System

Abstract

To provide a system that efficiently performs support management and appearance management of AI models.SOLUTION: The system according to the embodiment includes a generation unit, a management unit, and an appearance unit. The generation unit creates AI models of characters or persons. The management unit performs support management and maintenance of the AI models created by the generation unit. The appearance unit manages the appearances of the AI models under support management by the management unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology does not adequately manage the upkeep, maintenance, and performance management of AI models, leaving room for improvement.

[0005] The system according to the embodiment aims to efficiently perform maintenance and performance management of AI models. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation unit, a management unit, and a performance unit. The generation unit creates an AI model of a character or person. The management unit maintains and manages the AI ​​model created by the generation unit. The performance unit manages the performance of the AI ​​model maintained by the management unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently perform maintenance and performance management of AI models. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0028] (Example 1) The AI ​​production system according to the embodiment of the present invention is a system that uses a generative AI to create various characters and people into AI, and provides production functions such as maintenance and appearance management of the AI ​​model. This AI production system uses a generative AI to create an AI model of a character or person, adjusts the AI ​​model (prompt engineering), and suppresses the input of new knowledge and the transmission of harmful information. Next, the system maintains and manages the created AI model. This includes regular updates and performance monitoring of the AI ​​model. Furthermore, the system manages the appearance of the AI ​​model to support its use in appropriate situations. For example, the system manages and adjusts schedules when the AI ​​model appears on television programs and events. This mechanism makes it possible to maintain the quality of the AI ​​model and to use it effectively. For example, the AI ​​production system uses a generative AI to create an AI model of a character or person. The generative AI learns the characteristics of the character or person and generates a realistic AI model. Next, the AI ​​production system maintains and manages the generated AI model. For example, the AI ​​model is regularly updated to reflect the latest information. The system also monitors the performance of the AI ​​model and makes adjustments as necessary. Furthermore, the AI ​​production system manages the appearance of the AI ​​model. For example, the system can manage the schedule of an AI model's appearance on a television program or event, and have it appear at the appropriate time. This allows the quality of the AI ​​model to be maintained and used effectively. This allows the AI ​​production system to efficiently create, maintain, and manage the appearance of AI models of characters and people.

[0029] The AI ​​production system according to the embodiment includes a generation unit, a management unit, and a performance unit. The generation unit creates an AI model of a character or person using a generation AI. The generation unit, for example, learns the characteristics of the character or person to generate a realistic AI model. The generation unit can reproduce the appearance, voice, and movement of the character or person using the generation AI. For example, the generation unit learns the facial expressions and tone of voice of the character to perform realistic expressions. The generation unit can also learn the movements of the character to reproduce natural movements. The management unit maintains and manages the AI ​​model created by the generation unit. For example, the management unit periodically updates the AI ​​model to reflect the latest information. The management unit can also monitor the performance of the AI ​​model and make adjustments as necessary. For example, the management unit monitors the operating speed and responsiveness of the AI ​​model to maintain it in an optimal state. Furthermore, the management unit can take measures to ensure the security of the AI ​​model. For example, the management unit sets a security policy to prevent unauthorized access to the AI ​​model. The performance unit manages the performance of the AI ​​model maintained and managed by the management unit. The performance unit, for example, manages the schedule of the AI ​​model's appearance on a television program or event, and allows the AI ​​model to appear at an appropriate time. The performance unit can efficiently manage the appearance schedule of the AI ​​model and avoid overlaps and conflicts. For example, the performance unit manages the appearance schedule of the AI ​​model in a calendar app and sets reminders. The performance unit can also set appearance conditions for the AI ​​model and support its use in appropriate situations. For example, the performance unit allows the AI ​​model to appear only if it meets certain conditions. As a result, the AI ​​production system according to the embodiment can efficiently create, maintain, and manage the appearance of AI models of characters and people.

[0030] The generation unit uses the generation AI to create an AI model of a character or person. For example, the generation unit learns the characteristics of a character or person and generates a realistic AI model. Specifically, the generation AI uses a large amount of image data and voice data to learn the characteristics of the character or person, such as their appearance, voice, and movements, in detail. For example, when learning the facial expressions of a character, various expression data such as smiles, anger, and sadness are collected, and the generation AI realistically reproduces changes in expression based on them. In addition, when learning the tone of voice, voice changes according to different emotions and situations are analyzed to realize natural vocalization. Furthermore, in learning movements, human movements are recorded in detail using motion capture technology, and the generation AI reproduces natural movements based on that data. For example, it can handle a wide range of movements, from basic movements such as walking, running, and hand movements to dance and sports movements. The generation unit generates realistic and natural AI models of characters and people based on these learning data, and can provide users with a high-quality experience. Furthermore, the generation unit can continuously improve the algorithm of the generation AI to create an AI model with higher expressiveness. For example, by using deep learning technology, it is possible to reproduce more complex facial expressions and movements, thereby meeting user expectations.

[0031] The management unit maintains and manages the AI ​​model created by the generation unit. For example, the management unit periodically updates the AI ​​model to reflect the latest information. Specifically, the management unit periodically updates the learning data of the AI ​​model and incorporates new data to improve the accuracy and expressiveness of the AI ​​model. The management unit can also monitor the performance of the AI ​​model and make adjustments as necessary. For example, the management unit monitors the operating speed and responsiveness of the AI ​​model, and upgrades the hardware and optimizes the software to maintain the optimal state. Furthermore, the management unit can take measures to ensure the security of the AI ​​model. For example, the management unit sets a security policy to prevent unauthorized access to the AI ​​model, and implements access control and data encryption. In addition, the management unit can monitor the operation log of the AI ​​model, and respond quickly if abnormal operation or unauthorized access is detected. This allows the management unit to ensure the reliability and safety of the AI ​​model and provide an environment in which users can use it with peace of mind. Furthermore, the management unit can collect feedback from users and use it to improve the AI ​​model. For example, if a user has dissatisfaction or requests regarding the operation of the AI ​​model, the management unit adjusts and improves the AI ​​model based on that feedback. This allows the management department to constantly update with the latest information and technology and maintain the quality of the AI ​​model.

[0032] The performance department manages the appearance of the AI ​​model maintained and managed by the management department. For example, the performance department manages the schedule when the AI ​​model appears on a TV program or event, and allows the AI ​​model to appear at the appropriate time. Specifically, the performance department manages the appearance schedule of the AI ​​model in a calendar app and sets reminders to avoid overlaps and conflicts. The performance department can also set the appearance conditions of the AI ​​model and support its use in appropriate situations. For example, by allowing the AI ​​model to appear only when it meets certain conditions, it provides a high-quality performance. In addition, the performance department can collect feedback on the appearance of the AI ​​model and use it for the next appearance. For example, based on the reactions from viewers and event participants, it adjusts the expression and behavior of the AI ​​model to achieve a better performance. In addition, the performance department also provides technical support for the appearance of the AI ​​model. For example, it prepares the hardware and software required for the AI ​​model to appear, and supports smooth appearances. As a result, the performance department can efficiently manage the appearance of the AI ​​model and provide a high-quality experience to the user. In addition, the performance department can analyze data on the appearance of the AI ​​model and use it to plan future appearances. For example, based on past performance data, the popularity and effectiveness of the AI ​​model can be evaluated and the next performance schedule can be optimized. This allows the performance department to effectively manage the AI ​​model's performance and meet user expectations.

[0033] The generation unit includes an adjustment unit that performs prompt engineering. The adjustment unit performs prompt engineering using the generation AI. Prompt engineering is a technology that designs and adjusts a prompt for the generation AI to generate an appropriate response. For example, the adjustment unit sets a prompt such as "Please explain the characteristics of this character" for the generation AI and adjusts it so that the generation AI generates an appropriate response. The adjustment unit can also evaluate the quality of the response generated by the generation AI and modify the prompt as necessary. For example, the adjustment unit evaluates the accuracy and consistency of the response generated by the generation AI and optimizes the prompt. Furthermore, the adjustment unit can design a prompt when the generation AI learns new information. For example, the adjustment unit sets a prompt such as "Please summarize the latest news" for the generation AI and adjusts it so that the generation AI learns the latest information. This allows the adjustment unit to design and adjust a prompt for the generation AI to generate an appropriate response. This improves the accuracy of the AI ​​model through prompt engineering.

[0034] The generation unit includes an input unit that inputs new knowledge. The input unit inputs new knowledge using the generation AI. The input of new knowledge is a technology that allows the generation AI to learn the latest information and reflect it in the AI ​​model. For example, the input unit sets a prompt to the generation AI, "Please learn the latest news," and adjusts the generation AI to learn the latest news. The input unit can also design a prompt when the generation AI takes in external information. For example, the input unit sets a prompt to the generation AI, "Please obtain information from this database," and adjusts the generation AI to take in external information. Furthermore, the input unit can also design a prompt when the generation AI uses a learning algorithm. For example, the input unit sets a prompt to the generation AI, "Please analyze data using this algorithm," and adjusts the generation AI to use the learning algorithm. This allows the input unit to allow the generation AI to learn the latest information and reflect it in the AI ​​model. This allows the AI ​​model to reflect the latest information by inputting new knowledge.

[0035] The generation unit includes a suppression unit that suppresses the transmission of harmful information. The suppression unit suppresses the transmission of harmful information using the generation AI. The suppression of the transmission of harmful information is a technology that prevents the generation AI from generating inappropriate information. For example, the suppression unit sets a prompt for the generation AI, "Do not use inappropriate words," and adjusts the generation AI so that it does not generate inappropriate information. The suppression unit can also evaluate the quality of the information generated by the generation AI and apply filtering technology as necessary. For example, the suppression unit analyzes the content of the information generated by the generation AI and filters out inappropriate information. Furthermore, the suppression unit can adjust the generation AI to comply with the moderation policy. For example, the suppression unit sets a prompt for the generation AI, "Please generate information in accordance with this policy," and adjusts the generation AI to comply with the moderation policy. This allows the suppression unit to adjust the generation AI so that it does not generate inappropriate information. This improves the reliability of the AI ​​model by suppressing the transmission of harmful information.

[0036] The management unit includes an update unit that performs regular updates. The update unit performs regular updates using the generation AI. Regular updates are a necessary technique for maintaining the performance of the AI ​​model. For example, the update unit sets a prompt for the generation AI, "Please learn the latest data every month," and adjusts the generation AI to regularly learn the latest data. The update unit can also design a prompt when the generation AI applies a security patch. For example, the update unit sets a prompt for the generation AI, "Please apply this security patch," and adjusts the generation AI to apply the security patch. The update unit can also design a prompt when the generation AI adds a new function. For example, the update unit sets a prompt for the generation AI, "Please add this new function," and adjusts the generation AI to add the new function. This allows the generation AI to regularly learn the latest data, apply security patches, and add new functions. This allows the performance of the AI ​​model to be maintained by regular updates.

[0037] The management unit includes a monitoring unit that monitors performance. The monitoring unit monitors performance using the generation AI. Performance monitoring is a necessary technique for maintaining an optimal state of the AI ​​model. For example, the monitoring unit sets a prompt for the generation AI, "Please monitor the operating speed of the AI ​​model," and adjusts the generation AI to monitor the operating speed of the AI ​​model. The monitoring unit can also design a prompt for the generation AI when setting performance metrics. For example, the monitoring unit sets a prompt for the generation AI, "Please evaluate performance based on this metric," and adjusts the generation AI to set performance metrics. Furthermore, the monitoring unit can also design a prompt for the generation AI when introducing an alert system. For example, the monitoring unit sets a prompt for the generation AI, "Please generate an alert when this condition is met," and adjusts the generation AI to introduce the alert system. This allows the monitoring unit to allow the generation AI to monitor the operating speed of the AI ​​model, set performance metrics, and introduce the alert system. This allows the AI ​​model to be maintained in an optimal state by performance monitoring.

[0038] The appearance department can manage the schedule when the AI ​​model appears on a television program or event. The appearance department uses the generation AI to manage the schedule when the AI ​​model appears on a television program or event. Schedule management is a technique for efficiently managing the appearance schedule of the AI ​​model and avoiding overlaps and conflicts. For example, the appearance department sets a prompt for the generation AI, "Please manage this schedule," and adjusts the generation AI to manage the schedule. The appearance department can also design a prompt when the generation AI uses a calendar app. For example, the appearance department sets a prompt for the generation AI, "Please use this calendar app to manage your schedule," and adjusts the generation AI to use the calendar app. Furthermore, the appearance department can design a prompt when the generation AI sets a reminder. For example, the appearance department sets a prompt for the generation AI, "Please set this reminder," and adjusts the generation AI to set a reminder. This allows the appearance department to efficiently manage the appearance schedule of the AI ​​model and avoid overlaps and conflicts. This allows the appearance schedule of the AI ​​model to be efficiently managed.

[0039] The generation unit can analyze the past behavior history of the character or person at the time of generation and select the optimal generation method. The generation unit uses the generation AI to analyze the past behavior history of the character or person at the time of generation and select the optimal generation method. Analysis of past behavior history is a technology in which the generation AI learns the past behavior of the character or person and selects the optimal generation method based on that behavior. For example, the generation unit sets a prompt to the generation AI saying "Please analyze the past behavior history of this character" and adjusts the generation AI so that it analyzes the past behavior history. The generation unit can also design a prompt when the generation AI extracts a behavior pattern. For example, the generation unit sets a prompt to the generation AI saying "Please extract this behavior pattern" and adjusts the generation AI so that it extracts a behavior pattern. Furthermore, the generation unit can design a prompt when the generation AI analyzes past utterances. For example, the generation unit sets a prompt to the generation AI saying "Please analyze the past utterances of this character" and adjusts the generation AI so that it analyzes past utterances. This allows the generation unit to analyze the past behavior history of the character or person and select the optimal generation method based on that behavior. This allows for the generation of consistent AI models by selecting a generation method based on past behavioral history.

[0040] The generation unit can customize the generation algorithm based on the attribute information of the character or person at the time of generation. The generation unit customizes the generation algorithm based on the attribute information of the character or person at the time of generation using the generation AI. Customization of the generation algorithm based on attribute information is a technology in which the generation AI learns the attribute information of the character or person and optimizes the generation algorithm based on the information. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the age and gender of this character," and adjusts the generation AI to customize the generation algorithm based on the attribute information. The generation unit can also design a prompt when the generation AI customizes the generation algorithm based on the occupation or hobby. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the occupation and hobby of this character," and adjusts the generation AI to customize the generation algorithm based on the occupation and hobby. Furthermore, the generation unit can also design a prompt when the generation AI customizes the generation algorithm based on the cultural background. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the cultural background of this character," and adjusts the generation AI to customize the generation algorithm based on the cultural background. This allows the generation AI to learn the attribute information of characters and people, and optimize the generation algorithm based on that information. This allows the generation algorithm to be customized based on attribute information, generating a more appropriate AI model.

[0041] The generation unit can adjust the AI ​​model to be generated by taking into account the geographical background of the character or person at the time of generation. The generation unit adjusts the AI ​​model to be generated by taking into account the geographical background of the character or person at the time of generation using the generation AI. Consideration of the geographical background is a technology in which the generation AI learns the geographical background of the character or person and adjusts the AI ​​model to be generated based on that background. For example, the generation unit sets a prompt for the generation AI, "If this character lives in an urban area, please generate it with urban scenery and sounds as the background," and adjusts the generation AI to generate it by taking into account the geographical background. The generation unit can also design a prompt when the generation AI generates a character living in a rural area. For example, the generation unit sets a prompt for the generation AI, "If this character lives in a rural area, please generate it with natural scenery and sounds as the background," and adjusts the generation AI to generate it by taking into account the rural background. Furthermore, the generation unit can design a prompt when the generation AI generates a character living in a specific country or region. For example, the generation unit sets a prompt to the generation AI saying, "If this character lives in a specific country or region, please reflect the culture and customs of that region," and adjusts the generation AI to generate the character taking into account the background of the specific region. This allows the generation unit to adjust the AI ​​model that the generation AI generates based on the geographical background of the character or person. This generates a more realistic AI model by taking the geographical background into account.

[0042] The generation unit can analyze the social media activities of the character or person at the time of generation and reflect related information in the AI ​​model to be generated. The generation unit uses the generation AI to analyze the social media activities of the character or person at the time of generation and reflects related information in the AI ​​model to be generated. Analysis of social media activities is a technology in which the generation AI learns the social media activities of the character or person and reflects related information in the AI ​​model to be generated based on the activities. For example, the generation unit sets a prompt for the generation AI, "Please analyze the social media activities of this character," and adjusts the generation AI to analyze social media activities. The generation unit can also design a prompt when the generation AI incorporates comments on social media. For example, the generation unit sets a prompt for the generation AI, "Please incorporate words and phrases that this character frequently uses on social media," and adjusts the generation AI to incorporate comments on social media. Furthermore, the generation unit can also design a prompt when the generation AI reflects popular topics on social media. For example, the generation unit sets a prompt for the generation AI, "Please reflect popular topics on social media for this character," and adjusts the generation AI to reflect popular topics. This allows the generation unit to have the generation AI learn the social media activities of characters and people and reflect related information in the AI ​​model it generates based on those activities, thereby generating a more realistic AI model by reflecting social media activities.

[0043] The management unit can analyze the past performance data of the AI ​​model at the time of management and select the optimal management method. The management unit uses the generation AI to analyze the past performance data of the AI ​​model at the time of management and select the optimal management method. The analysis of past performance data is a technology in which the generation AI learns the past performance of the AI ​​model and selects the optimal management method based on the data. For example, the management unit sets a prompt for the generation AI, "Please analyze the past performance data of this AI model," and adjusts the generation AI to analyze the past performance data. The management unit can also design a prompt when the generation AI evaluates performance metrics. For example, the management unit sets a prompt for the generation AI, "Please evaluate based on this performance metric," and adjusts the generation AI to evaluate the performance metric. Furthermore, the management unit can design a prompt when the generation AI analyzes log data. For example, the management unit sets a prompt for the generation AI, "Please analyze this log data," and adjusts the generation AI to analyze the log data. This allows the management unit to analyze the past performance data of the AI ​​model and select the optimal management method based on the data. This optimizes the management of AI models by selecting management methods based on past performance data.

[0044] The management unit can customize the management algorithm based on the attribute information of the AI ​​model at the time of management. The management unit customizes the management algorithm based on the attribute information of the AI ​​model at the time of management using the generation AI. Customization of the management algorithm based on attribute information is a technology in which the generation AI learns the attribute information of the AI ​​model and optimizes the management algorithm based on the information. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the age and gender of this AI model," and adjusts the generation AI to customize the management algorithm based on the attribute information. The management unit can also design a prompt when the generation AI customizes the management algorithm based on the usage environment. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the usage environment of this AI model," and adjusts the generation AI to customize the management algorithm based on the usage environment. Furthermore, the management unit can also design a prompt when the generation AI customizes the management algorithm based on a specific function. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on a specific function of this AI model," and adjusts the generation AI to customize the management algorithm based on the specific function. This allows the management unit to have the generating AI learn attribute information of the AI ​​model and optimize the management algorithm based on that information. This optimizes the management of the AI ​​model by customizing the management algorithm based on the attribute information.

[0045] The management unit can adjust the management method by taking into account the geographical background of the AI ​​model during management. The management unit adjusts the management method by taking into account the geographical background of the AI ​​model during management using the generation AI. Consideration of the geographical background is a technique in which the generation AI learns the geographical background of the AI ​​model and adjusts the management method based on the background. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in an urban area, please select a management method that addresses issues specific to the city," and adjusts the generation AI to adjust the management method by taking into account the geographical background. The management unit can also design a prompt when the generation AI manages an AI model used in a rural area. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in a rural area, please select a management method that addresses issues specific to the rural area," and adjusts the generation AI to adjust the management method by taking into account the rural background. Furthermore, the management unit can design a prompt when the generation AI manages an AI model used in a specific country or region. For example, the management department sets a prompt for the generating AI that says, "If this AI model is to be used in a specific country or region, please select a management method suited to the characteristics of that region," and adjusts the generating AI to adjust the management method taking into account the background of the specific region. This allows the management department to make the generating AI learn the geographical background of the AI ​​model and adjust the management method based on that background. This maintains a more realistic AI model through management that takes the geographical background into account.

[0046] The management department can analyze the social media activity of the AI ​​model at the time of management and reflect related information in management. The management department uses the generation AI to analyze the social media activity of the AI ​​model at the time of management and reflect related information in management. Analysis of social media activity is a technology in which the generation AI learns the social media activity of the AI ​​model and reflects information related to management based on the activity. For example, the management department sets a prompt for the generation AI, "Please analyze the social media activity of this AI model," and adjusts the generation AI to analyze social media activity. The management department can also design a prompt when the generation AI incorporates a statement on social media. For example, the management department sets a prompt for the generation AI, "Please incorporate the social media statement of this AI model," and adjusts the generation AI to incorporate a statement on social media. Furthermore, the management department can also design a prompt when the generation AI considers the reaction of followers on social media. For example, the management department sets a prompt for the generation AI, "Please consider the reaction of followers on social media of this AI model," and adjusts the generation AI to consider the reaction of followers. This allows the management department to allow the generation AI to learn the social media activity of the AI ​​model and reflect information related to management based on the activity. This maintains a more realistic AI model by reflecting social media activity.

[0047] The performance department can analyze the past performance history of the AI ​​model at the time of appearance and select the optimal performance method. The performance department uses the generation AI to analyze the past performance history of the AI ​​model at the time of appearance and select the optimal performance method. Analysis of past performance history is a technology in which the generation AI learns the past performance history of the AI ​​model and selects the optimal performance method based on that history. For example, the performance department sets a prompt for the generation AI, "Please analyze the past performance history of this AI model," and adjusts the generation AI to analyze the past performance history. The performance department can also design a prompt when the generation AI sets an appearance schedule. For example, the performance department sets a prompt for the generation AI, "Please set this appearance schedule," and adjusts the generation AI to set an appearance schedule. Furthermore, the performance department can also design a prompt when the generation AI identifies and improves a specific problem. For example, the performance department sets a prompt for the generation AI, "Please identify and improve this problem," and adjusts the generation AI to identify and improve a specific problem. This allows the performance department to analyze the past performance history of the AI ​​model and select the optimal performance method based on that history. This optimizes the AI ​​model's performance by selecting the performance method based on past performance history.

[0048] The performance unit can customize the performance algorithm based on the attribute information of the AI ​​model at the time of performance. The performance unit uses the generation AI to customize the performance algorithm based on the attribute information of the AI ​​model at the time of performance. Customization of the performance algorithm based on attribute information is a technology in which the generation AI learns the attribute information of the AI ​​model and optimizes the performance algorithm based on the information. For example, the performance unit sets a prompt for the generation AI, "Please customize the performance algorithm based on the age and gender of this AI model," and adjusts the generation AI to customize the performance algorithm based on the attribute information. The performance unit can also design a prompt when the generation AI customizes the performance algorithm based on the usage environment. For example, the performance unit sets a prompt for the generation AI, "Please customize the performance algorithm based on the usage environment of this AI model," and adjusts the generation AI to customize the performance algorithm based on the usage environment. In addition, the performance unit can also design a prompt when the generation AI customizes the performance algorithm based on a specific function. For example, the performance unit sets a prompt for the generation AI, "Please customize the performance algorithm based on a specific function of this AI model," and adjusts the generation AI to customize the performance algorithm based on the specific function. This allows the generation AI to learn the attribute information of the AI ​​model, and optimize the performance algorithm based on that information. This optimizes the performance of the AI ​​model by customizing the performance algorithm based on the attribute information.

[0049] The performance unit can adjust the appearance method by taking into account the geographical background of the AI ​​model when performing. The performance unit adjusts the appearance method by taking into account the geographical background of the AI ​​model when performing using the generation AI. Consideration of the geographical background is a technique in which the generation AI learns the geographical background of the AI ​​model and adjusts the appearance method based on that background. For example, the performance unit sets a prompt for the generation AI, "If this AI model is used in an urban area, please select an appearance method that addresses issues specific to the city," and adjusts the generation AI to adjust the appearance method by taking into account the geographical background. The performance unit can also design a prompt when the generation AI performs an AI model to be used in a rural area. For example, the performance unit sets a prompt for the generation AI, "If this AI model is used in a rural area, please select an appearance method that addresses issues specific to the rural area," and adjusts the generation AI to adjust the appearance method by taking into account the rural background. Furthermore, the performance unit can design a prompt when the generation AI performs an AI model to be used in a specific country or region. For example, the performance department sets a prompt for the generation AI that says, "If this AI model is used in a specific country or region, please select a performance method that suits the characteristics of that region," and adjusts the generation AI to adjust the performance method taking into account the background of the specific region. This allows the performance department to make the generation AI learn the geographical background of the AI ​​model and adjust the performance method based on that background. This allows a more realistic AI model to perform by taking the geographical background into account.

[0050] The performance department can analyze the social media activity of the AI ​​model at the time of the appearance and reflect the related information in the appearance. The performance department uses the generation AI to analyze the social media activity of the AI ​​model at the time of the appearance and reflect the related information in the appearance. The analysis of social media activity is a technology in which the generation AI learns the social media activity of the AI ​​model and reflects information related to the appearance based on the activity. For example, the performance department sets a prompt for the generation AI, "Please analyze the social media activity of this AI model," and adjusts the generation AI to analyze the social media activity. The performance department can also design a prompt when the generation AI incorporates a statement on social media. For example, the performance department sets a prompt for the generation AI, "Please incorporate the social media statement of this AI model," and adjusts the generation AI to incorporate the statement on social media. Furthermore, the performance department can also design a prompt when the generation AI considers the reaction of followers on social media. For example, the performance department sets a prompt for the generation AI, "Please consider the reaction of followers on social media of this AI model," and adjusts the generation AI to consider the reaction of followers. In this way, the performance department can make the generation AI learn the social media activity of the AI ​​model and reflect information related to the appearance based on the activity. This allows for a more realistic AI model to appear that reflects social media activity.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The generation unit can analyze the past behavior history of a character or person at the time of generation and select the optimal generation method. For example, the generation unit sets a prompt for the generation AI, "Please analyze the past behavior history of this character," and adjusts the generation AI to analyze the past behavior history. The generation unit can also design a prompt when the generation AI extracts a behavior pattern. For example, the generation unit sets a prompt for the generation AI, "Please extract this behavior pattern," and adjusts the generation AI to extract a behavior pattern. The generation unit can also design a prompt when the generation AI analyzes past utterances. For example, the generation unit sets a prompt for the generation AI, "Please analyze the past utterances of this character," and adjusts the generation AI to analyze past utterances. This allows the generation unit to analyze the past behavior history of a character or person and select the optimal generation method based on that behavior. As a result, a consistent AI model is generated by selecting a generation method based on the past behavior history.

[0053] The generation unit can customize the generation algorithm based on the attribute information of the character or person at the time of generation. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the age and gender of this character," and adjusts the generation AI to customize the generation algorithm based on the attribute information. The generation unit can also design a prompt when the generation AI customizes the generation algorithm based on an occupation or hobby. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the occupation and hobby," and adjusts the generation AI to customize the generation algorithm based on the occupation and hobby. Furthermore, the generation unit can design a prompt when the generation AI customizes the generation algorithm based on a cultural background. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the cultural background of this character," and adjusts the generation AI to customize the generation algorithm based on the cultural background. This allows the generation unit to allow the generation AI to learn the attribute information of the character or person and optimize the generation algorithm based on that information. This allows a more appropriate AI model to be generated by customizing the generation algorithm based on the attribute information.

[0054] The generation unit can adjust the AI ​​model to be generated by taking into account the geographical background of the character or person at the time of generation. For example, the generation unit sets a prompt for the generation AI, "If this character lives in an urban area, please generate it with urban scenery and sounds in the background," and adjusts the generation AI to generate it by taking into account the geographical background. The generation unit can also design a prompt when the generation AI generates a character living in a rural area. For example, the generation unit sets a prompt for the generation AI, "If this character lives in a rural area, please generate it with natural scenery and sounds in the background," and adjusts the generation AI to generate it by taking into account the rural background. The generation unit can also design a prompt when the generation AI generates a character living in a specific country or region. For example, the generation unit sets a prompt for the generation AI, "If this character lives in a specific country or region, please reflect the culture and customs of that region," and adjusts the generation AI to generate it by taking into account the background of the specific region. This allows the generation unit to learn the geographical background of the character or person and adjust the AI ​​model to be generated based on that background. This generates a more realistic AI model by taking the geographical background into account.

[0055] During management, the management unit can analyze past performance data of the AI ​​model and select an optimal management method. For example, the management unit sets a prompt for the generation AI, "Analyze the past performance data of this AI model," and adjusts the generation AI to analyze the past performance data. The management unit can also design a prompt for the generation AI to evaluate performance metrics. For example, the management unit sets a prompt for the generation AI, "Evaluate based on this performance metric," and adjusts the generation AI to evaluate the performance metric. The management unit can also design a prompt for the generation AI to analyze log data. For example, the management unit sets a prompt for the generation AI, "Analyze this log data," and adjusts the generation AI to analyze the log data. This allows the management unit to allow the generation AI to analyze past performance data of the AI ​​model and select an optimal management method based on the data. This optimizes the management of the AI ​​model by selecting a management method based on past performance data.

[0056] The management unit can customize the management algorithm based on the attribute information of the AI ​​model during management. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the age and gender of this AI model," and adjusts the generation AI to customize the management algorithm based on the attribute information. The management unit can also design a prompt when the generation AI customizes the management algorithm based on the usage environment. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the usage environment of this AI model," and adjusts the generation AI to customize the management algorithm based on the usage environment. Furthermore, the management unit can also design a prompt when the generation AI customizes the management algorithm based on a specific function. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on a specific function of this AI model," and adjusts the generation AI to customize the management algorithm based on the specific function. This allows the management unit to allow the generation AI to learn the attribute information of the AI ​​model and optimize the management algorithm based on that information. This optimizes the management of the AI ​​model by customizing the management algorithm based on the attribute information.

[0057] The management unit can adjust the management method by taking into account the geographical background of the AI ​​model during management. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in an urban area, please select a management method that addresses issues specific to the city," and adjusts the generation AI to adjust the management method by taking into account the geographical background. The management unit can also design a prompt when the generation AI manages an AI model to be used in a rural area. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in a rural area, please select a management method that addresses issues specific to the rural area," and adjusts the generation AI to adjust the management method by taking into account the background of the rural area. Furthermore, the management unit can also design a prompt when the generation AI manages an AI model to be used in a specific country or region. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in a specific country or region, please select a management method that addresses the characteristics of the region," and adjusts the generation AI to adjust the management method by taking into account the background of the specific region. This allows the management unit to allow the generation AI to learn the geographical background of the AI ​​model and adjust the management method based on that background. As a result, a more realistic AI model is maintained by management that takes into account the geographical background.

[0058] The process flow of the first embodiment will be briefly described below.

[0059] Step 1: The generation unit uses generative AI to create an AI model of a character or person. The generation unit learns the characteristics of the character or person and generates a realistic AI model. The generation unit can reproduce the appearance, voice, and movements of the character or person. For example, the generation unit learns the character's facial expressions and tone of voice to produce realistic expressions. The generation unit can also learn the character's movements and reproduce natural movements. Step 2: The management department maintains and manages the AI ​​model created by the generation department. The management department regularly updates the AI ​​model to reflect the latest information. The management department also monitors the performance of the AI ​​model and makes adjustments as necessary. For example, the management department monitors the operating speed and responsiveness of the AI ​​model to maintain it in an optimal state. Furthermore, the management department takes measures to ensure the security of the AI ​​model. For example, the management department sets security policies to prevent unauthorized access to the AI ​​model. Step 3: The Performance Department manages the appearances of the AI ​​model maintained by the Management Department. The Performance Department manages the schedule of the AI ​​model's appearances on TV programs and events, and allows it to appear at the appropriate time. The Performance Department can efficiently manage the appearance schedule of the AI ​​model and avoid overlaps and conflicts. For example, the Performance Department manages the appearance schedule of the AI ​​model in a calendar app and sets reminders. The Performance Department also sets the appearance conditions for the AI ​​model and supports its use in appropriate situations. For example, the Performance Department allows the AI ​​model to appear only if it meets certain conditions.

[0060] (Example 2) The AI ​​production system according to the embodiment of the present invention is a system that uses a generative AI to create various characters and people into AI, and provides production functions such as maintenance and appearance management of the AI ​​model. This AI production system uses a generative AI to create an AI model of a character or person, adjusts the AI ​​model (prompt engineering), and suppresses the input of new knowledge and the transmission of harmful information. Next, the system maintains and manages the created AI model. This includes regular updates and performance monitoring of the AI ​​model. Furthermore, the system manages the appearance of the AI ​​model to support its use in appropriate situations. For example, the system manages and adjusts schedules when the AI ​​model appears on television programs and events. This mechanism makes it possible to maintain the quality of the AI ​​model and to use it effectively. For example, the AI ​​production system uses a generative AI to create an AI model of a character or person. The generative AI learns the characteristics of the character or person and generates a realistic AI model. Next, the AI ​​production system maintains and manages the generated AI model. For example, the AI ​​model is regularly updated to reflect the latest information. The system also monitors the performance of the AI ​​model and makes adjustments as necessary. Furthermore, the AI ​​production system manages the appearance of the AI ​​model. For example, the system can manage the schedule of an AI model's appearance on a television program or event, and have it appear at the appropriate time. This allows the quality of the AI ​​model to be maintained and used effectively. This allows the AI ​​production system to efficiently create, maintain, and manage the appearance of AI models of characters and people.

[0061] The AI ​​production system according to the embodiment includes a generation unit, a management unit, and a performance unit. The generation unit creates an AI model of a character or person using a generation AI. The generation unit, for example, learns the characteristics of the character or person to generate a realistic AI model. The generation unit can reproduce the appearance, voice, and movement of the character or person using the generation AI. For example, the generation unit learns the facial expressions and tone of voice of the character to perform realistic expressions. The generation unit can also learn the movements of the character to reproduce natural movements. The management unit maintains and manages the AI ​​model created by the generation unit. For example, the management unit periodically updates the AI ​​model to reflect the latest information. The management unit can also monitor the performance of the AI ​​model and make adjustments as necessary. For example, the management unit monitors the operating speed and responsiveness of the AI ​​model to maintain it in an optimal state. Furthermore, the management unit can take measures to ensure the security of the AI ​​model. For example, the management unit sets a security policy to prevent unauthorized access to the AI ​​model. The performance unit manages the performance of the AI ​​model maintained and managed by the management unit. The performance unit, for example, manages the schedule of the AI ​​model's appearance on a television program or event, and allows the AI ​​model to appear at an appropriate time. The performance unit can efficiently manage the appearance schedule of the AI ​​model and avoid overlaps and conflicts. For example, the performance unit manages the appearance schedule of the AI ​​model in a calendar app and sets reminders. The performance unit can also set appearance conditions for the AI ​​model and support its use in appropriate situations. For example, the performance unit allows the AI ​​model to appear only if it meets certain conditions. As a result, the AI ​​production system according to the embodiment can efficiently create, maintain, and manage the appearance of AI models of characters and people.

[0062] The generation unit uses the generation AI to create an AI model of a character or person. For example, the generation unit learns the characteristics of a character or person and generates a realistic AI model. Specifically, the generation AI uses a large amount of image data and voice data to learn the characteristics of the character or person, such as their appearance, voice, and movements, in detail. For example, when learning the facial expressions of a character, various expression data such as smiles, anger, and sadness are collected, and the generation AI realistically reproduces changes in expression based on them. In addition, when learning the tone of voice, voice changes according to different emotions and situations are analyzed to realize natural vocalization. Furthermore, in learning movements, human movements are recorded in detail using motion capture technology, and the generation AI reproduces natural movements based on that data. For example, it can handle a wide range of movements, from basic movements such as walking, running, and hand movements to dance and sports movements. The generation unit generates realistic and natural AI models of characters and people based on these learning data, and can provide users with a high-quality experience. Furthermore, the generation unit can continuously improve the algorithm of the generation AI to create an AI model with higher expressiveness. For example, by using deep learning technology, it is possible to reproduce more complex facial expressions and movements, thereby meeting user expectations.

[0063] The management unit maintains and manages the AI ​​model created by the generation unit. For example, the management unit periodically updates the AI ​​model to reflect the latest information. Specifically, the management unit periodically updates the learning data of the AI ​​model and incorporates new data to improve the accuracy and expressiveness of the AI ​​model. The management unit can also monitor the performance of the AI ​​model and make adjustments as necessary. For example, the management unit monitors the operating speed and responsiveness of the AI ​​model, and upgrades the hardware and optimizes the software to maintain the optimal state. Furthermore, the management unit can take measures to ensure the security of the AI ​​model. For example, the management unit sets a security policy to prevent unauthorized access to the AI ​​model, and implements access control and data encryption. In addition, the management unit can monitor the operation log of the AI ​​model, and respond quickly if abnormal operation or unauthorized access is detected. This allows the management unit to ensure the reliability and safety of the AI ​​model and provide an environment in which users can use it with peace of mind. Furthermore, the management unit can collect feedback from users and use it to improve the AI ​​model. For example, if a user has dissatisfaction or requests regarding the operation of the AI ​​model, the management unit adjusts and improves the AI ​​model based on that feedback. This allows the management department to constantly update with the latest information and technology and maintain the quality of the AI ​​model.

[0064] The performance department manages the appearance of the AI ​​model maintained and managed by the management department. For example, the performance department manages the schedule when the AI ​​model appears on a TV program or event, and allows the AI ​​model to appear at the appropriate time. Specifically, the performance department manages the appearance schedule of the AI ​​model in a calendar app and sets reminders to avoid overlaps and conflicts. The performance department can also set the appearance conditions of the AI ​​model and support its use in appropriate situations. For example, by allowing the AI ​​model to appear only when it meets certain conditions, it provides a high-quality performance. In addition, the performance department can collect feedback on the appearance of the AI ​​model and use it for the next appearance. For example, based on the reactions from viewers and event participants, it adjusts the expression and behavior of the AI ​​model to achieve a better performance. In addition, the performance department also provides technical support for the appearance of the AI ​​model. For example, it prepares the hardware and software required for the AI ​​model to appear, and supports smooth appearances. As a result, the performance department can efficiently manage the appearance of the AI ​​model and provide a high-quality experience to the user. In addition, the performance department can analyze data on the appearance of the AI ​​model and use it to plan future appearances. For example, based on past performance data, the popularity and effectiveness of the AI ​​model can be evaluated and the next performance schedule can be optimized. This allows the performance department to effectively manage the AI ​​model's performance and meet user expectations.

[0065] The generation unit includes an adjustment unit that performs prompt engineering. The adjustment unit performs prompt engineering using the generation AI. Prompt engineering is a technology that designs and adjusts a prompt for the generation AI to generate an appropriate response. For example, the adjustment unit sets a prompt such as "Please explain the characteristics of this character" for the generation AI and adjusts it so that the generation AI generates an appropriate response. The adjustment unit can also evaluate the quality of the response generated by the generation AI and modify the prompt as necessary. For example, the adjustment unit evaluates the accuracy and consistency of the response generated by the generation AI and optimizes the prompt. Furthermore, the adjustment unit can design a prompt when the generation AI learns new information. For example, the adjustment unit sets a prompt such as "Please summarize the latest news" for the generation AI and adjusts it so that the generation AI learns the latest information. This allows the adjustment unit to design and adjust a prompt for the generation AI to generate an appropriate response. This improves the accuracy of the AI ​​model through prompt engineering.

[0066] The generation unit includes an input unit that inputs new knowledge. The input unit inputs new knowledge using the generation AI. The input of new knowledge is a technology that allows the generation AI to learn the latest information and reflect it in the AI ​​model. For example, the input unit sets a prompt to the generation AI, "Please learn the latest news," and adjusts the generation AI to learn the latest news. The input unit can also design a prompt when the generation AI takes in external information. For example, the input unit sets a prompt to the generation AI, "Please obtain information from this database," and adjusts the generation AI to take in external information. Furthermore, the input unit can also design a prompt when the generation AI uses a learning algorithm. For example, the input unit sets a prompt to the generation AI, "Please analyze data using this algorithm," and adjusts the generation AI to use the learning algorithm. This allows the input unit to allow the generation AI to learn the latest information and reflect it in the AI ​​model. This allows the AI ​​model to reflect the latest information by inputting new knowledge.

[0067] The generation unit includes a suppression unit that suppresses the transmission of harmful information. The suppression unit suppresses the transmission of harmful information using the generation AI. The suppression of the transmission of harmful information is a technology that prevents the generation AI from generating inappropriate information. For example, the suppression unit sets a prompt for the generation AI, "Do not use inappropriate words," and adjusts the generation AI so that it does not generate inappropriate information. The suppression unit can also evaluate the quality of the information generated by the generation AI and apply filtering technology as necessary. For example, the suppression unit analyzes the content of the information generated by the generation AI and filters out inappropriate information. Furthermore, the suppression unit can adjust the generation AI to comply with the moderation policy. For example, the suppression unit sets a prompt for the generation AI, "Please generate information in accordance with this policy," and adjusts the generation AI to comply with the moderation policy. This allows the suppression unit to adjust the generation AI so that it does not generate inappropriate information. This improves the reliability of the AI ​​model by suppressing the transmission of harmful information.

[0068] The management unit includes an update unit that performs regular updates. The update unit performs regular updates using the generation AI. Regular updates are a necessary technique for maintaining the performance of the AI ​​model. For example, the update unit sets a prompt for the generation AI, "Please learn the latest data every month," and adjusts the generation AI to regularly learn the latest data. The update unit can also design a prompt when the generation AI applies a security patch. For example, the update unit sets a prompt for the generation AI, "Please apply this security patch," and adjusts the generation AI to apply the security patch. The update unit can also design a prompt when the generation AI adds a new function. For example, the update unit sets a prompt for the generation AI, "Please add this new function," and adjusts the generation AI to add the new function. This allows the generation AI to regularly learn the latest data, apply security patches, and add new functions. This allows the performance of the AI ​​model to be maintained by regular updates.

[0069] The management unit includes a monitoring unit that monitors performance. The monitoring unit monitors performance using the generation AI. Performance monitoring is a necessary technique for maintaining an optimal state of the AI ​​model. For example, the monitoring unit sets a prompt for the generation AI, "Please monitor the operating speed of the AI ​​model," and adjusts the generation AI to monitor the operating speed of the AI ​​model. The monitoring unit can also design a prompt for the generation AI when setting performance metrics. For example, the monitoring unit sets a prompt for the generation AI, "Please evaluate performance based on this metric," and adjusts the generation AI to set performance metrics. Furthermore, the monitoring unit can also design a prompt for the generation AI when introducing an alert system. For example, the monitoring unit sets a prompt for the generation AI, "Please generate an alert when this condition is met," and adjusts the generation AI to introduce the alert system. This allows the monitoring unit to allow the generation AI to monitor the operating speed of the AI ​​model, set performance metrics, and introduce the alert system. This allows the AI ​​model to be maintained in an optimal state by performance monitoring.

[0070] The appearance department can manage the schedule when the AI ​​model appears on a television program or event. The appearance department uses the generation AI to manage the schedule when the AI ​​model appears on a television program or event. Schedule management is a technique for efficiently managing the appearance schedule of the AI ​​model and avoiding overlaps and conflicts. For example, the appearance department sets a prompt for the generation AI, "Please manage this schedule," and adjusts the generation AI to manage the schedule. The appearance department can also design a prompt when the generation AI uses a calendar app. For example, the appearance department sets a prompt for the generation AI, "Please use this calendar app to manage your schedule," and adjusts the generation AI to use the calendar app. Furthermore, the appearance department can design a prompt when the generation AI sets a reminder. For example, the appearance department sets a prompt for the generation AI, "Please set this reminder," and adjusts the generation AI to set a reminder. This allows the appearance department to efficiently manage the appearance schedule of the AI ​​model and avoid overlaps and conflicts. This allows the appearance schedule of the AI ​​model to be efficiently managed.

[0071] The generation unit can estimate the emotion of a character or person and adjust the expression method of the AI ​​model to be generated based on the estimated emotion. The generation unit uses the generation AI to estimate the emotion of a character or person and adjust the expression method of the AI ​​model to be generated based on the estimated emotion. Emotion estimation is a technology in which the generation AI recognizes the emotion of a character or person and adjusts the expression method based on the emotion. For example, the generation unit sets a prompt for the generation AI such as "If this character is sad, please adjust the facial expression and tone of voice" and adjusts the generation AI to adjust the expression method based on the emotion. The generation unit can also design a prompt when the generation AI adjusts the expression method based on the emotion score. For example, the generation unit sets a prompt for the generation AI such as "Please adjust the expression method based on this emotion score" and adjusts the generation AI to adjust the expression method based on the emotion score. Furthermore, the generation unit can also design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the generation unit sets a prompt for the generation AI such as "Please estimate the emotion by combining facial expression recognition, voice analysis, and text analysis" and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the generation AI to estimate the emotions of characters and people and adjust the expression method based on those emotions, thereby generating a more realistic AI model by adjusting the expression method based on emotions.

[0072] The generation unit can analyze the past behavior history of the character or person at the time of generation and select the optimal generation method. The generation unit uses the generation AI to analyze the past behavior history of the character or person at the time of generation and select the optimal generation method. Analysis of past behavior history is a technology in which the generation AI learns the past behavior of the character or person and selects the optimal generation method based on that behavior. For example, the generation unit sets a prompt to the generation AI saying "Please analyze the past behavior history of this character" and adjusts the generation AI so that it analyzes the past behavior history. The generation unit can also design a prompt when the generation AI extracts a behavior pattern. For example, the generation unit sets a prompt to the generation AI saying "Please extract this behavior pattern" and adjusts the generation AI so that it extracts a behavior pattern. Furthermore, the generation unit can design a prompt when the generation AI analyzes past utterances. For example, the generation unit sets a prompt to the generation AI saying "Please analyze the past utterances of this character" and adjusts the generation AI so that it analyzes past utterances. This allows the generation unit to analyze the past behavior history of the character or person and select the optimal generation method based on that behavior. This allows for the generation of consistent AI models by selecting a generation method based on past behavioral history.

[0073] The generation unit can customize the generation algorithm based on the attribute information of the character or person at the time of generation. The generation unit customizes the generation algorithm based on the attribute information of the character or person at the time of generation using the generation AI. Customization of the generation algorithm based on attribute information is a technology in which the generation AI learns the attribute information of the character or person and optimizes the generation algorithm based on the information. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the age and gender of this character," and adjusts the generation AI to customize the generation algorithm based on the attribute information. The generation unit can also design a prompt when the generation AI customizes the generation algorithm based on the occupation or hobby. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the occupation and hobby of this character," and adjusts the generation AI to customize the generation algorithm based on the occupation and hobby. Furthermore, the generation unit can also design a prompt when the generation AI customizes the generation algorithm based on the cultural background. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the cultural background of this character," and adjusts the generation AI to customize the generation algorithm based on the cultural background. This allows the generation AI to learn the attribute information of characters and people, and optimize the generation algorithm based on that information. This allows the generation algorithm to be customized based on attribute information, generating a more appropriate AI model.

[0074] The generation unit can estimate the emotions of characters and people, and determine the priority of AI models to be generated based on the estimated emotions. The generation unit uses the generation AI to estimate the emotions of characters and people, and determine the priority of AI models to be generated based on the estimated emotions. Emotion estimation is a technology in which the generation AI recognizes the emotions of characters and people, and determines the priority of AI models to be generated based on the emotions. For example, the generation unit sets a prompt for the generation AI, "If this character is facing an emergency, please set the priority high," and adjusts the generation AI to determine the priority based on emotions. The generation unit can also design a prompt when the generation AI determines the priority based on the emotion score. For example, the generation unit sets a prompt for the generation AI, "Please determine the priority based on this emotion score," and adjusts the generation AI to determine the priority based on the emotion score. Furthermore, the generation unit can also design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the generation unit sets a prompt for the generation AI, "Please estimate emotions by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the generation unit to estimate the emotions of characters or people and determine the priority of the AI ​​models to be generated based on those emotions. This allows AI models to be generated at a more appropriate time by determining the priority based on emotions.

[0075] The generation unit can adjust the AI ​​model to be generated by taking into account the geographical background of the character or person at the time of generation. The generation unit adjusts the AI ​​model to be generated by taking into account the geographical background of the character or person at the time of generation using the generation AI. Consideration of the geographical background is a technology in which the generation AI learns the geographical background of the character or person and adjusts the AI ​​model to be generated based on that background. For example, the generation unit sets a prompt for the generation AI, "If this character lives in an urban area, please generate it with urban scenery and sounds as the background," and adjusts the generation AI to generate it by taking into account the geographical background. The generation unit can also design a prompt when the generation AI generates a character living in a rural area. For example, the generation unit sets a prompt for the generation AI, "If this character lives in a rural area, please generate it with natural scenery and sounds as the background," and adjusts the generation AI to generate it by taking into account the rural background. Furthermore, the generation unit can design a prompt when the generation AI generates a character living in a specific country or region. For example, the generation unit sets a prompt to the generation AI saying, "If this character lives in a specific country or region, please reflect the culture and customs of that region," and adjusts the generation AI to generate the character taking into account the background of the specific region. This allows the generation unit to adjust the AI ​​model that the generation AI generates based on the geographical background of the character or person. This generates a more realistic AI model by taking the geographical background into account.

[0076] The generation unit can analyze the social media activities of the character or person at the time of generation and reflect related information in the AI ​​model to be generated. The generation unit uses the generation AI to analyze the social media activities of the character or person at the time of generation and reflects related information in the AI ​​model to be generated. Analysis of social media activities is a technology in which the generation AI learns the social media activities of the character or person and reflects related information in the AI ​​model to be generated based on the activities. For example, the generation unit sets a prompt for the generation AI, "Please analyze the social media activities of this character," and adjusts the generation AI to analyze social media activities. The generation unit can also design a prompt when the generation AI incorporates comments on social media. For example, the generation unit sets a prompt for the generation AI, "Please incorporate words and phrases that this character frequently uses on social media," and adjusts the generation AI to incorporate comments on social media. Furthermore, the generation unit can also design a prompt when the generation AI reflects popular topics on social media. For example, the generation unit sets a prompt for the generation AI, "Please reflect popular topics on social media for this character," and adjusts the generation AI to reflect popular topics. This allows the generation unit to have the generation AI learn the social media activities of characters and people and reflect related information in the AI ​​model it generates based on those activities, thereby generating a more realistic AI model by reflecting social media activities.

[0077] The management unit can estimate the emotions of a character or person and adjust the maintenance schedule of the AI ​​model based on the estimated emotions. The management unit uses the generation AI to estimate the emotions of a character or person and adjust the maintenance schedule of the AI ​​model based on the estimated emotions. Emotion estimation is a technology in which the generation AI recognizes the emotions of a character or person and adjusts the maintenance schedule based on the emotions. For example, the management unit sets a prompt for the generation AI, "If this character is stressed, perform maintenance frequently," and adjusts the generation AI to adjust the maintenance schedule based on the emotions. The management unit can also design a prompt when the generation AI adjusts the maintenance schedule based on the emotion score. For example, the management unit sets a prompt for the generation AI, "Adjust the maintenance schedule based on this emotion score," and adjusts the generation AI to adjust the maintenance schedule based on the emotion score. Furthermore, the management unit can design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the management unit sets a prompt for the generation AI, "Combine facial expression recognition, voice analysis, and text analysis to estimate emotions," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the management department to use the generative AI to estimate the emotions of characters or people and adjust the maintenance schedule based on those emotions, optimizing the performance of the AI ​​model by adjusting the maintenance schedule based on emotions.

[0078] The management unit can analyze the past performance data of the AI ​​model at the time of management and select the optimal management method. The management unit uses the generation AI to analyze the past performance data of the AI ​​model at the time of management and select the optimal management method. The analysis of past performance data is a technology in which the generation AI learns the past performance of the AI ​​model and selects the optimal management method based on the data. For example, the management unit sets a prompt for the generation AI, "Please analyze the past performance data of this AI model," and adjusts the generation AI to analyze the past performance data. The management unit can also design a prompt when the generation AI evaluates performance metrics. For example, the management unit sets a prompt for the generation AI, "Please evaluate based on this performance metric," and adjusts the generation AI to evaluate the performance metric. Furthermore, the management unit can design a prompt when the generation AI analyzes log data. For example, the management unit sets a prompt for the generation AI, "Please analyze this log data," and adjusts the generation AI to analyze the log data. This allows the management unit to analyze the past performance data of the AI ​​model and select the optimal management method based on the data. This optimizes the management of AI models by selecting management methods based on past performance data.

[0079] The management unit can customize the management algorithm based on the attribute information of the AI ​​model at the time of management. The management unit customizes the management algorithm based on the attribute information of the AI ​​model at the time of management using the generation AI. Customization of the management algorithm based on attribute information is a technology in which the generation AI learns the attribute information of the AI ​​model and optimizes the management algorithm based on the information. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the age and gender of this AI model," and adjusts the generation AI to customize the management algorithm based on the attribute information. The management unit can also design a prompt when the generation AI customizes the management algorithm based on the usage environment. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the usage environment of this AI model," and adjusts the generation AI to customize the management algorithm based on the usage environment. Furthermore, the management unit can also design a prompt when the generation AI customizes the management algorithm based on a specific function. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on a specific function of this AI model," and adjusts the generation AI to customize the management algorithm based on the specific function. This allows the management unit to have the generating AI learn attribute information of the AI ​​model and optimize the management algorithm based on that information. This optimizes the management of the AI ​​model by customizing the management algorithm based on the attribute information.

[0080] The management unit can estimate the emotions of characters and people, and determine the management priority of the AI ​​model based on the estimated emotions. The management unit uses the generation AI to estimate the emotions of characters and people, and determines the management priority of the AI ​​model based on the estimated emotions. Emotion estimation is a technology in which the generation AI recognizes the emotions of characters and people and determines the management priority based on the emotions. For example, the management unit sets a prompt for the generation AI, "If this character is facing an emergency, please set the management priority high," and adjusts the generation AI to determine the management priority based on emotions. The management unit can also design a prompt when the generation AI determines the management priority based on the emotion score. For example, the management unit sets a prompt for the generation AI, "Please determine the management priority based on this emotion score," and adjusts the generation AI to determine the management priority based on the emotion score. Furthermore, the management unit can also design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the management unit sets a prompt for the generation AI, "Please estimate emotions by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the management department to determine management priorities based on the emotions of characters and people, and the generation AI can estimate these emotions. This allows the AI ​​model to be managed at a more appropriate time by determining management priorities based on emotions.

[0081] The management unit can adjust the management method by taking into account the geographical background of the AI ​​model during management. The management unit adjusts the management method by taking into account the geographical background of the AI ​​model during management using the generation AI. Consideration of the geographical background is a technique in which the generation AI learns the geographical background of the AI ​​model and adjusts the management method based on the background. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in an urban area, please select a management method that addresses issues specific to the city," and adjusts the generation AI to adjust the management method by taking into account the geographical background. The management unit can also design a prompt when the generation AI manages an AI model used in a rural area. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in a rural area, please select a management method that addresses issues specific to the rural area," and adjusts the generation AI to adjust the management method by taking into account the rural background. Furthermore, the management unit can design a prompt when the generation AI manages an AI model used in a specific country or region. For example, the management department sets a prompt for the generating AI that says, "If this AI model is to be used in a specific country or region, please select a management method suited to the characteristics of that region," and adjusts the generating AI to adjust the management method taking into account the background of the specific region. This allows the management department to make the generating AI learn the geographical background of the AI ​​model and adjust the management method based on that background. This maintains a more realistic AI model through management that takes the geographical background into account.

[0082] The management department can analyze the social media activity of the AI ​​model at the time of management and reflect related information in management. The management department uses the generation AI to analyze the social media activity of the AI ​​model at the time of management and reflect related information in management. Analysis of social media activity is a technology in which the generation AI learns the social media activity of the AI ​​model and reflects information related to management based on the activity. For example, the management department sets a prompt for the generation AI, "Please analyze the social media activity of this AI model," and adjusts the generation AI to analyze social media activity. The management department can also design a prompt when the generation AI incorporates a statement on social media. For example, the management department sets a prompt for the generation AI, "Please incorporate the social media statement of this AI model," and adjusts the generation AI to incorporate a statement on social media. Furthermore, the management department can also design a prompt when the generation AI considers the reaction of followers on social media. For example, the management department sets a prompt for the generation AI, "Please consider the reaction of followers on social media of this AI model," and adjusts the generation AI to consider the reaction of followers. This allows the management department to allow the generation AI to learn the social media activity of the AI ​​model and reflect information related to management based on the activity. This maintains a more realistic AI model by reflecting social media activity.

[0083] The performance unit can estimate the emotions of a character or person and adjust the appearance schedule based on the estimated emotions. The performance unit uses the generation AI to estimate the emotions of a character or person and adjust the appearance schedule based on the estimated emotions. Emotion estimation is a technology in which the generation AI recognizes the emotions of a character or person and adjusts the appearance schedule based on the emotions. For example, the performance unit sets a prompt for the generation AI, "If this character is tired, please adjust the appearance schedule," and adjusts the generation AI to adjust the appearance schedule based on the emotion. The performance unit can also design a prompt when the generation AI adjusts the appearance schedule based on the emotion score. For example, the performance unit sets a prompt for the generation AI, "Please adjust the appearance schedule based on this emotion score," and adjusts the generation AI to adjust the appearance schedule based on the emotion score. Furthermore, the performance unit can also design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the performance unit sets a prompt for the generation AI, "Please estimate emotions by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the Generative AI to estimate the emotions of characters and people, and adjust the performance schedule based on those emotions. This optimizes the performance of the AI ​​model by adjusting the performance schedule based on emotions.

[0084] The performance department can analyze the past performance history of the AI ​​model at the time of appearance and select the optimal performance method. The performance department uses the generation AI to analyze the past performance history of the AI ​​model at the time of appearance and select the optimal performance method. Analysis of past performance history is a technology in which the generation AI learns the past performance history of the AI ​​model and selects the optimal performance method based on that history. For example, the performance department sets a prompt for the generation AI, "Please analyze the past performance history of this AI model," and adjusts the generation AI to analyze the past performance history. The performance department can also design a prompt when the generation AI sets an appearance schedule. For example, the performance department sets a prompt for the generation AI, "Please set this appearance schedule," and adjusts the generation AI to set an appearance schedule. Furthermore, the performance department can also design a prompt when the generation AI identifies and improves a specific problem. For example, the performance department sets a prompt for the generation AI, "Please identify and improve this problem," and adjusts the generation AI to identify and improve a specific problem. This allows the performance department to analyze the past performance history of the AI ​​model and select the optimal performance method based on that history. This optimizes the AI ​​model's performance by selecting the performance method based on past performance history.

[0085] The performance unit can customize the performance algorithm based on the attribute information of the AI ​​model at the time of performance. The performance unit uses the generation AI to customize the performance algorithm based on the attribute information of the AI ​​model at the time of performance. Customization of the performance algorithm based on attribute information is a technology in which the generation AI learns the attribute information of the AI ​​model and optimizes the performance algorithm based on the information. For example, the performance unit sets a prompt for the generation AI, "Please customize the performance algorithm based on the age and gender of this AI model," and adjusts the generation AI to customize the performance algorithm based on the attribute information. The performance unit can also design a prompt when the generation AI customizes the performance algorithm based on the usage environment. For example, the performance unit sets a prompt for the generation AI, "Please customize the performance algorithm based on the usage environment of this AI model," and adjusts the generation AI to customize the performance algorithm based on the usage environment. In addition, the performance unit can also design a prompt when the generation AI customizes the performance algorithm based on a specific function. For example, the performance unit sets a prompt for the generation AI, "Please customize the performance algorithm based on a specific function of this AI model," and adjusts the generation AI to customize the performance algorithm based on the specific function. This allows the generation AI to learn the attribute information of the AI ​​model, and optimize the performance algorithm based on that information. This optimizes the performance of the AI ​​model by customizing the performance algorithm based on the attribute information.

[0086] The performance unit can estimate the emotions of characters and people and determine the priority of appearances based on the estimated emotions. The performance unit uses the generation AI to estimate the emotions of characters and people and determine the priority of appearances based on the estimated emotions. Emotion estimation is a technology in which the generation AI recognizes the emotions of characters and people and determines the priority of appearances based on the emotions. For example, the performance unit sets a prompt for the generation AI saying, "If this character is facing an emergency, please set the priority of appearances high," and adjusts the generation AI to determine the priority of appearances based on emotions. The performance unit can also design a prompt when the generation AI determines the priority of appearances based on emotion scores. For example, the performance unit sets a prompt for the generation AI saying, "Please determine the priority of appearances based on this emotion score," and adjusts the generation AI to determine the priority of appearances based on emotion scores. Furthermore, the performance unit can also design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the performance unit sets a prompt for the generation AI saying, "Please estimate emotions by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the Generative AI to estimate the emotions of characters and people, and prioritize appearances based on those emotions. This allows the AI ​​model to appear at a more appropriate time by prioritizing appearances based on emotions.

[0087] The performance unit can adjust the appearance method by taking into account the geographical background of the AI ​​model when performing. The performance unit adjusts the appearance method by taking into account the geographical background of the AI ​​model when performing using the generation AI. Consideration of the geographical background is a technique in which the generation AI learns the geographical background of the AI ​​model and adjusts the appearance method based on that background. For example, the performance unit sets a prompt for the generation AI, "If this AI model is used in an urban area, please select an appearance method that addresses issues specific to the city," and adjusts the generation AI to adjust the appearance method by taking into account the geographical background. The performance unit can also design a prompt when the generation AI performs an AI model to be used in a rural area. For example, the performance unit sets a prompt for the generation AI, "If this AI model is used in a rural area, please select an appearance method that addresses issues specific to the rural area," and adjusts the generation AI to adjust the appearance method by taking into account the rural background. Furthermore, the performance unit can design a prompt when the generation AI performs an AI model to be used in a specific country or region. For example, the performance department sets a prompt for the generation AI that says, "If this AI model is used in a specific country or region, please select a performance method that suits the characteristics of that region," and adjusts the generation AI to adjust the performance method taking into account the background of the specific region. This allows the performance department to make the generation AI learn the geographical background of the AI ​​model and adjust the performance method based on that background. This allows a more realistic AI model to perform by taking the geographical background into account.

[0088] The performance department can analyze the social media activity of the AI ​​model at the time of the appearance and reflect the related information in the appearance. The performance department uses the generation AI to analyze the social media activity of the AI ​​model at the time of the appearance and reflect the related information in the appearance. The analysis of social media activity is a technology in which the generation AI learns the social media activity of the AI ​​model and reflects information related to the appearance based on the activity. For example, the performance department sets a prompt for the generation AI, "Please analyze the social media activity of this AI model," and adjusts the generation AI to analyze the social media activity. The performance department can also design a prompt when the generation AI incorporates a statement on social media. For example, the performance department sets a prompt for the generation AI, "Please incorporate the social media statement of this AI model," and adjusts the generation AI to incorporate the statement on social media. Furthermore, the performance department can also design a prompt when the generation AI considers the reaction of followers on social media. For example, the performance department sets a prompt for the generation AI, "Please consider the reaction of followers on social media of this AI model," and adjusts the generation AI to consider the reaction of followers. In this way, the performance department can make the generation AI learn the social media activity of the AI ​​model and reflect information related to the appearance based on the activity. This allows for a more realistic AI model to appear that reflects social media activity.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The generation unit can estimate the emotion of a character or person, and adjust the expression method of the AI ​​model to be generated based on the estimated emotion. For example, the generation unit sets a prompt for the generation AI, "If this character is sad, please adjust the facial expression and tone of voice," and adjusts the generation AI to adjust the expression method based on the emotion. The generation unit can also design a prompt when the generation AI adjusts the expression method based on the emotion score. For example, the generation unit sets a prompt for the generation AI, "Please adjust the expression method based on this emotion score," and adjusts the generation AI to adjust the expression method based on the emotion score. Furthermore, the generation unit can design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the generation unit sets a prompt for the generation AI, "Please estimate the emotion by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the generation unit to estimate the emotion of a character or person, and adjust the expression method based on the emotion. This allows a more realistic AI model to be generated by adjusting the expression method based on the emotion.

[0091] The generation unit can analyze the past behavior history of a character or person at the time of generation and select the optimal generation method. For example, the generation unit sets a prompt for the generation AI, "Please analyze the past behavior history of this character," and adjusts the generation AI to analyze the past behavior history. The generation unit can also design a prompt when the generation AI extracts a behavior pattern. For example, the generation unit sets a prompt for the generation AI, "Please extract this behavior pattern," and adjusts the generation AI to extract a behavior pattern. The generation unit can also design a prompt when the generation AI analyzes past utterances. For example, the generation unit sets a prompt for the generation AI, "Please analyze the past utterances of this character," and adjusts the generation AI to analyze past utterances. This allows the generation unit to analyze the past behavior history of a character or person and select the optimal generation method based on that behavior. As a result, a consistent AI model is generated by selecting a generation method based on the past behavior history.

[0092] The generation unit can customize the generation algorithm based on the attribute information of the character or person at the time of generation. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the age and gender of this character," and adjusts the generation AI to customize the generation algorithm based on the attribute information. The generation unit can also design a prompt when the generation AI customizes the generation algorithm based on an occupation or hobby. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the occupation and hobby," and adjusts the generation AI to customize the generation algorithm based on the occupation and hobby. Furthermore, the generation unit can design a prompt when the generation AI customizes the generation algorithm based on a cultural background. For example, the generation unit sets a prompt for the generation AI, "Please customize the generation algorithm based on the cultural background of this character," and adjusts the generation AI to customize the generation algorithm based on the cultural background. This allows the generation unit to allow the generation AI to learn the attribute information of the character or person and optimize the generation algorithm based on that information. This allows a more appropriate AI model to be generated by customizing the generation algorithm based on the attribute information.

[0093] The generation unit can estimate the emotions of a character or person and determine the priority of an AI model to be generated based on the estimated emotions. For example, the generation unit sets a prompt for the generation AI, "If this character is facing an emergency, set the priority high," and adjusts the generation AI to determine the priority based on emotions. The generation unit can also design a prompt when the generation AI determines the priority based on an emotion score. For example, the generation unit sets a prompt for the generation AI, "Determine the priority based on this emotion score," and adjusts the generation AI to determine the priority based on the emotion score. Furthermore, the generation unit can design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the generation unit sets a prompt for the generation AI, "Determine the emotion by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the generation unit to estimate the emotions of a character or person and determine the priority of an AI model to be generated based on the emotion. This allows an AI model to be generated at a more appropriate time by determining the priority based on emotions.

[0094] The generation unit can adjust the AI ​​model to be generated by taking into account the geographical background of the character or person at the time of generation. For example, the generation unit sets a prompt for the generation AI, "If this character lives in an urban area, please generate it with urban scenery and sounds in the background," and adjusts the generation AI to generate it by taking into account the geographical background. The generation unit can also design a prompt when the generation AI generates a character living in a rural area. For example, the generation unit sets a prompt for the generation AI, "If this character lives in a rural area, please generate it with natural scenery and sounds in the background," and adjusts the generation AI to generate it by taking into account the rural background. The generation unit can also design a prompt when the generation AI generates a character living in a specific country or region. For example, the generation unit sets a prompt for the generation AI, "If this character lives in a specific country or region, please reflect the culture and customs of that region," and adjusts the generation AI to generate it by taking into account the background of the specific region. This allows the generation unit to learn the geographical background of the character or person and adjust the AI ​​model to be generated based on that background. This generates a more realistic AI model by taking the geographical background into account.

[0095] The management unit can estimate the emotions of a character or person, and adjust the maintenance schedule of the AI ​​model based on the estimated emotions. For example, the management unit sets a prompt for the generation AI, "If this character is stressed, perform maintenance frequently," and adjusts the generation AI to adjust the maintenance schedule based on emotions. The management unit can also design a prompt when the generation AI adjusts the maintenance schedule based on an emotion score. For example, the management unit sets a prompt for the generation AI, "Adjust the maintenance schedule based on this emotion score," and adjusts the generation AI to adjust the maintenance schedule based on the emotion score. Furthermore, the management unit can design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the management unit sets a prompt for the generation AI, "Estimate emotions by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the management unit to allow the generation AI to estimate the emotions of a character or person, and adjust the maintenance schedule based on the emotions. This optimizes the performance of the AI ​​model by adjusting the maintenance schedule based on emotions.

[0096] During management, the management unit can analyze past performance data of the AI ​​model and select an optimal management method. For example, the management unit sets a prompt for the generation AI, "Analyze the past performance data of this AI model," and adjusts the generation AI to analyze the past performance data. The management unit can also design a prompt for the generation AI to evaluate performance metrics. For example, the management unit sets a prompt for the generation AI, "Evaluate based on this performance metric," and adjusts the generation AI to evaluate the performance metric. The management unit can also design a prompt for the generation AI to analyze log data. For example, the management unit sets a prompt for the generation AI, "Analyze this log data," and adjusts the generation AI to analyze the log data. This allows the management unit to allow the generation AI to analyze past performance data of the AI ​​model and select an optimal management method based on the data. This optimizes the management of the AI ​​model by selecting a management method based on past performance data.

[0097] The management unit can customize the management algorithm based on the attribute information of the AI ​​model during management. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the age and gender of this AI model," and adjusts the generation AI to customize the management algorithm based on the attribute information. The management unit can also design a prompt when the generation AI customizes the management algorithm based on the usage environment. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on the usage environment of this AI model," and adjusts the generation AI to customize the management algorithm based on the usage environment. Furthermore, the management unit can also design a prompt when the generation AI customizes the management algorithm based on a specific function. For example, the management unit sets a prompt for the generation AI, "Please customize the management algorithm based on a specific function of this AI model," and adjusts the generation AI to customize the management algorithm based on the specific function. This allows the management unit to allow the generation AI to learn the attribute information of the AI ​​model and optimize the management algorithm based on that information. This optimizes the management of the AI ​​model by customizing the management algorithm based on the attribute information.

[0098] The management unit can estimate the emotions of a character or person and determine the management priority of the AI ​​model based on the estimated emotions. For example, the management unit sets a prompt for the generation AI, "If this character is facing an emergency, set the management priority high," and adjusts the generation AI to determine the management priority based on emotions. The management unit can also design a prompt when the generation AI determines the management priority based on an emotion score. For example, the management unit sets a prompt for the generation AI, "Please determine the management priority based on this emotion score," and adjusts the generation AI to determine the management priority based on the emotion score. Furthermore, the management unit can design a prompt when the generation AI combines multiple emotion estimation technologies. For example, the management unit sets a prompt for the generation AI, "Please estimate emotions by combining facial expression recognition, voice analysis, and text analysis," and adjusts the generation AI to combine multiple emotion estimation technologies. This allows the management unit to allow the generation AI to estimate the emotions of a character or person and determine the management priority based on the emotions. This allows the AI ​​model to be managed at a more appropriate time by determining the management priority based on emotions.

[0099] The management unit can adjust the management method by taking into account the geographical background of the AI ​​model during management. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in an urban area, please select a management method that addresses issues specific to the city," and adjusts the generation AI to adjust the management method by taking into account the geographical background. The management unit can also design a prompt when the generation AI manages an AI model to be used in a rural area. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in a rural area, please select a management method that addresses issues specific to the rural area," and adjusts the generation AI to adjust the management method by taking into account the background of the rural area. Furthermore, the management unit can also design a prompt when the generation AI manages an AI model to be used in a specific country or region. For example, the management unit sets a prompt for the generation AI, "If this AI model is used in a specific country or region, please select a management method that addresses the characteristics of the region," and adjusts the generation AI to adjust the management method by taking into account the background of the specific region. This allows the management unit to allow the generation AI to learn the geographical background of the AI ​​model and adjust the management method based on that background. As a result, a more realistic AI model is maintained by management that takes into account the geographical background.

[0100] The process flow of the second embodiment will be briefly described below.

[0101] Step 1: The generation unit uses generative AI to create an AI model of a character or person. The generation unit learns the characteristics of the character or person and generates a realistic AI model. The generation unit can reproduce the appearance, voice, and movements of the character or person. For example, the generation unit learns the character's facial expressions and tone of voice to produce realistic expressions. The generation unit can also learn the character's movements and reproduce natural movements. Step 2: The management department maintains and manages the AI ​​model created by the generation department. The management department regularly updates the AI ​​model to reflect the latest information. The management department also monitors the performance of the AI ​​model and makes adjustments as necessary. For example, the management department monitors the operating speed and responsiveness of the AI ​​model to maintain it in an optimal state. Furthermore, the management department takes measures to ensure the security of the AI ​​model. For example, the management department sets security policies to prevent unauthorized access to the AI ​​model. Step 3: The Performance Department manages the appearances of the AI ​​model maintained by the Management Department. The Performance Department manages the schedule of the AI ​​model's appearances on TV programs and events, and allows it to appear at the appropriate time. The Performance Department can efficiently manage the appearance schedule of the AI ​​model and avoid overlaps and conflicts. For example, the Performance Department manages the appearance schedule of the AI ​​model in a calendar app and sets reminders. The Performance Department also sets the appearance conditions for the AI ​​model and supports its use in appropriate situations. For example, the Performance Department allows the AI ​​model to appear only if it meets certain conditions.

[0102] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0103] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0104] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0105] Each of the multiple elements including the above-mentioned generation unit, management unit, and performance unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart device 14, and creates an AI model of a character or person using a generation AI. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs maintenance and management of the AI ​​model. The performance unit is realized, for example, by the control unit 46A of the smart device 14, and performs performance management of the AI ​​model. Each of the multiple elements including the adjustment unit, input unit, suppression unit, update unit, and monitoring unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0108] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0113] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0116] In the smart glasses 214, the 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 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0118] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed 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 required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0121] Each of the multiple elements including the above-mentioned generation unit, management unit, and performance unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the smart glasses 214, and creates an AI model of a character or person using a generation AI. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs maintenance and management of the AI ​​model. The performance unit is realized, for example, by the control unit 46A of the smart glasses 214, and performs performance management of the AI ​​model. Each of the multiple elements including the adjustment unit, input unit, suppression unit, update unit, and monitoring unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0132] In the headset type terminal 314, the 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 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0137] Each of the multiple elements including the above-mentioned generation unit, management unit, and performance unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the headset type terminal 314, and creates an AI model of a character or person using a generation AI. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs maintenance and management of the AI ​​model. The performance unit is realized, for example, by the control unit 46A of the headset type terminal 314, and performs performance management of the AI ​​model. Each of the multiple elements including the adjustment unit, input unit, suppression unit, update unit, and monitoring unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0138] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0139] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0140] 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. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0141] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0142] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0144] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0145] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0146] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0147] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0149] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0153] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed 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 required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0154] Each of the plurality of elements including the above-mentioned generation unit, management unit, and performance unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the generation unit is realized by the control unit 46A of the robot 414, and creates an AI model of a character or person using a generation AI. The management unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and performs maintenance and management of the AI ​​model. The performance unit is realized, for example, by the control unit 46A of the robot 414, and performs performance management of the AI ​​model. Each of the plurality of elements including the adjustment unit, input unit, suppression unit, update unit, and monitoring unit is realized, for example, by at least one of the robot 414 and the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0155] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0156] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0157] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0158] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0159] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0160] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this 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 positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0161] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0162] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0163] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0164] In addition, 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 upon request from the data processing device 12.

[0165] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0166] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0167] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0168] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0169] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0170] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0171] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0172] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0173] (Appendix 1) A generator for creating an AI model of a character or person; A management unit that maintains and manages the AI ​​model created by the generation unit; A performance unit that performs performance management of the AI ​​model maintained and managed by the management unit. A system characterized by: (Appendix 2) The generation unit is Equipping a coordination department for prompt engineering 2. The system of claim 1, (Appendix 3) The generation unit is Equipping the input section for inputting new knowledge 2. The system of claim 1, (Appendix 4) The generation unit is Equipped with a suppression unit that suppresses the transmission of harmful information 2. The system of claim 1, (Appendix 5) The management unit Equipped with an update section that performs regular updates 2. The system of claim 1, (Appendix 6) The management unit Equipped with a monitoring section to monitor performance 2. The system of claim 1, (Appendix 7) The cast includes: Manage the schedule for AI models to appear on TV shows or events 2. The system of claim 1, (Appendix 8) The generation unit is Estimate the emotions of characters and people, and adjust the expression method of the generated AI model based on the estimated emotions. 2. The system of claim 1, (Appendix 9) The generation unit is During generation, the past behavioral history of characters and people is analyzed to select the optimal generation method. 2. The system of claim 1, (Appendix 10) The generation unit is Customize the generation algorithm based on the attributes of characters and people during generation. 2. The system of claim 1, (Appendix 11) The generation unit is Estimate the emotions of characters and people, and prioritize the AI ​​models to be generated based on the estimated emotions. 2. The system of claim 1, (Appendix 12) The generation unit is During generation, the AI ​​model is adjusted to take into account the geographical background of the characters or people. 2. The system of claim 1, (Appendix 13) The generation unit is During generation, the social media activity of characters and people is analyzed and relevant information is fed into the AI ​​model that generates them. 2. The system of claim 1, (Appendix 14) The management unit Estimate the emotions of characters and people, and adjust the maintenance schedule of the AI ​​model based on the estimated emotions. 2. The system of claim 1, (Appendix 15) The management unit During management, the AI ​​model's past performance data is analyzed to select the optimal management method. 2. The system of claim 1, (Appendix 16) The management unit During management, the management algorithm is customized based on the attribute information of the AI ​​model. 2. The system of claim 1, (Appendix 17) The management unit Estimate the emotions of characters and people, and determine management priorities for AI models based on the estimated emotions. 2. The system of claim 1, (Appendix 18) The management unit During management, adjust management methods by taking into account the geographical context of the AI ​​model. 2. The system of claim 1, (Appendix 19) The management unit During management, the AI ​​model analyzes social media activity and reflects relevant information in management. 2. The system of claim 1, (Appendix 20) The cast includes: Estimate the emotions of characters and people and adjust appearance schedules based on the estimated emotions 2. The system of claim 1, (Appendix 21) The cast includes: When performing, the AI ​​model's past performance history is analyzed to select the optimal performance method. 2. The system of claim 1, (Appendix 22) The cast includes: When performing, the performance algorithm is customized based on the AI ​​model's attribute information. 2. The system of claim 1, (Appendix 23) The cast includes: Estimate the emotions of characters and people and prioritize appearances based on the estimated emotions 2. The system of claim 1, (Appendix 24) The cast includes: When performing, the AI ​​model will take into account the geographical context to adjust the performance method. 2. The system of claim 1, (Appendix 25) The cast includes: During the performance, the AI ​​model analyzes social media activity and incorporates relevant information into the performance. 2. The system of claim 1, [Explanation of symbols]

[0174] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A generator that creates an AI model of a character or person; A management unit that maintains and manages the AI ​​model created by the generation unit; A performance unit that performs performance management of the AI ​​model maintained and managed by the management unit. A system characterized by:

2. The generation unit is Equipping a coordination department for prompt engineering 2. The system of claim 1 .

3. The generation unit is Equipping the input section for inputting new knowledge 2. The system of claim 1 .

4. The generation unit is Equipped with a suppression unit that suppresses the transmission of harmful information 2. The system of claim 1 .

5. The management unit Equipped with an update section that performs regular updates 2. The system of claim 1 .

6. The management unit Equipped with a monitoring section to monitor performance 2. The system of claim 1 .

7. The system according to claim 1 , wherein the appearance department manages a schedule when the AI ​​model appears on a television program or event.

8. The generation unit is Estimate the emotions of characters and people, and adjust the expression method of the generated AI model based on the estimated emotions.

2. The system of claim 1 .

9. The generation unit is During generation, the past behavioral history of characters and people is analyzed to select the optimal generation method.

2. The system of claim 1 .

Images