unit can detect errors such as syntax errors, logic errors, and data errors. The error detection unit detects errors by having multiple generative AIs cooperate to verify each other's results. For example, the error detection unit compares the output results of the generative AIs with each other and detects an error if they do not match. The content provision unit provides users with high-quality and diverse content. The content provision unit can provide diverse content such as text, images, videos, and audio. The content provision unit provides users with the results of the generative AI. For example, the content provision unit provides users with high-quality content generated by the generative AI, improving the user experience. As a result, the generative AI-to-generative AI interface standardization system according to this embodiment can seamlessly link different generative AI systems, achieving efficient resource utilization and improved creativity.

[0030] The protocol definition section defines common communication protocols and data formats. Specifically, it can define communication protocols such as HTTP, WebSocket, and MQTT. This enables smooth data communication between different generative AI systems. For example, using the HTTP protocol standardizes the exchange of requests and responses between generative AI systems, ensuring compatibility. Using WebSocket enables real-time bidirectional communication, realizing immediate data exchange between generative AI systems. Furthermore, using MQTT enables efficient messaging with low bandwidth, saving resources. Regarding data formats, JSON, XML, and CSV can also be defined. JSON is widely used because it is lightweight, easy to read, and easy to serialize and deserialize. XML has a hierarchical structure and is easy to structure data, making it suitable for representing complex data. CSV is a simple text format that can efficiently handle large amounts of data. By standardizing these communication protocols and data formats, the protocol definition section streamlines data exchange between generative AI systems and ensures compatibility. This allows different generative AI systems to work seamlessly together and exchange data smoothly.

[0031] The task distribution unit distributes tasks according to each generative AI's area of ​​expertise. Specifically, tasks can be distributed based on areas of specialization such as image generation, text generation, and speech generation. For example, an AI specializing in image generation can be assigned image-related tasks, and an AI specializing in text generation can be assigned text-related tasks. This allows for efficient use of each generative AI's resources and improves overall performance. The task distribution unit considers the characteristics and performance of each generative AI to perform optimal task distribution. For example, if an image generation AI can generate high-resolution images in a short time, high-resolution image generation tasks will be concentrated on that AI. On the other hand, if a text generation AI excels at generating natural-sounding text, text generation tasks will be concentrated on that AI. Furthermore, the task distribution unit can monitor the load on each generative AI in real time and dynamically redistribute tasks to prevent uneven load distribution. This maintains the balance of the entire system and ensures efficient resource utilization. In addition, the task distribution unit can construct an optimal task distribution algorithm based on the generative AI's training data and past performance. This maximizes the performance of each generative AI and enables the efficient generation of high-quality content.

[0032] The error detection unit verifies the task results, detects errors, and corrects them. Specifically, it can detect errors such as syntax errors, logic errors, and data errors. The error detection unit detects errors by having multiple generating AIs cooperate to verify each other's results. For example, it compares the output results of the generating AIs with each other and detects errors if they do not match. This improves the reliability of the output results of the generating AIs. The error detection unit utilizes AI-based anomaly detection algorithms to detect unusual patterns and abnormal data at an early stage. For example, it checks the grammatical and semantic consistency of generated text and detects abnormal contexts and unnatural expressions. It also evaluates the quality of generated images and detects errors if they contain noise or artifacts. Furthermore, the error detection unit can identify the type and cause of errors and propose appropriate correction methods. For example, in the case of syntax errors, it provides specific steps to correct the grammar, and in the case of logic errors, it points out areas for algorithmic correction. This enables early detection and rapid correction of errors, improving the reliability and quality of the generating AI system.

[0033] The content delivery department provides users with high-quality and diverse content. Specifically, it can provide a variety of content such as text, images, videos, and audio. The content delivery department delivers the results of generative AI to users, improving the user experience. For example, it provides users with high-quality text generated by generative AI, providing easy-to-read and engaging writing. It also provides users with high-resolution images and videos generated by generative AI, providing visually appealing content. Furthermore, it provides users with natural-sounding audio generated by generative AI, providing auditory-pleasant content. The content delivery department can select and provide the most suitable content according to the user's needs and preferences. For example, if a user is looking for text on a specific theme or style, it will generate and provide text that meets that need. Also, if a user is looking for images of a specific resolution or format, it will generate and provide images that meet those requirements. Furthermore, the content delivery department can collect feedback from users and continuously improve the performance of the generative AI and the quality of the content. This increases user satisfaction and maximizes the value of the generative AI system.

[0034] The protocol definition unit can define a common communication protocol to facilitate communication between different generative AI systems. The protocol definition unit defines communication protocols such as HTTP, WebSocket, and MQTT. The protocol definition unit uses standardized protocols to streamline data exchange between different generative AI systems. For example, the protocol definition unit can use the HTTP protocol for data communication between generative AI systems. It can also use the WebSocket protocol to achieve real-time data communication. Furthermore, the protocol definition unit can use the MQTT protocol for lightweight data communication. This enables the protocol definition unit to facilitate smooth communication between different generative AI systems.

[0035] The task distribution unit can distribute tasks according to each generating AI's area of ​​expertise. For example, the task distribution unit distributes tasks based on areas of expertise such as image generation, text generation, and speech generation. The task distribution unit appropriately distributes tasks to efficiently utilize the resources of the generating AIs. For example, the task distribution unit distributes image-related tasks to a generating AI specializing in image generation, and text-related tasks to a generating AI specializing in text generation. The task distribution unit can also distribute speech-related tasks to a generating AI specializing in speech generation. This allows the task distribution unit to distribute tasks according to each generating AI's area of ​​expertise.

[0036] The error detection unit can detect errors by having multiple generating AIs cooperate to verify each other's results. The error detection unit can detect errors such as syntax errors, logic errors, and data errors. The error detection unit compares the output results of the generating AIs with each other and detects errors if they do not match. For example, the error detection unit analyzes the interrelationships of the output results of the generating AIs and detects abnormal patterns. The error detection unit can also identify the cause of an error based on the interrelationships of the output results of the generating AIs. As a result, the accuracy of error detection is improved by having multiple generating AIs cooperate to detect errors.

[0037] The content delivery department can provide users with high-quality and diverse content. For example, it can provide a variety of content such as text, images, videos, and audio. The content delivery department also provides users with the results of generative AI. For example, it can provide users with high-quality content generated by generative AI, improving the user experience. Furthermore, the content delivery department can improve content based on user feedback. For example, it can collect user ratings and comments and use them to improve the quality of its content. This allows the content delivery department to provide users with high-quality and diverse content.

[0038] The protocol definition unit can define protocols to optimize communication speeds between different generative AI systems. For example, the protocol definition unit can monitor the communication speed of each generative AI system in real time and select the optimal protocol. If the communication speed is slow, the protocol definition unit can also define protocols that improve communication speed using data compression techniques. Furthermore, if the communication speed is fast, the protocol definition unit can define protocols that enable the transmission and reception of high-quality data. In this way, the protocol definition unit enables efficient communication by defining protocols that optimize communication speed.

[0039] The protocol definition unit can apply different communication protocols depending on the type of data. For example, it can apply a lightweight protocol to text data to improve communication speed. It can also apply a high-quality protocol to image data to prevent data loss. Furthermore, it can apply a protocol suitable for real-time streaming to video data. In this way, the protocol definition unit can apply the optimal communication protocol according to the type of data.

[0040] The protocol definition unit can adjust communication protocols considering the geographical distribution of different generative AI systems. For example, the protocol definition unit can apply a protocol that minimizes latency between geographically distant generative AI systems. It can also apply a protocol that enables high-speed communication between generative AI systems within the same region. Furthermore, the protocol definition unit can define a protocol that selects the optimal communication path according to geographical conditions. This allows the protocol definition unit to adjust communication protocols considering geographical distribution.

[0041] The protocol definition unit can select the optimal protocol by referring to the past communication history of the generating AI system. For example, the protocol definition unit can select the most stable protocol from the past communication history. The protocol definition unit can also select the fastest protocol from the past communication history. Furthermore, the protocol definition unit can select the most efficient protocol from the past communication history. In this way, the protocol definition unit can select the optimal protocol based on past communication history.

[0042] The task allocation unit can analyze the past performance data of each generating AI and select the optimal task allocation method. For example, the task allocation unit can perform optimal task allocation based on the past processing speed of each generating AI. The task allocation unit can also perform highly reliable task allocation based on the past error rate of each generating AI. Furthermore, the task allocation unit can perform efficient task allocation based on the past resource usage of each generating AI. In this way, the task allocation unit can select the optimal task allocation method based on past performance data.

[0043] The task distribution unit can dynamically redistribute tasks based on the current resource status of the generating AIs. For example, the task distribution unit can redistribute tasks based on the current CPU usage of each generating AI. The task distribution unit can also redistribute tasks based on the current memory usage of each generating AI. Furthermore, the task distribution unit can redistribute tasks based on the current network bandwidth of each generating AI. This enables the task distribution unit to dynamically redistribute tasks based on the current resource status.

[0044] The task distribution unit can distribute tasks while considering the geographical distribution of the generating AI. For example, the task distribution unit can distribute tasks to geographically close generating AIs to minimize communication delays. The task distribution unit can also distribute tasks to geographically distant generating AIs to distribute the load. Furthermore, the task distribution unit can select the optimal task distribution method according to geographical conditions. This enables the task distribution unit to distribute tasks while considering geographical distribution.

[0045] The task distribution unit can subdivide tasks based on the specialization of the generative AI. For example, the task distribution unit can distribute image-related tasks to generative AIs specializing in image generation. It can also distribute text-related tasks to generative AIs specializing in text generation. Furthermore, the task distribution unit can distribute speech-related tasks to generative AIs specializing in speech generation. This enables the task distribution unit to subdivide tasks based on their specialization.

[0046] The error detection unit can optimize its error detection algorithm by referring to past error data. For example, it can improve the accuracy of the error detection algorithm based on past error data. It can also improve the speed of the error detection algorithm based on past error data. Furthermore, it can improve the efficiency of the error detection algorithm based on past error data. In this way, the error detection unit can optimize its error detection algorithm based on past error data.

[0047] The error detection unit can improve the accuracy of error detection by considering the interrelationships of the output results of the generated AI. For example, the error detection unit compares the output results of the generated AI with each other and detects an error if they do not match. The error detection unit can also analyze the interrelationships of the output results of the generated AI and detect abnormal patterns. Furthermore, the error detection unit can identify the cause of the error based on the interrelationships of the output results of the generated AI. In this way, the error detection unit improves the accuracy of error detection by considering the interrelationships of the output results of the generated AI.

[0048] The error detection unit can perform error detection while considering the geographical distribution of the generated AI. For example, the error detection unit can prioritize detecting errors in geographically close generated AI. The error detection unit can also distribute and detect errors in geographically distant generated AI. Furthermore, the error detection unit can select the optimal error detection method according to geographical conditions. This enables the error detection unit to perform error detection while considering geographical distribution.

[0049] The error detection unit can improve the accuracy of error detection by referring to relevant literature on the generating AI. For example, the error detection unit can improve the accuracy of the error detection algorithm based on relevant literature on the generating AI. The error detection unit can also improve the speed of the error detection algorithm based on relevant literature on the generating AI. Furthermore, the error detection unit can improve the efficiency of the error detection algorithm based on relevant literature on the generating AI. As a result, the error detection unit improves the accuracy of error detection by referring to relevant literature.

[0050] The content delivery department can select the optimal delivery method by referring to the user's past content usage history. For example, the content delivery department can prioritize providing content that the user has frequently used in the past. The content delivery department can also suggest highly relevant content based on the user's past usage history. Furthermore, the content delivery department can analyze the user's past usage history and select the optimal delivery method. In this way, the content delivery department can select the optimal content delivery method based on past usage history.

[0051] The content provider can customize content based on the user's current areas of interest. For example, the content provider can provide content related to topics the user is currently interested in. The content provider can also suggest content related to the user's areas of interest based on the user's current search history. Furthermore, the content provider can analyze the user's current social media activity and provide content related to their areas of interest. This enables the content provider to customize content based on the user's current areas of interest.

[0052] The content provider can deliver optimal content by considering the user's geographical location. For example, the content provider can provide information on nearby events based on the user's current location. The content provider can also provide news relevant to the user's region based on the user's geographical location. Furthermore, the content provider can deliver optimal advertisements by considering the user's geographical location. This enables the content provider to deliver optimal content while taking geographical location into account.

[0053] The content provider can analyze users' social media activity and provide relevant content. For example, the content provider can provide relevant content based on a user's social media "likes" and shares history. The content provider can also suggest content that a user's followers and friends are interested in. Furthermore, the content provider can analyze users' social media comments and posts and provide relevant content. In this way, the content provider can provide relevant content based on social media activity.

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

[0055] The AI-to-AI generation interface standardization system can further include a performance analysis unit that analyzes the historical performance data of each generation AI and selects the optimal task allocation method. For example, the performance analysis unit can optimize task allocation based on the historical processing speed of each generation AI. It can also perform highly reliable task allocation based on the historical error rate of each generation AI. Furthermore, it can perform efficient task allocation based on the historical resource usage of each generation AI. This allows the performance analysis unit to select the optimal task allocation method based on historical performance data.

[0056] The generation AI-to-generation AI interface standardization system can further include a resource management unit that dynamically redistributes tasks based on the current resource status of the generation AIs. For example, the resource management unit redistributes tasks based on the current CPU usage of each generation AI. It can also redistribute tasks based on the current memory usage of each generation AI. Furthermore, it can redistribute tasks based on the current network bandwidth of each generation AI. This enables the resource management unit to dynamically redistribute tasks based on the current resource status.

[0057] The Generative AI-to-Generative AI Interface Standardization System can further include a geographical distribution unit that distributes tasks considering the geographical distribution of the Generative AIs. The geographical distribution unit can, for example, distribute tasks to geographically close Generative AIs to minimize communication delays. It can also distribute tasks to geographically distant Generative AIs to distribute the load. Furthermore, it can select the optimal task distribution method according to geographical conditions. This enables the geographical distribution unit to distribute tasks considering geographical distribution.

[0058] The generation AI-to-generation AI interface standardization system can further include an error optimization unit that optimizes the error detection algorithm by referring to past error data. The error optimization unit can, for example, improve the accuracy of the error detection algorithm based on past error data. It can also improve the speed of the error detection algorithm based on past error data. Furthermore, it can improve the efficiency of the error detection algorithm based on past error data. Thus, the error optimization unit can optimize the error detection algorithm based on past error data.

[0059] The generation AI-to-generation AI interface standardization system may further include a relationship analysis unit that improves the accuracy of error detection by considering the interrelationships of the output results of the generation AI. The relationship analysis unit, for example, compares the output results of the generation AI with each other and detects errors when they do not match. It can also analyze the interrelationships of the output results of the generation AI and detect abnormal patterns. Furthermore, it can identify the cause of errors based on the interrelationships of the output results of the generation AI. As a result, the accuracy of error detection is improved by the relationship analysis unit considering the interrelationships of the output results of the generation AI.

[0060] The Generative AI-to-Generative AI Interface Standardization System may further include a literature reference unit that improves the accuracy of error detection by referring to relevant literature on the Generative AI. The literature reference unit can, for example, improve the accuracy of the error detection algorithm based on relevant literature on the Generative AI. It can also improve the speed of the error detection algorithm based on relevant literature on the Generative AI. Furthermore, it can improve the efficiency of the error detection algorithm based on relevant literature on the Generative AI. As a result, the literature reference unit improves the accuracy of error detection by referring to relevant literature.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The protocol definition section defines common communication protocols and data formats. For example, it can define communication protocols such as HTTP, WebSocket, and MQTT, as well as data formats such as JSON, XML, and CSV. This facilitates communication between generation AI systems and streamlines data exchange. Step 2: The task distribution unit distributes tasks according to each generating AI's area of ​​expertise, based on the protocol defined by the protocol definition unit. For example, tasks are distributed based on areas of expertise such as image generation, text generation, and speech generation, ensuring efficient use of the generating AI's resources. Step 3: The error detection unit verifies the results of the tasks assigned by the task distribution unit, detects errors, and corrects them. For example, it detects syntax errors, logic errors, data errors, etc., and multiple generating AIs cooperate to verify the results and detect errors. Step 4: The content delivery unit provides the user with the results after correcting the errors detected by the error detection unit. For example, it provides a variety of content such as text, images, videos, and audio, delivering high-quality content generated by the generation AI to the user.

[0063] (Example of form 2) The generative AI-to-generative AI interface standardization system according to an embodiment of the present invention is a mechanism for seamlessly linking different generative AI systems. This generative AI-to-generative AI interface standardization system includes a protocol definition unit that defines a common communication protocol and data format, a task distribution unit that distributes tasks according to the strengths of each generative AI, an error detection unit that verifies the results of tasks, detects and corrects errors, and a content provision unit that provides high-quality content to users. This enables the meshing of generative AIs, which is expected to lead to efficient resource utilization and improved creativity. For example, the protocol definition unit defines a common communication protocol to facilitate communication between different generative AI systems. The task distribution unit distributes tasks according to the strengths of each generative AI. The error detection unit detects errors by having multiple generative AIs cooperate to verify each other's results. The content provision unit provides users with high-quality and diverse content. As a result, users can access high-quality and diverse content and enjoy a richer experience. In addition, it reduces power consumption due to excessive GPU use and carbon dioxide (CO2) emissions from the operation of the cooling system, mitigating the problem of increasing burden on the global environment. This enables the sustainable operation of generative AI and contributes to solving environmental problems. The generative AI-to-generative AI interface standardization system allows for seamless integration of different generative AI systems, resulting in efficient resource utilization and enhanced creativity.

[0064] The generative AI-to-generative AI interface standardization system according to the embodiment comprises a protocol definition unit, a task allocation unit, an error detection unit, and a content provision unit. The protocol definition unit defines common communication protocols and data formats. The protocol definition unit can define communication protocols such as HTTP, WebSocket, and MQTT. The protocol definition unit can also define data formats such as JSON, XML, and CSV. The protocol definition unit defines common protocols to facilitate communication between generative AI systems. For example, the protocol definition unit uses standardized protocols to streamline data exchange between different generative AI systems. The task allocation unit allocates tasks according to the expertise of each generative AI. For example, the task allocation unit can allocate tasks based on areas of expertise such as image generation, text generation, and speech generation. The task allocation unit appropriately distributes tasks to efficiently utilize the resources of the generative AIs. For example, the task allocation unit distributes image-related tasks to generative AIs specialized in image generation and text-related tasks to generative AIs specialized in text generation. The error detection unit verifies the task results, detects errors, and corrects them. The error detection unit can detect errors such as syntax errors, logic errors, and data errors. The error detection unit detects errors by having multiple generative AIs cooperate to verify each other's results. For example, the error detection unit compares the output results of the generative AIs with each other and detects an error if they do not match. The content provision unit provides users with high-quality and diverse content. The content provision unit can provide diverse content such as text, images, videos, and audio. The content provision unit provides users with the results of the generative AI. For example, the content provision unit provides users with high-quality content generated by the generative AI, improving the user experience. As a result, the generative AI-to-generative AI interface standardization system according to this embodiment can seamlessly link different generative AI systems, achieving efficient resource utilization and improved creativity.

[0065] The protocol definition section defines common communication protocols and data formats. Specifically, it can define communication protocols such as HTTP, WebSocket, and MQTT. This enables smooth data communication between different generative AI systems. For example, using the HTTP protocol standardizes the exchange of requests and responses between generative AI systems, ensuring compatibility. Using WebSocket enables real-time bidirectional communication, realizing immediate data exchange between generative AI systems. Furthermore, using MQTT enables efficient messaging with low bandwidth, saving resources. Regarding data formats, JSON, XML, and CSV can also be defined. JSON is widely used because it is lightweight, easy to read, and easy to serialize and deserialize. XML has a hierarchical structure and is easy to structure data, making it suitable for representing complex data. CSV is a simple text format that can efficiently handle large amounts of data. By standardizing these communication protocols and data formats, the protocol definition section streamlines data exchange between generative AI systems and ensures compatibility. This allows different generative AI systems to work seamlessly together and exchange data smoothly.

[0066] The task distribution unit distributes tasks according to each generative AI's area of ​​expertise. Specifically, tasks can be distributed based on areas of specialization such as image generation, text generation, and speech generation. For example, an AI specializing in image generation can be assigned image-related tasks, and an AI specializing in text generation can be assigned text-related tasks. This allows for efficient use of each generative AI's resources and improves overall performance. The task distribution unit considers the characteristics and performance of each generative AI to perform optimal task distribution. For example, if an image generation AI can generate high-resolution images in a short time, high-resolution image generation tasks will be concentrated on that AI. On the other hand, if a text generation AI excels at generating natural-sounding text, text generation tasks will be concentrated on that AI. Furthermore, the task distribution unit can monitor the load on each generative AI in real time and dynamically redistribute tasks to prevent uneven load distribution. This maintains the balance of the entire system and ensures efficient resource utilization. In addition, the task distribution unit can construct an optimal task distribution algorithm based on the generative AI's training data and past performance. This maximizes the performance of each generative AI and enables the efficient generation of high-quality content.

[0067] The error detection unit verifies the task results, detects errors, and corrects them. Specifically, it can detect errors such as syntax errors, logic errors, and data errors. The error detection unit detects errors by having multiple generating AIs cooperate to verify each other's results. For example, it compares the output results of the generating AIs with each other and detects errors if they do not match. This improves the reliability of the output results of the generating AIs. The error detection unit utilizes AI-based anomaly detection algorithms to detect unusual patterns and abnormal data at an early stage. For example, it checks the grammatical and semantic consistency of generated text and detects abnormal contexts and unnatural expressions. It also evaluates the quality of generated images and detects errors if they contain noise or artifacts. Furthermore, the error detection unit can identify the type and cause of errors and propose appropriate correction methods. For example, in the case of syntax errors, it provides specific steps to correct the grammar, and in the case of logic errors, it points out areas for algorithmic correction. This enables early detection and rapid correction of errors, improving the reliability and quality of the generating AI system.

[0068] The content delivery department provides users with high-quality and diverse content. Specifically, it can provide a variety of content such as text, images, videos, and audio. The content delivery department delivers the results of generative AI to users, improving the user experience. For example, it provides users with high-quality text generated by generative AI, providing easy-to-read and engaging writing. It also provides users with high-resolution images and videos generated by generative AI, providing visually appealing content. Furthermore, it provides users with natural-sounding audio generated by generative AI, providing auditory-pleasant content. The content delivery department can select and provide the most suitable content according to the user's needs and preferences. For example, if a user is looking for text on a specific theme or style, it will generate and provide text that meets that need. Also, if a user is looking for images of a specific resolution or format, it will generate and provide images that meet those requirements. Furthermore, the content delivery department can collect feedback from users and continuously improve the performance of the generative AI and the quality of the content. This increases user satisfaction and maximizes the value of the generative AI system.

[0069] The protocol definition unit can define a common communication protocol to facilitate communication between different generative AI systems. The protocol definition unit defines communication protocols such as HTTP, WebSocket, and MQTT. The protocol definition unit uses standardized protocols to streamline data exchange between different generative AI systems. For example, the protocol definition unit can use the HTTP protocol for data communication between generative AI systems. It can also use the WebSocket protocol to achieve real-time data communication. Furthermore, the protocol definition unit can use the MQTT protocol for lightweight data communication. This enables the protocol definition unit to facilitate smooth communication between different generative AI systems.

[0070] The task distribution unit can distribute tasks according to each generating AI's area of ​​expertise. For example, the task distribution unit distributes tasks based on areas of expertise such as image generation, text generation, and speech generation. The task distribution unit appropriately distributes tasks to efficiently utilize the resources of the generating AIs. For example, the task distribution unit distributes image-related tasks to a generating AI specializing in image generation, and text-related tasks to a generating AI specializing in text generation. The task distribution unit can also distribute speech-related tasks to a generating AI specializing in speech generation. This allows the task distribution unit to distribute tasks according to each generating AI's area of ​​expertise.

[0071] The error detection unit can detect errors by having multiple generating AIs cooperate to verify each other's results. The error detection unit can detect errors such as syntax errors, logic errors, and data errors. The error detection unit compares the output results of the generating AIs with each other and detects errors if they do not match. For example, the error detection unit analyzes the interrelationships of the output results of the generating AIs and detects abnormal patterns. The error detection unit can also identify the cause of an error based on the interrelationships of the output results of the generating AIs. As a result, the accuracy of error detection is improved by having multiple generating AIs cooperate to detect errors.

[0072] The content delivery department can provide users with high-quality and diverse content. For example, it can provide a variety of content such as text, images, videos, and audio. The content delivery department also provides users with the results of generative AI. For example, it can provide users with high-quality content generated by generative AI, improving the user experience. Furthermore, the content delivery department can improve content based on user feedback. For example, it can collect user ratings and comments and use them to improve the quality of its content. This allows the content delivery department to provide users with high-quality and diverse content.

[0073] The protocol definition unit can estimate the user's emotions and adjust the protocol selection criteria based on the estimated emotions. For example, if the user is stressed, the protocol definition unit can select a simple and intuitive protocol. If the user is relaxed, the protocol definition unit can also select a protocol that allows for detailed settings. Furthermore, if the user is in a hurry, the protocol definition unit can select a protocol that enables rapid communication. This allows the protocol definition unit to select a protocol that is appropriate for the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0074] The protocol definition unit can define protocols to optimize communication speeds between different generative AI systems. For example, the protocol definition unit can monitor the communication speed of each generative AI system in real time and select the optimal protocol. If the communication speed is slow, the protocol definition unit can also define protocols that improve communication speed using data compression techniques. Furthermore, if the communication speed is fast, the protocol definition unit can define protocols that enable the transmission and reception of high-quality data. In this way, the protocol definition unit enables efficient communication by defining protocols that optimize communication speed.

[0075] The protocol definition unit can apply different communication protocols depending on the type of data. For example, it can apply a lightweight protocol to text data to improve communication speed. It can also apply a high-quality protocol to image data to prevent data loss. Furthermore, it can apply a protocol suitable for real-time streaming to video data. In this way, the protocol definition unit can apply the optimal communication protocol according to the type of data.

[0076] The protocol definition unit can estimate the user's emotions and determine protocol priorities based on those emotions. For example, if the user is tense, the protocol definition unit will prioritize protocols that prioritize stability. If the user is relaxed, the protocol definition unit may also prioritize protocols that prioritize flexibility. Furthermore, if the user is in a hurry, the protocol definition unit may prioritize protocols that prioritize speed. In this way, the protocol definition unit can determine protocol priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0077] The protocol definition unit can adjust communication protocols considering the geographical distribution of different generative AI systems. For example, the protocol definition unit can apply a protocol that minimizes latency between geographically distant generative AI systems. It can also apply a protocol that enables high-speed communication between generative AI systems within the same region. Furthermore, the protocol definition unit can define a protocol that selects the optimal communication path according to geographical conditions. This allows the protocol definition unit to adjust communication protocols considering geographical distribution.

[0078] The protocol definition unit can select the optimal protocol by referring to the past communication history of the generating AI system. For example, the protocol definition unit can select the most stable protocol from the past communication history. The protocol definition unit can also select the fastest protocol from the past communication history. Furthermore, the protocol definition unit can select the most efficient protocol from the past communication history. In this way, the protocol definition unit can select the optimal protocol based on past communication history.

[0079] The task distribution unit can estimate the user's emotions and adjust the task distribution method based on the estimated emotions. For example, if the user is stressed, the task distribution unit may adopt a simple task distribution method. If the user is relaxed, the task distribution unit may adopt a more detailed task distribution method. Furthermore, if the user is in a hurry, the task distribution unit may adopt a method that distributes tasks quickly. In this way, the task distribution unit can adjust the task distribution method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0080] The task allocation unit can analyze the past performance data of each generating AI and select the optimal task allocation method. For example, the task allocation unit can perform optimal task allocation based on the past processing speed of each generating AI. The task allocation unit can also perform highly reliable task allocation based on the past error rate of each generating AI. Furthermore, the task allocation unit can perform efficient task allocation based on the past resource usage of each generating AI. In this way, the task allocation unit can select the optimal task allocation method based on past performance data.

[0081] The task distribution unit can dynamically redistribute tasks based on the current resource status of the generating AIs. For example, the task distribution unit can redistribute tasks based on the current CPU usage of each generating AI. The task distribution unit can also redistribute tasks based on the current memory usage of each generating AI. Furthermore, the task distribution unit can redistribute tasks based on the current network bandwidth of each generating AI. This enables the task distribution unit to dynamically redistribute tasks based on the current resource status.

[0082] The task allocation unit can estimate the user's emotions and determine task priorities based on those emotions. For example, if the user is stressed, the task allocation unit will prioritize important tasks. If the user is relaxed, the task allocation unit can also set flexible task priorities. Furthermore, if the user is in a hurry, the task allocation unit can prioritize tasks that can be completed quickly. In this way, the task allocation unit can determine task priorities according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0083] The task distribution unit can distribute tasks while considering the geographical distribution of the generating AI. For example, the task distribution unit can distribute tasks to geographically close generating AIs to minimize communication delays. The task distribution unit can also distribute tasks to geographically distant generating AIs to distribute the load. Furthermore, the task distribution unit can select the optimal task distribution method according to geographical conditions. This enables the task distribution unit to distribute tasks while considering geographical distribution.

[0084] The task distribution unit can subdivide tasks based on the specialization of the generative AI. For example, the task distribution unit can distribute image-related tasks to generative AIs specializing in image generation. It can also distribute text-related tasks to generative AIs specializing in text generation. Furthermore, the task distribution unit can distribute speech-related tasks to generative AIs specializing in speech generation. This enables the task distribution unit to subdivide tasks based on their specialization.

[0085] The error detection unit can estimate the user's emotions and adjust the error detection criteria based on the estimated emotions. For example, if the user is stressed, the error detection unit can apply strict error detection criteria. If the user is relaxed, the error detection unit can also apply flexible error detection criteria. Furthermore, if the user is in a hurry, the error detection unit can apply criteria for rapid error detection. This allows the error detection unit to adjust the error detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0086] The error detection unit can optimize its error detection algorithm by referring to past error data. For example, it can improve the accuracy of the error detection algorithm based on past error data. It can also improve the speed of the error detection algorithm based on past error data. Furthermore, it can improve the efficiency of the error detection algorithm based on past error data. In this way, the error detection unit can optimize its error detection algorithm based on past error data.

[0087] The error detection unit can improve the accuracy of error detection by considering the interrelationships of the output results of the generated AI. For example, the error detection unit compares the output results of the generated AI with each other and detects an error if they do not match. The error detection unit can also analyze the interrelationships of the output results of the generated AI and detect abnormal patterns. Furthermore, the error detection unit can identify the cause of the error based on the interrelationships of the output results of the generated AI. In this way, the error detection unit improves the accuracy of error detection by considering the interrelationships of the output results of the generated AI.

[0088] The error detection unit can estimate the user's emotions and determine the priority of error detection based on the estimated emotions. For example, if the user is stressed, the error detection unit will prioritize detecting important errors. If the user is relaxed, the error detection unit can also set a flexible error detection priority. Furthermore, if the user is in a hurry, the error detection unit can prioritize errors that can be detected quickly. In this way, the error detection unit can determine the priority of error detection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0089] The error detection unit can perform error detection while considering the geographical distribution of the generated AI. For example, the error detection unit can prioritize detecting errors in geographically close generated AI. The error detection unit can also distribute and detect errors in geographically distant generated AI. Furthermore, the error detection unit can select the optimal error detection method according to geographical conditions. This enables the error detection unit to perform error detection while considering geographical distribution.

[0090] The error detection unit can improve the accuracy of error detection by referring to relevant literature on the generating AI. For example, the error detection unit can improve the accuracy of the error detection algorithm based on relevant literature on the generating AI. The error detection unit can also improve the speed of the error detection algorithm based on relevant literature on the generating AI. Furthermore, the error detection unit can improve the efficiency of the error detection algorithm based on relevant literature on the generating AI. As a result, the error detection unit improves the accuracy of error detection by referring to relevant literature.

[0091] The content provider can estimate the user's emotions and adjust the way content is delivered based on those emotions. For example, if the user is stressed, the content provider can provide simple and intuitive content. If the user is relaxed, the content provider can also provide content with detailed information. Furthermore, if the user is in a hurry, the content provider can provide content that can be accessed quickly. This allows the content provider to adjust the way content is delivered according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0092] The content delivery department can select the optimal delivery method by referring to the user's past content usage history. For example, the content delivery department can prioritize providing content that the user has frequently used in the past. The content delivery department can also suggest highly relevant content based on the user's past usage history. Furthermore, the content delivery department can analyze the user's past usage history and select the optimal delivery method. In this way, the content delivery department can select the optimal content delivery method based on past usage history.

[0093] The content provider can customize content based on the user's current areas of interest. For example, the content provider can provide content related to topics the user is currently interested in. The content provider can also suggest content related to the user's areas of interest based on the user's current search history. Furthermore, the content provider can analyze the user's current social media activity and provide content related to their areas of interest. This enables the content provider to customize content based on the user's current areas of interest.

[0094] The content provider can estimate the user's emotions and prioritize content based on those emotions. For example, if the user is stressed, the content provider can prioritize providing relaxing content. If the user is relaxed, the content provider can also prioritize providing engaging content. Furthermore, if the user is in a hurry, the content provider can prioritize providing content that can be accessed quickly. This allows the content provider to prioritize content according to the user's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0095] The content provider can deliver optimal content by considering the user's geographical location. For example, the content provider can provide information on nearby events based on the user's current location. The content provider can also provide news relevant to the user's region based on the user's geographical location. Furthermore, the content provider can deliver optimal advertisements by considering the user's geographical location. This enables the content provider to deliver optimal content while taking geographical location into account.

[0096] The content provider can analyze users' social media activity and provide relevant content. For example, the content provider can provide relevant content based on a user's social media "likes" and shares history. The content provider can also suggest content that a user's followers and friends are interested in. Furthermore, the content provider can analyze users' social media comments and posts and provide relevant content. In this way, the content provider can provide relevant content based on social media activity.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The generative AI-to-generative AI interface standardization system may further include a task adjustment unit that estimates the user's emotions and adjusts the task distribution method based on the estimated emotions. For example, if the user is stressed, the task adjustment unit may adopt a simple task distribution method. If the user is relaxed, it may adopt a more detailed task distribution method. If the user is in a hurry, it may adopt a method that distributes tasks quickly. In this way, the task adjustment unit can adjust the task distribution method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0099] The AI-to-AI generation interface standardization system can further include a performance analysis unit that analyzes the historical performance data of each generation AI and selects the optimal task allocation method. For example, the performance analysis unit can optimize task allocation based on the historical processing speed of each generation AI. It can also perform highly reliable task allocation based on the historical error rate of each generation AI. Furthermore, it can perform efficient task allocation based on the historical resource usage of each generation AI. This allows the performance analysis unit to select the optimal task allocation method based on historical performance data.

[0100] The generation AI-to-generation AI interface standardization system can further include a resource management unit that dynamically redistributes tasks based on the current resource status of the generation AIs. For example, the resource management unit redistributes tasks based on the current CPU usage of each generation AI. It can also redistribute tasks based on the current memory usage of each generation AI. Furthermore, it can redistribute tasks based on the current network bandwidth of each generation AI. This enables the resource management unit to dynamically redistribute tasks based on the current resource status.

[0101] The generative AI-to-generative AI interface standardization system may further include a task prioritization unit that estimates the user's emotions and determines task priorities based on the estimated emotions. For example, if the user is stressed, the task prioritization unit might prioritize important tasks. If the user is relaxed, it might set flexible task priorities. If the user is in a hurry, it might prioritize tasks that can be completed quickly. This allows the task prioritization unit to determine task priorities according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0102] The Generative AI-to-Generative AI Interface Standardization System can further include a geographical distribution unit that distributes tasks considering the geographical distribution of the Generative AIs. The geographical distribution unit can, for example, distribute tasks to geographically close Generative AIs to minimize communication delays. It can also distribute tasks to geographically distant Generative AIs to distribute the load. Furthermore, it can select the optimal task distribution method according to geographical conditions. This enables the geographical distribution unit to distribute tasks considering geographical distribution.

[0103] The generative AI-to-generative AI interface standardization system may further include an error criterion adjustment unit that estimates the user's emotions and adjusts the error detection criteria based on the estimated emotions. For example, the error criterion adjustment unit might apply strict error detection criteria when the user is stressed, flexible criteria when the user is relaxed, or rapid error detection criteria when the user is in a hurry. This allows the error criterion adjustment unit to adjust error detection criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0104] The generation AI-to-generation AI interface standardization system can further include an error optimization unit that optimizes the error detection algorithm by referring to past error data. The error optimization unit can, for example, improve the accuracy of the error detection algorithm based on past error data. It can also improve the speed of the error detection algorithm based on past error data. Furthermore, it can improve the efficiency of the error detection algorithm based on past error data. Thus, the error optimization unit can optimize the error detection algorithm based on past error data.

[0105] The generation AI-to-generation AI interface standardization system may further include a relationship analysis unit that improves the accuracy of error detection by considering the interrelationships of the output results of the generation AI. The relationship analysis unit, for example, compares the output results of the generation AI with each other and detects errors when they do not match. It can also analyze the interrelationships of the output results of the generation AI and detect abnormal patterns. Furthermore, it can identify the cause of errors based on the interrelationships of the output results of the generation AI. As a result, the accuracy of error detection is improved by the relationship analysis unit considering the interrelationships of the output results of the generation AI.

[0106] The generative AI-to-generative AI interface standardization system may further include an error prioritization unit that estimates the user's emotions and determines the priority of error detection based on the estimated emotions. For example, if the user is stressed, the error prioritization unit will prioritize detecting critical errors. If the user is relaxed, a flexible error detection priority can be set. If the user is in a hurry, errors that can be detected quickly can also be prioritized. This allows the error prioritization unit to determine the priority of error detection according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0107] The Generative AI-to-Generative AI Interface Standardization System may further include a literature reference unit that improves the accuracy of error detection by referring to relevant literature on the Generative AI. The literature reference unit can, for example, improve the accuracy of the error detection algorithm based on relevant literature on the Generative AI. It can also improve the speed of the error detection algorithm based on relevant literature on the Generative AI. Furthermore, it can improve the efficiency of the error detection algorithm based on relevant literature on the Generative AI. As a result, the literature reference unit improves the accuracy of error detection by referring to relevant literature.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The protocol definition section defines common communication protocols and data formats. For example, it can define communication protocols such as HTTP, WebSocket, and MQTT, as well as data formats such as JSON, XML, and CSV. This facilitates communication between generation AI systems and streamlines data exchange. Step 2: The task distribution unit distributes tasks according to each generating AI's area of ​​expertise, based on the protocol defined by the protocol definition unit. For example, tasks are distributed based on areas of expertise such as image generation, text generation, and speech generation, ensuring efficient use of the generating AI's resources. Step 3: The error detection unit verifies the results of the tasks assigned by the task distribution unit, detects errors, and corrects them. For example, it detects syntax errors, logic errors, data errors, etc., and multiple generating AIs cooperate to verify the results and detect errors. Step 4: The content delivery unit provides the user with the results after correcting the errors detected by the error detection unit. For example, it provides a variety of content such as text, images, videos, and audio, delivering high-quality content generated by the generation AI to the user.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] Each of the multiple elements described above, including the protocol definition unit, task allocation unit, error detection unit, and content provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the protocol definition unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The task allocation unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The error detection unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The content provision unit is implemented by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the protocol definition unit, task allocation unit, error detection unit, and content provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the protocol definition unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The task allocation unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The error detection unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The content provision unit is implemented by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the protocol definition unit, task allocation unit, error detection unit, and content provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the protocol definition unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The task allocation unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The error detection unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The content provision unit is implemented by the control unit 46A of the headset terminal 314 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements described above, including the protocol definition unit, task allocation unit, error detection unit, and content provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the protocol definition unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The task allocation unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The error detection unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The content provision unit is implemented by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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."

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] (Note 1) A protocol definition section that defines common communication protocols and data formats, A task distribution unit that distributes tasks according to the area of ​​expertise of each generating AI based on the protocol defined by the protocol definition unit, An error detection unit verifies the results of the tasks assigned by the task assignment unit, detects and corrects errors, The system includes a content provision unit that provides the user with the result after correcting the errors detected by the error detection unit. A system characterized by the following features. (Note 2) The protocol definition unit is, To define a common communication protocol to facilitate communication between different generative AI systems. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned task distribution unit is: Tasks are divided among the generating AIs according to their respective areas of expertise. The system described in Appendix 1, characterized by the features described herein. (Note 4) The error detection unit, Multiple generative AIs work together to verify the results and detect errors. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned content provision unit, To provide users with high-quality and diverse content. The system described in Appendix 1, characterized by the features described herein. (Note 6) The protocol definition unit is, The system estimates user sentiment and adjusts protocol selection criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 7) The protocol definition unit is, Define a protocol to optimize communication speed between different generative AI systems. The system described in Appendix 1, characterized by the features described herein. (Note 8) The protocol definition unit is, Applying different communication protocols depending on the type of data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The protocol definition unit is, It estimates the user's emotions and determines the priority of protocols based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The protocol definition unit is, Adjust communication protocols to take into account the geographical distribution of different generative AI systems. The system described in Appendix 1, characterized by the features described herein. (Note 11) The protocol definition unit is, The optimal protocol is selected by referring to the past communication history of the generation AI system. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned task distribution unit is: It estimates the user's emotions and adjusts how tasks are distributed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned task distribution unit is: Analyze the historical performance data of each generative AI to select the optimal task allocation method. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned task distribution unit is: Dynamically redistribute tasks based on the current resource status of the generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned task distribution unit is: It estimates the user's emotions and determines task priorities based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned task distribution unit is: Distribute tasks considering the geographical distribution of the generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned task distribution unit is: Break down tasks based on the expertise of the generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 18) The error detection unit, It estimates the user's emotions and adjusts the error detection criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The error detection unit, Optimize the error detection algorithm by referring to past error data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The error detection unit, Improve error detection accuracy by considering the interrelationships of the output results of the generated AI. The system described in Appendix 1, characterized by the features described herein. (Note 21) The error detection unit, The system estimates the user's emotions and determines the priority of error detection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The error detection unit, Error detection is performed considering the geographical distribution of generated AI. The system described in Appendix 1, characterized by the features described herein. (Note 23) The error detection unit, Referencing relevant literature on generative AI will improve the accuracy of error detection. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned content provision unit, We estimate user sentiment and adjust how content is delivered based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned content provision unit, The optimal delivery method is selected by referring to the user's past content usage history. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned content provision unit, Customize content based on the user's current areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned content provision unit, It estimates user sentiment and prioritizes content based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned content provision unit, We provide optimal content by taking into account the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned content provision unit, Analyze users' social media activity and provide relevant content. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0182] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A protocol definition section that defines common communication protocols and data formats, A task distribution unit that distributes tasks according to the area of ​​expertise of each generating AI based on the protocol defined by the protocol definition unit, An error detection unit verifies the results of the tasks assigned by the task assignment unit, detects and corrects errors, The system includes a content provision unit that provides the user with the result after correcting the errors detected by the error detection unit. A system characterized by the following features.

2. The protocol definition unit is, To define a common communication protocol to facilitate communication between different generative AI systems. The system according to feature 1.

3. The aforementioned task allocation unit is: Tasks are divided according to each generation AI's area of ​​expertise. The system according to feature 1.

4. The error detection unit, Multiple generating AIs work together to verify each other's results and detect errors. The system according to feature 1.

5. The aforementioned content provision unit, To provide users with high-quality and diverse content. The system according to feature 1.

6. The protocol definition unit is, The system estimates user sentiment and adjusts protocol selection criteria based on the estimated user sentiment. The system according to feature 1.

7. The protocol definition unit is, Define a protocol to optimize communication speed between different generative AI systems. The system according to feature 1.

8. The protocol definition unit is, Applying different communication protocols depending on the type of data. The system according to feature 1.

9. The protocol definition unit is, It estimates the user's emotions and determines the priority of protocols based on the estimated user emotions. The system according to feature 1.

10. The protocol definition unit is, Adjust the communication protocol considering the geographical distribution of different generative AI systems. The system according to feature 1.

Images