System

Abstract

An object of the system according to the embodiment is to provide text and instructions in real time and smoothly support the performance of the performer.SOLUTION: A system includes an instruction generation part, an instruction provision part, a training plan generation part, a provision part, and a reception part. The instruction generation unit generates an instruction. The instruction providing unit provides the instruction generated by the instruction generation unit. The training plan generator generates a training plan. The providing unit provides the training plan generated by the training plan generating unit. The reception unit receives an affiliation fee.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 an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

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

[0004] Conventional technology has the drawback of making it difficult to provide text and instructions in real time, making it difficult to smoothly support performers' performances.

[0005] The system according to the embodiment aims to provide text and instructions in real time to smoothly support the performers' performance. [Means for solving the problem]

[0006] The system according to the embodiment includes an instruction generation unit, an instruction provision unit, a training plan generation unit, a training plan provision unit, and a reception unit. The instruction generation unit generates instructions. The instruction provision unit provides the instructions generated by the instruction generation unit. The training plan generation unit generates a training plan. The provision unit provides the training plan generated by the training plan generation unit. The reception unit receives an affiliation fee. [Effects of the Invention]

[0007] The system according to the embodiment can provide text and instructions in real time to smoothly support the performers' performance. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A next-generation talent agency system according to an embodiment of the present invention is a system that efficiently generates and provides instructions, generates and provides training plans, and receives membership fees. In the next-generation talent agency system, prompt engineers are dispatched to television programs and YouTube channels and use generation AI to provide text and instructions in real time to support performers in smooth performances. The system also uses generation AI to provide optimal training plans to idols and entertainers considering debuting, improving their abilities. Furthermore, the agency receives membership fees from the idols and entertainers it represents. For example, the next-generation talent agency system uses generation AI to provide instructions to prompt engineers to support performers' performances in real time. For example, the generation AI provides instructions to adjust the content and timing of what performers say during talk shows. Next, the next-generation talent agency system uses generation AI to provide optimal training plans for individual idols and entertainers considering debuting. For example, the generation AI suggests specific practice content to improve speaking skills and performance. This allows idols and entertainers to efficiently improve their abilities. Furthermore, the next-generation talent agency system receives membership fees from the idols and entertainers it represents. This allows agencies to secure stable revenue and continue to train and dispatch prompt engineers. This allows the next-generation entertainment agency system to improve the performance of idols and entertainers, as well as enhance the abilities of those aiming to debut. It also allows agencies to secure stable revenue and continue to operate.

[0029] A next-generation talent agency system according to an embodiment includes an instruction generation unit, an instruction provision unit, a training plan generation unit, a training plan provision unit, and a reception unit. The instruction generation unit generates instructions using a generation AI. For example, the instruction generation unit generates instructions to adjust the content and timing of what a performer will say in a talk show. The instruction generation unit can also estimate the emotions of the performers and adjust the content of the instructions based on the estimated emotions. For example, if a performer is nervous, the instruction generation unit can generate instructions to help the performer relax. The instruction provision unit provides the generated instructions in real time. For example, the instruction provision unit displays the generated instructions to the performers in real time. The instruction provision unit can also estimate the emotions of the performers and adjust the display method of the instructions based on the estimated emotions. For example, if a performer is nervous, the instruction provision unit can provide a simple, highly visible display method. The training plan generation unit generates a training plan using a generation AI. For example, the training plan generation unit generates a training plan based on the goals and wishes of an idol or comedian. The training plan generation unit can also estimate the emotions of the idol or comedian and adjust the content of the training plan based on the estimated emotions. For example, if an idol or comedian is nervous, a training plan to help them relax can be generated. The training plan providing unit provides the generated training plan. For example, the training plan providing unit provides the generated training plan to the idol or comedian. The training plan providing unit can also estimate the emotions of the idol or comedian, and adjust the display method of the training plan based on the estimated emotions. For example, if an idol or comedian is nervous, a simple and highly visible display method can be provided. The reception unit accepts an membership fee. For example, the reception unit accepts an membership fee from the idol or comedian. The reception unit can also estimate the emotions of the idol or comedian, and adjust the payment method for the membership fee based on the estimated emotions. For example, if an idol or comedian is nervous, a simple and highly visible payment method can be provided.As a result, the next-generation talent agency system according to the embodiment can efficiently generate and provide instructions, generate and provide training plans, and receive membership fees.

[0030] The instruction generation unit generates instructions using a generation AI. Examples of generation AI include natural language generation AI and image generation AI. The instruction generation unit uses the generation AI to generate instructions to adjust the content and timing of what the performers will say during a talk show. For example, the generation AI receives a prompt such as, "What topic should we talk about next?" and suggests an appropriate topic. The instruction generation unit can also estimate the emotions of the performers and adjust the content of the instructions based on the estimated emotions. For example, the generation AI can analyze the facial expressions and voice data of the performers and generate instructions to relax them if they are nervous. This improves the accuracy of instruction generation by using generation AI.

[0031] The instruction providing unit can provide the generated instructions in real time. Real time means that the instructions are provided almost immediately with an extremely short delay time. The instruction providing unit displays the generated instructions to the performers in real time. For example, the instruction providing unit displays the generated instructions on a screen or monitor. The instruction providing unit can also estimate the emotions of the performers and adjust the way the instructions are displayed based on the estimated emotions. For example, if the performer is nervous, a simple, highly visible display method can be provided. This allows for smooth support of the performers' performance by providing instructions in real time.

[0032] The training plan generation unit generates a training plan using a generation AI. Examples of generation AI include natural language generation AI and image generation AI. The training plan generation unit uses the generation AI to generate a training plan based on the goals and wishes of an idol or comedian. For example, the generation AI receives a prompt such as, "What are your idol's goals?" and proposes an appropriate training plan. The training plan generation unit can also estimate the emotions of an idol or comedian and adjust the content of the training plan based on the estimated emotions. For example, the generation AI can analyze the facial expressions and voice data of an idol or comedian and generate a training plan to help them relax if they are nervous. This improves the accuracy of training plan generation by using generation AI.

[0033] The training plan providing unit can provide the generated training plan. The training plan includes, for example, an exercise plan, a skill improvement plan, a mental training plan, etc. The training plan providing unit provides the generated training plan to the idol or comedian. For example, the training plan providing unit displays the generated training plan on a screen or monitor. The training plan providing unit can also estimate the emotions of the idol or comedian and adjust the display method of the training plan based on the estimated emotions. For example, if the idol or comedian is nervous, a simple and highly visible display method can be provided. In this way, by providing the generated training plan, it is possible to support the idol or comedian in improving their abilities.

[0034] The reception unit can accept membership fees. The membership fees include, for example, monthly fees, lump-sum fees, installment fees, etc. The reception unit accepts the membership fees from idols and comedians. For example, the reception unit accepts the membership fees using an online payment system. The reception unit can also estimate the emotions of the idols and comedians and adjust the payment method for the membership fees based on the estimated emotions. For example, if the idols and comedians are nervous, it can provide them with a simple, highly visible payment method. This allows the agency to secure revenue by accepting the membership fees.

[0035] The instruction generation unit can analyze the program's progress in real time and generate appropriate instructions. The program's progress is analyzed based on, for example, the program script and real-time viewer reactions. The instruction generation unit can analyze the program's progress in real time and generate appropriate instructions. For example, if the program is running behind schedule, the generation AI can provide instructions to speed up the program. Also, if the program is progressing smoothly, the generation AI can provide instructions to smoothly transition to the next segment. Also, if the program is progressing too fast, the generation AI can provide instructions to slow down the pace. In this way, instructions can be provided according to the program's progress, supporting smooth progress.

[0036] The instruction generation unit can generate individually customized instructions by referencing the performer's past performance data. Past performance data includes, for example, past performance records and evaluation data. The instruction generation unit generates individually customized instructions by referencing the performer's past performance data. For example, the generation AI can provide similar instructions based on the performer's past successful performances. The generation AI can also provide instructions to help the performer avoid performances that failed in the past. The generation AI can also analyze the performer's past performance data and provide optimal instructions. In this way, the performer's performance can be optimized by providing instructions based on the past performance data.

[0037] The instruction generation unit can apply different instruction generation algorithms depending on the theme or topic of the program. Examples of instruction generation algorithms include rule-based and machine learning-based algorithms. The instruction generation unit applies different instruction generation algorithms depending on the theme or topic of the program. For example, for a variety show, the generation AI can provide humorous instructions. For a news program, the generation AI can also provide precise and concise instructions. For a drama program, the generation AI can also provide emotionally appealing instructions. This improves the quality of the program by providing instructions that are appropriate for the program's theme or topic.

[0038] The instruction generation unit can analyze viewer reactions to a program in real time and generate instructions based on that. Viewer reactions include, for example, real-time comments and viewer rating data. The instruction generation unit can analyze viewer reactions to a program in real time and generate instructions based on that. For example, if viewer reactions are good, the generation AI can provide instructions to continue the program as is. Also, if viewer reactions are bad, the generation AI can provide instructions to change the content. Also, if viewer reactions are neutral, the generation AI can provide instructions to attract viewer interest. In this way, the quality of the program can be improved by providing instructions according to viewer reactions.

[0039] The instruction generation unit can refer to the program progress script and generate instructions in accordance with the script. The progress script includes, for example, a script or a scenario. The instruction generation unit refers to the program progress script and generates instructions in accordance with the script. For example, the instruction generation unit instructs a transition to the next segment based on the program progress script. The generation AI can also provide instructions to talk about a specific topic based on the program progress script. The generation AI can also provide instructions to clarify the roles of performers based on the program progress script. In this way, by providing instructions based on the progress script, it is possible to support the smooth progression of the program.

[0040] The instruction generation unit can change the style of instructions depending on the genre of the program. Program genres include, for example, variety shows, news, dramas, etc. The instruction generation unit changes the style of instructions depending on the genre of the program. For example, for a variety show, the generation AI provides humorous instructions. For a news program, the generation AI can also provide precise and concise instructions. For a drama program, the generation AI can also provide instructions that bring out emotions. In this way, the quality of the program is improved by providing instructions that are appropriate for the program genre.

[0041] The instruction providing unit can monitor the current performance status of the performer in real time when providing instructions, and update the instructions as necessary. Monitoring of the performance status is performed, for example, based on real-time motion analysis and performance evaluation. The instruction providing unit can monitor the current performance status of the performer in real time when providing instructions, and update the instructions as necessary. For example, if the performer is progressing ahead of schedule, the next instruction can be provided earlier. Also, if the performer is falling behind schedule, instructions can be provided to speed up the progress. Also, if the performer makes a mistake, instructions to correct the mistake can be provided in real time. In this way, by monitoring the performance status in real time and updating instructions, the quality of the performance can be improved.

[0042] When providing instructions, the instruction providing unit can optimize the presentation method by reflecting the performer's past feedback. Past feedback includes, for example, survey results and evaluation comments. When providing instructions, the instruction providing unit optimizes the presentation method by reflecting the performer's past feedback. For example, the instruction providing unit can prioritize and provide display methods that the performer has preferred in the past. It can also provide display methods that the performer has avoided in the past by excluding them. It can also provide the optimal display method based on the performer's past feedback. In this way, optimizing the presentation method based on past feedback improves understanding of instructions.

[0043] When providing instructions, the instruction providing unit can adjust the level of detail of the instructions according to the skill level of the performer. Skill levels include, for example, beginner, intermediate, and advanced. When providing instructions, the instruction providing unit adjusts the level of detail of the instructions according to the skill level of the performer. For example, if the performer is a beginner, detailed instructions can be provided. Also, if the performer is an intermediate performer, instructions that focus on the main points can be provided. Also, if the performer is an advanced performer, concise instructions can be provided. In this way, by providing instructions according to the performer's skill level, understanding of the instructions can be improved.

[0044] When providing instructions, the instruction providing unit can select the optimal display method by taking into consideration the device information of the performer. Device information includes, for example, the device type (e.g., smartphone, tablet, PC) and device setting information. When providing instructions, the instruction providing unit selects the optimal display method by taking into consideration the device information of the performer. For example, if the performer is using a smartphone, a display method that matches the screen size can be provided. Also, if the performer is using a tablet, a display method optimized for a large screen can be provided. Also, if the performer is using a smartwatch, a simple and highly visible display method can be provided. In this way, by providing a display method based on device information, understanding of instructions can be improved.

[0045] When providing instructions, the instruction providing unit can make the instruction content multilingual in accordance with the language setting of the performer. The language setting includes, for example, language types such as Japanese, English, and Spanish, and language setting information. When providing instructions, the instruction providing unit makes the instruction content multilingual in accordance with the language setting of the performer. For example, the instruction language can be automatically set based on the language setting of the performer's device. In addition, if the performer uses multiple languages, a language switching function can be provided. In addition, if the performer selects a specific language, instructions can be provided in that language. In this way, by providing instructions based on the language setting, understanding of the instructions can be improved.

[0046] When providing instructions, the instruction providing unit can customize the presentation method by referring to the performer's past performance data. Past performance data includes, for example, past performance records and evaluation data. When providing instructions, the instruction providing unit customizes the presentation method by referring to the performer's past performance data. For example, the instruction providing unit provides a display method that the performer has preferred in the past with priority. It can also provide a display method that the performer has avoided in the past by excluding such a display method. It can also provide an optimal display method based on the performer's past performance data. In this way, customizing the presentation method based on past performance data improves understanding of instructions.

[0047] The training plan generation unit can generate an individually customized training plan by referencing the idol's or comedian's past performance data. Past performance data includes, for example, past appearance records and evaluation data. The training plan generation unit generates an individually customized training plan by referencing the idol's or comedian's past performance data. For example, the generation AI provides a similar training plan based on the idol's or comedian's past successful performances. The generation AI can also provide a training plan to help the idol or comedian avoid past unsuccessful performances. The generation AI can also analyze the idol's or comedian's past performance data and provide an optimal training plan. In this way, the training effectiveness is improved by providing a training plan based on past performance data.

[0048] When generating a training plan, the training plan generation unit can optimize the plan based on the goals and hopes of the idol or comedian. Goals and hopes include, for example, career goals and hopes for skill improvement. When generating a training plan, the training plan generation unit optimizes the plan based on the goals and hopes of the idol or comedian. For example, the AI ​​generating a training plan provides it based on the goals that the idol or comedian is aiming for. The AI ​​generating a training plan can also provide it based on the hopes of the idol or comedian. The AI ​​generating a training plan can also provide an optimal training plan by combining the goals and hopes of the idol or comedian. In this way, the effectiveness of training is improved by providing a training plan based on the goals and hopes.

[0049] When generating a training plan, the training plan generation unit can combine different training methods to create an optimal plan. Training methods include, for example, physical training and mental training. When generating a training plan, the training plan generation unit combines different training methods to create an optimal plan. For example, the generation AI provides a plan that combines singing training and dance training depending on the skills of an idol or comedian. The generation AI can also provide a plan that combines acting training and talking training depending on the goals of the idol or comedian. The generation AI can also provide a plan that combines physical training and mental training depending on the wishes of the idol or comedian. In this way, the effectiveness of training is improved by combining different training methods.

[0050] When generating a training plan, the training plan generation unit can adjust the plan taking into account the schedule of the idol or comedian. The schedule includes, for example, a schedule table or calendar information. When generating a training plan, the training plan generation unit adjusts the plan taking into account the schedule of the idol or comedian. For example, the training time period can be adjusted to match the idol or comedian's schedule. The frequency of training can also be adjusted to match the idol or comedian's schedule. The content of training can also be adjusted to match the idol or comedian's schedule. In this way, the effectiveness of training can be improved by providing a training plan based on the schedule.

[0051] The training plan generation unit can update the training plan by reflecting feedback from idols and comedians when generating the plan. Feedback includes, for example, survey results and evaluation comments. The training plan generation unit updates the plan by reflecting feedback from idols and comedians when generating the training plan. For example, the content of the training plan is updated based on the feedback from idols and comedians. The frequency of the training plan can also be updated based on the feedback from idols and comedians. The time period of the training plan can also be updated based on the feedback from idols and comedians. In this way, the effectiveness of training can be improved by providing a training plan based on feedback.

[0052] When generating a training plan, the training plan generation unit can customize the plan according to the specialty of the idol or comedian. Specialties include, for example, dancing, singing, and acting. When generating a training plan, the training plan generation unit customizes the plan according to the specialty of the idol or comedian. For example, an idol who aspires to be a singer can be provided with a plan centered on singing training by the generation AI. An idol who aspires to be a dancer can also be provided with a plan centered on dance training by the generation AI. Furthermore, an entertainer who aspires to be a comedian can be provided with a plan centered on talk training by the generation AI. In this way, the effectiveness of training can be improved by providing a training plan based on the specialty.

[0053] The training plan providing unit can monitor the current training status of the idol or comedian in real time when providing a training plan, and update the plan as necessary. Monitoring the training status is performed, for example, based on real-time motion analysis and training evaluation. The training plan providing unit can monitor the current training status of the idol or comedian in real time when providing a training plan, and update the plan as necessary. For example, if the idol or comedian is progressing faster than planned, the next training plan can be provided earlier. Also, if the idol or comedian is falling behind schedule, a training plan to speed up the progress can be provided. Also, if the idol or comedian makes a mistake, a training plan to correct the mistake can be provided in real time. In this way, by monitoring the training status in real time and updating the plan, the effectiveness of training can be improved.

[0054] When providing a training plan, the training plan providing unit can optimize the method of providing the training plan by reflecting past feedback from the idol or comedian. Past feedback includes, for example, survey results and evaluation comments. When providing a training plan, the training plan providing unit optimizes the method of providing the training plan by reflecting past feedback from the idol or comedian. For example, the training plan providing unit can prioritize and provide a display method that the idol or comedian has preferred in the past. It can also provide a display method that the idol or comedian has avoided in the past by excluding such display methods. It can also provide the optimal display method based on the idol or comedian's past feedback. In this way, optimizing the method of providing the plan based on past feedback improves understanding of the training plan.

[0055] When providing a training plan, the training plan providing unit can adjust the level of detail of the plan according to the skill level of the idol or comedian. Skill levels include, for example, beginner, intermediate, and advanced. When providing a training plan, the training plan providing unit adjusts the level of detail of the plan according to the skill level of the idol or comedian. For example, if the idol or comedian is a beginner, a detailed training plan can be provided. Also, if the idol or comedian is intermediate, a training plan that focuses on the main points can be provided. Also, if the idol or comedian is advanced, a concise training plan can be provided. In this way, by providing a training plan according to the skill level, understanding of the training plan can be improved.

[0056] When providing a training plan, the training plan providing unit can select the optimal display method by taking into consideration the device information of the idol or comedian. Device information includes, for example, the device type (smartphone, tablet, PC, etc.) and device setting information. When providing a training plan, the training plan providing unit selects the optimal display method by taking into consideration the device information of the idol or comedian. For example, if the idol or comedian is using a smartphone, a display method that matches the screen size can be provided. Also, if the idol or comedian is using a tablet, a display method optimized for a large screen can be provided. Also, if the idol or comedian is using a smartwatch, a simple and highly visible display method can be provided. In this way, by providing a display method based on device information, understanding of the training plan can be improved.

[0057] When providing a training plan, the training plan providing unit can make the plan content multilingual in accordance with the language setting of the idol or comedian. The language setting includes, for example, language types such as Japanese, English, and Spanish, and language setting information. When providing a training plan, the training plan providing unit makes the plan content multilingual in accordance with the language setting of the idol or comedian. For example, the training plan language can be automatically set based on the language setting of the idol or comedian's device. In addition, if the idol or comedian speaks multiple languages, a language switching function can be provided. In addition, if the idol or comedian selects a specific language, the training plan can be provided in that language. In this way, by providing a training plan based on the language setting, understanding of the training plan can be improved.

[0058] When providing a training plan, the training plan providing unit can customize the method of providing it by referring to the idol's or comedian's past training data. Past training data includes, for example, past training records and evaluation data. When providing a training plan, the training plan providing unit customizes the method of providing it by referring to the idol's or comedian's past training data. For example, the training plan providing unit provides a display method that the idol or comedian has preferred in the past with priority. It can also provide a display method that the idol or comedian has avoided in the past by excluding such display methods. It can also provide an optimal display method based on the idol's or comedian's past training data. In this way, customizing the method of providing it based on past training data improves understanding of the training plan.

[0059] When accepting the membership fee, the reception unit can propose an optimal payment plan by referring to the idol's or entertainer's past payment history. The past payment history includes, for example, payment dates and payment amounts. When accepting the membership fee, the reception unit proposes an optimal payment plan by referring to the idol's or entertainer's past payment history. For example, the reception unit proposes an optimal payment plan based on the idol's or entertainer's past payment history. The reception unit can also customize the payment method based on the idol's or entertainer's past payment history. The reception unit can also analyze the idol's or entertainer's past payment history and propose an optimal payment plan. This improves the smoothness of payments by providing payment plans based on past payment history.

[0060] The reception unit can improve the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. Feedback includes, for example, survey results and evaluation comments. The reception unit improves the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. For example, the reception unit improves the payment method based on the idol's or comedian's feedback. The reception unit can also improve the payment plan based on the idol's or comedian's feedback. The reception unit can also provide the optimal payment method based on the idol's or comedian's feedback. In this way, providing a payment method based on feedback improves the smoothness of payments.

[0061] The reception unit can select the optimal payment method by taking into consideration the geographic location information of the idol or entertainer when accepting the membership fee. Geographic location information includes, for example, GPS data and address information. The reception unit selects the optimal payment method by taking into consideration the geographic location information of the idol or entertainer when accepting the membership fee. For example, if the idol or entertainer is overseas, an international payment method can be provided. Also, if the idol or entertainer is in a rural area, a local bank payment method can be provided. The optimal payment method can also be provided based on the geographic location information of the idol or entertainer. In this way, by providing a payment method based on geographic location information, the smoothness of payments is improved.

[0062] The reception unit can select the optimal payment method by taking into consideration the device information of the idol or comedian when accepting the membership fee. Device information includes, for example, the device type (smartphone, tablet, PC, etc.) and device setting information. The reception unit selects the optimal payment method by taking into consideration the device information of the idol or comedian when accepting the membership fee. For example, if the idol or comedian uses a smartphone, mobile payment can be provided. Also, if the idol or comedian uses a tablet, a payment method optimized for tablets can be provided. Also, if the idol or comedian uses a PC, online banking can be provided. In this way, by offering payment methods based on device information, the smoothness of payments is improved.

[0063] The reception unit can improve the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. Feedback includes, for example, survey results and evaluation comments. The reception unit improves the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. For example, the reception unit improves the payment method based on the idol's or comedian's feedback. The reception unit can also improve the payment plan based on the idol's or comedian's feedback. The reception unit can also provide the optimal payment method based on the idol's or comedian's feedback. In this way, providing a payment method based on feedback improves the smoothness of payments.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] The next-generation talent agency system may further include a schedule management unit. The schedule management unit manages the schedules of performers and provides feedback to the training plan generation unit. For example, if a performer has a busy schedule, the training plan generation unit can generate a short and effective training plan. The schedule management unit can also take performers' rest times into consideration and make adjustments to avoid excessive training. Furthermore, the schedule management unit can suggest optimal training times based on the performers' schedules. This makes it possible to provide flexible training plans that fit the performers' schedules and support efficient training.

[0066] The next-generation talent agency system can further include a health management unit. The health management unit monitors the health status of performers and provides the data to the training plan generation unit. For example, it can analyze the performer's heart rate and sleep data to generate a training plan based on their health status. The health management unit can also manage the performer's diet and nutritional status and provide advice to support healthy lifestyle habits. Furthermore, the health management unit can suggest a training plan to help performers relax if they are feeling stressed. This makes it possible to provide training plans based on the performer's health status and support the improvement of their overall performance.

[0067] The next-generation talent agency system may further include a feedback collection unit. The feedback collection unit collects feedback from performers and viewers and provides the data to the instruction generation unit and the training plan generation unit. For example, the feedback collection unit may collect information about how performers feel about a training plan and adjust the plan based on the feedback. The feedback collection unit may also collect viewers' reactions and generate instructions tailored to the viewers' preferences. Furthermore, the feedback collection unit may collect evaluations of the performers' performances and provide instructions to improve the next performance based on the evaluations. This makes it possible to utilize feedback from performers and viewers to provide more effective training plans and instructions.

[0068] The next-generation talent agency system may further include an audience analysis unit. The audience analysis unit analyzes audience responses in real time and provides the data to the instruction generation unit. For example, the audience analysis unit may analyze audience comments and reactions to understand audience emotions and interests. The audience analysis unit may also adjust instructions to performers based on audience responses. For example, if viewers show interest in a particular topic, it may generate instructions related to that topic. The audience analysis unit may also adjust the progress of the program based on audience responses. This allows for providing instructions according to audience responses and improving the quality of the program.

[0069] The next-generation talent agency system may further include a performance prediction unit. The performance prediction unit predicts future performances based on the performer's past performance data and provides the results to the instruction generation unit. For example, the performance prediction unit may analyze the patterns of the performer's past successful performances and generate instructions to replicate similar success. The performance prediction unit may also generate instructions to help the performer avoid performances that failed in the past. Furthermore, the performance prediction unit may analyze the performer's performance trends and provide optimal instructions. This makes it possible to optimize the performer's performance by utilizing predictions based on past data.

[0070] The next-generation talent agency system can further include a content generation unit. The content generation unit generates new content based on the performers' performances and provides that content to the instruction generation unit. For example, the content generation unit can suggest the next topic based on what the performers said in a talk show. The content generation unit can also analyze the performers' performances and suggest new plans or ideas based on the results. Furthermore, the content generation unit can generate content that will interest viewers based on their reactions. This allows for the provision of new content based on the performers' performances, improving the quality of the program.

[0071] The next-generation talent agency system can further include a performance improvement unit. The performance improvement unit monitors the performers' performances in real time and, based on that data, identifies areas for improvement. For example, it can analyze the performers' tone of voice and facial expressions when they speak at a talk show and provide the instruction generation unit with areas for improvement. The performance improvement unit can also analyze the performers' movements and posture and provide advice on how to perform more effectively. Furthermore, the performance improvement unit can suggest performance styles that viewers prefer based on their reactions. This allows for continuous improvement of the performers' performances and increases viewer satisfaction.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The instruction generation unit generates instructions using a generation AI. For example, it generates instructions to adjust the content and timing of what a performer says during a talk show. It can also estimate the performer's emotions and adjust the content of the instructions based on the estimated emotions. For example, if a performer is nervous, it can generate instructions to help them relax. Step 2: The instruction providing unit provides the generated instructions in real time. For example, the generated instructions are displayed to the performers in real time. The unit can also estimate the performers' emotions and adjust the way the instructions are displayed based on the estimated emotions. For example, if the performers are nervous, a simple, highly visible display method can be provided. Step 3: The training plan generation unit uses generation AI to generate a training plan. For example, it generates a training plan based on the idol's or comedian's goals and aspirations. It can also estimate the idol's or comedian's emotions and adjust the content of the training plan based on the estimated emotions. For example, if the idol or comedian is nervous, it can generate a training plan to help them relax. Step 4: The training plan providing unit provides the generated training plan. For example, the generated training plan is provided to an idol or comedian. The unit can also estimate the emotions of the idol or comedian and adjust the display method of the training plan based on the estimated emotions. For example, if the idol or comedian is nervous, a simple, highly visible display method can be provided. Step 5: The reception unit accepts membership fees. For example, it accepts membership fees from idols or comedians. It can also estimate the emotions of idols or comedians and adjust the payment method for the membership fees based on the estimated emotions. For example, if an idol or comedian is nervous, it can provide a simple and highly visible payment method.

[0074] (Example 2) A next-generation talent agency system according to an embodiment of the present invention is a system that efficiently generates and provides instructions, generates and provides training plans, and receives membership fees. In this system, prompt engineers are dispatched to television programs and YouTube channels and use generative AI to provide text and instructions in real time to support performers in smooth performances. The system also uses generative AI to provide optimal training plans to idols and entertainers considering debuting, improving their abilities. Furthermore, the agency receives membership fees from the idols and entertainers it represents. For example, the next-generation talent agency system uses generative AI to provide instructions to prompt engineers to support performers' performances in real time. For example, the generative AI provides instructions to adjust the content and timing of what performers say during talk shows. Next, the next-generation talent agency system uses generative AI to provide optimal training plans for each idol or entertainer considering debuting. For example, the generative AI suggests specific practice content to improve speaking skills and performance. This allows idols and entertainers to efficiently improve their abilities. Furthermore, the next-generation talent agency system receives membership fees from the idols and entertainers it represents. This allows agencies to secure stable revenue and continue to train and dispatch prompt engineers. This allows the next-generation entertainment agency system to improve the performance of idols and entertainers, as well as enhance the abilities of those aiming to debut. It also allows agencies to secure stable revenue and continue to operate.

[0075] A next-generation talent agency system according to an embodiment includes an instruction generation unit, an instruction provision unit, a training plan generation unit, a training plan provision unit, and a reception unit. The instruction generation unit generates instructions using a generation AI. For example, the instruction generation unit generates instructions to adjust the content and timing of what a performer will say in a talk show. The instruction generation unit can also estimate the emotions of the performers and adjust the content of the instructions based on the estimated emotions. For example, if a performer is nervous, the instruction generation unit can generate instructions to help the performer relax. The instruction provision unit provides the generated instructions in real time. For example, the instruction provision unit displays the generated instructions to the performers in real time. The instruction provision unit can also estimate the emotions of the performers and adjust the display method of the instructions based on the estimated emotions. For example, if a performer is nervous, the instruction provision unit can provide a simple, highly visible display method. The training plan generation unit generates a training plan using a generation AI. For example, the training plan generation unit generates a training plan based on the goals and wishes of an idol or comedian. The training plan generation unit can also estimate the emotions of the idol or comedian and adjust the content of the training plan based on the estimated emotions. For example, if an idol or comedian is nervous, a training plan to help them relax can be generated. The training plan providing unit provides the generated training plan. For example, the training plan providing unit provides the generated training plan to the idol or comedian. The training plan providing unit can also estimate the emotions of the idol or comedian, and adjust the display method of the training plan based on the estimated emotions. For example, if an idol or comedian is nervous, a simple and highly visible display method can be provided. The reception unit accepts an membership fee. For example, the reception unit accepts an membership fee from the idol or comedian. The reception unit can also estimate the emotions of the idol or comedian, and adjust the payment method for the membership fee based on the estimated emotions. For example, if an idol or comedian is nervous, a simple and highly visible payment method can be provided.As a result, the next-generation talent agency system according to the embodiment can efficiently generate and provide instructions, generate and provide training plans, and receive membership fees.

[0076] The instruction generation unit generates instructions using a generation AI. Examples of generation AI include natural language generation AI and image generation AI. The instruction generation unit uses the generation AI to generate instructions to adjust the content and timing of what a performer will say during a talk show. For example, the generation AI receives a prompt such as, "What topic should we talk about next?" and suggests an appropriate topic. The instruction generation unit can also estimate the emotions of a performer and adjust the content of the instructions based on the estimated emotions. For example, the generation AI can analyze the facial expressions and voice data of a performer and generate instructions to relax them if they are nervous. This improves the accuracy of instruction generation by using generation AI.

[0077] The instruction providing unit can provide the generated instructions in real time. Real time means that the instructions are provided almost immediately with an extremely short delay time. The instruction providing unit displays the generated instructions to the performers in real time. For example, the instruction providing unit displays the generated instructions on a screen or monitor. The instruction providing unit can also estimate the emotions of the performers and adjust the way the instructions are displayed based on the estimated emotions. For example, if the performer is nervous, a simple, highly visible display method can be provided. This allows for smooth support of the performers' performance by providing instructions in real time.

[0078] The training plan generation unit generates a training plan using a generation AI. Examples of generation AI include natural language generation AI and image generation AI. The training plan generation unit uses the generation AI to generate a training plan based on the goals and wishes of an idol or comedian. For example, the generation AI receives a prompt such as, "What are your idol's goals?" and proposes an appropriate training plan. The training plan generation unit can also estimate the emotions of an idol or comedian and adjust the content of the training plan based on the estimated emotions. For example, the generation AI can analyze the facial expressions and voice data of an idol or comedian and generate a training plan to help them relax if they are nervous. This improves the accuracy of training plan generation by using generation AI.

[0079] The training plan providing unit can provide the generated training plan. The training plan includes, for example, an exercise plan, a skill improvement plan, a mental training plan, etc. The training plan providing unit provides the generated training plan to the idol or comedian. For example, the training plan providing unit displays the generated training plan on a screen or monitor. The training plan providing unit can also estimate the emotions of the idol or comedian and adjust the display method of the training plan based on the estimated emotions. For example, if the idol or comedian is nervous, a simple and highly visible display method can be provided. In this way, by providing the generated training plan, it is possible to support the idol or comedian in improving their abilities.

[0080] The reception unit can accept membership fees. The membership fees include, for example, monthly fees, lump-sum fees, installment fees, etc. The reception unit accepts the membership fees from idols and comedians. For example, the reception unit accepts the membership fees using an online payment system. The reception unit can also estimate the emotions of the idols and comedians and adjust the payment method for the membership fees based on the estimated emotions. For example, if the idols and comedians are nervous, it can provide them with a simple, highly visible payment method. This allows the agency to secure revenue by accepting the membership fees.

[0081] The instruction generation unit can estimate the emotions of the performers and adjust the content of the instructions based on the estimated emotions. Emotion estimation is achieved, for example, by using an emotion estimation function with an emotion engine or generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. The instruction generation unit estimates the emotions of the performers and adjusts the content of the instructions based on the estimated emotions. For example, if the performers are nervous, the generation AI can provide instructions to relax them. Also, if the performers are excited, the generation AI can provide instructions to stay calm. Also, if the performers are tired, the generation AI can provide instructions to increase their energy. In this way, the quality of the performance is improved by providing instructions that correspond to the performers' emotions.

[0082] The instruction generation unit can analyze the program's progress in real time and generate appropriate instructions. The program's progress is analyzed based on, for example, the program script and real-time viewer reactions. The instruction generation unit can analyze the program's progress in real time and generate appropriate instructions. For example, if the program is running behind schedule, the generation AI can provide instructions to speed up the program. Also, if the program is progressing smoothly, the generation AI can provide instructions to smoothly transition to the next segment. Also, if the program is progressing too fast, the generation AI can provide instructions to slow down the pace. In this way, instructions can be provided according to the program's progress, supporting smooth progress.

[0083] The instruction generation unit can generate individually customized instructions by referencing the performer's past performance data. Past performance data includes, for example, past performance records and evaluation data. The instruction generation unit generates individually customized instructions by referencing the performer's past performance data. For example, the generation AI can provide similar instructions based on the performer's past successful performances. The generation AI can also provide instructions to help the performer avoid performances that failed in the past. The generation AI can also analyze the performer's past performance data and provide optimal instructions. In this way, the performer's performance can be optimized by providing instructions based on the past performance data.

[0084] The instruction generation unit can apply different instruction generation algorithms depending on the theme or topic of the program. Examples of instruction generation algorithms include rule-based and machine learning-based algorithms. The instruction generation unit applies different instruction generation algorithms depending on the theme or topic of the program. For example, for a variety show, the generation AI can provide humorous instructions. For a news program, the generation AI can also provide precise and concise instructions. For a drama program, the generation AI can also provide emotionally appealing instructions. This improves the quality of the program by providing instructions that are appropriate for the program's theme or topic.

[0085] The instruction generation unit can estimate the emotions of the performers and adjust the timing of instructions based on the estimated emotions. Emotion estimation is achieved, for example, by using an emotion estimation function with an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI. The instruction generation unit estimates the emotions of the performers and adjusts the timing of instructions based on the estimated emotions. For example, if the performers are nervous, the timing of instructions can be delayed to give them time to relax. Also, if the performers are excited, the timing of instructions can be advanced to keep them calm. Also, if the performers are tired, the timing of instructions can be adjusted to allow them to take a break. This improves the quality of the performance by providing instructions at times that correspond to the performers' emotions.

[0086] The instruction generation unit can analyze viewer reactions to a program in real time and generate instructions based on that. Viewer reactions include, for example, real-time comments and viewer rating data. The instruction generation unit can analyze viewer reactions to a program in real time and generate instructions based on that. For example, if viewer reactions are good, the generation AI can provide instructions to continue the program as is. Also, if viewer reactions are bad, the generation AI can provide instructions to change the content. Also, if viewer reactions are neutral, the generation AI can provide instructions to attract viewer interest. In this way, the quality of the program can be improved by providing instructions according to viewer reactions.

[0087] The instruction generation unit can refer to the program progress script and generate instructions in accordance with the script. The progress script includes, for example, a script or a scenario. The instruction generation unit refers to the program progress script and generates instructions in accordance with the script. For example, the instruction generation unit instructs a transition to the next segment based on the program progress script. The generation AI can also provide instructions to talk about a specific topic based on the program progress script. The generation AI can also provide instructions to clarify the roles of performers based on the program progress script. In this way, by providing instructions based on the progress script, it is possible to support the smooth progression of the program.

[0088] The instruction generation unit can change the style of instructions depending on the genre of the program. Program genres include, for example, variety shows, news, dramas, etc. The instruction generation unit changes the style of instructions depending on the genre of the program. For example, for a variety show, the generation AI provides humorous instructions. For a news program, the generation AI can also provide precise and concise instructions. For a drama program, the generation AI can also provide instructions that bring out emotions. In this way, the quality of the program is improved by providing instructions that are appropriate for the program genre.

[0089] The instruction providing unit can estimate the emotions of the performers and adjust the display method of the instructions based on the estimated emotions. Emotion estimation is achieved, for example, by using an emotion estimation function with an emotion engine or generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. The instruction providing unit estimates the emotions of the performers and adjusts the display method of the instructions based on the estimated emotions. For example, if the performer is nervous, a simple, highly visible display method can be provided. Alternatively, if the performer is relaxed, a display method including detailed information can be provided. Alternatively, if the performer is in a hurry, a display method that focuses on the main points can be provided. In this way, by providing a display method that corresponds to the performer's emotions, understanding of the instructions can be improved.

[0090] The instruction providing unit can monitor the current performance status of the performer in real time when providing instructions, and update the instructions as necessary. Monitoring of the performance status is performed, for example, based on real-time motion analysis and performance evaluation. The instruction providing unit can monitor the current performance status of the performer in real time when providing instructions, and update the instructions as necessary. For example, if the performer is progressing ahead of schedule, the next instruction can be provided earlier. Also, if the performer is falling behind schedule, instructions can be provided to speed up the progress. Also, if the performer makes a mistake, instructions to correct the mistake can be provided in real time. In this way, by monitoring the performance status in real time and updating instructions, the quality of the performance can be improved.

[0091] When providing instructions, the instruction providing unit can optimize the presentation method by reflecting the performer's past feedback. Past feedback includes, for example, survey results and evaluation comments. When providing instructions, the instruction providing unit optimizes the presentation method by reflecting the performer's past feedback. For example, the instruction providing unit can prioritize and provide display methods that the performer has preferred in the past. It can also provide display methods that the performer has avoided in the past by excluding them. It can also provide the optimal display method based on the performer's past feedback. In this way, optimizing the presentation method based on past feedback improves understanding of instructions.

[0092] When providing instructions, the instruction providing unit can adjust the level of detail of the instructions according to the skill level of the performer. Skill levels include, for example, beginner, intermediate, and advanced. When providing instructions, the instruction providing unit adjusts the level of detail of the instructions according to the skill level of the performer. For example, if the performer is a beginner, detailed instructions can be provided. Also, if the performer is an intermediate performer, instructions that focus on the main points can be provided. Also, if the performer is an advanced performer, concise instructions can be provided. In this way, by providing instructions according to the performer's skill level, understanding of the instructions can be improved.

[0093] The instruction providing unit can estimate the emotions of the performers and prioritize instructions based on the estimated emotions. Emotion estimation is achieved, for example, by using an emotion estimation function with an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI. The instruction providing unit estimates the emotions of the performers and prioritizes instructions based on the estimated emotions. For example, if the performer is nervous, instructions to relax can be prioritized. Also, if the performer is excited, instructions to stay calm can be prioritized. Also, if the performer is tired, instructions to increase energy can be prioritized. In this way, the quality of the performance is improved by prioritizing instructions according to the performers' emotions.

[0094] When providing instructions, the instruction providing unit can select the optimal display method by taking into consideration the device information of the performer. Device information includes, for example, the device type (e.g., smartphone, tablet, PC) and device setting information. When providing instructions, the instruction providing unit selects the optimal display method by taking into consideration the device information of the performer. For example, if the performer is using a smartphone, a display method that matches the screen size can be provided. Also, if the performer is using a tablet, a display method optimized for a large screen can be provided. Also, if the performer is using a smartwatch, a simple and highly visible display method can be provided. In this way, by providing a display method based on device information, understanding of instructions can be improved.

[0095] When providing instructions, the instruction providing unit can make the instruction content multilingual in accordance with the language setting of the performer. The language setting includes, for example, language types such as Japanese, English, and Spanish, and language setting information. When providing instructions, the instruction providing unit makes the instruction content multilingual in accordance with the language setting of the performer. For example, the instruction language can be automatically set based on the language setting of the performer's device. In addition, if the performer uses multiple languages, a language switching function can be provided. In addition, if the performer selects a specific language, instructions can be provided in that language. In this way, by providing instructions based on the language setting, understanding of the instructions can be improved.

[0096] When providing instructions, the instruction providing unit can customize the presentation method by referring to the performer's past performance data. Past performance data includes, for example, past performance records and evaluation data. When providing instructions, the instruction providing unit customizes the presentation method by referring to the performer's past performance data. For example, the instruction providing unit provides a display method that the performer has preferred in the past with priority. It can also provide a display method that the performer has avoided in the past by excluding such a display method. It can also provide an optimal display method based on the performer's past performance data. In this way, customizing the presentation method based on past performance data improves understanding of instructions.

[0097] The training plan generation unit can estimate the emotions of the idols or comedians and adjust the content of the training plan based on the estimated emotions. Emotion estimation is achieved, for example, using an emotion estimation function with an emotion engine or generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI. The training plan generation unit estimates the emotions of the idols or comedians and adjusts the content of the training plan based on the estimated emotions. For example, if the idols or comedians are nervous, the generation AI can provide them with a training plan to relax. Also, if the idols or comedians are excited, the generation AI can provide them with a training plan to keep them calm. Also, if the idols or comedians are tired, the generation AI can provide them with a training plan to increase their energy. In this way, the effectiveness of training is improved by providing a training plan that matches the emotions of the idols or comedians.

[0098] The training plan generation unit can generate an individually customized training plan by referencing the idol's or comedian's past performance data. Past performance data includes, for example, past appearance records and evaluation data. The training plan generation unit generates an individually customized training plan by referencing the idol's or comedian's past performance data. For example, the generation AI provides a similar training plan based on the idol's or comedian's past successful performances. The generation AI can also provide a training plan to help the idol or comedian avoid past unsuccessful performances. The generation AI can also analyze the idol's or comedian's past performance data and provide an optimal training plan. In this way, the training effectiveness is improved by providing a training plan based on past performance data.

[0099] When generating a training plan, the training plan generation unit can optimize the plan based on the goals and hopes of the idol or comedian. Goals and hopes include, for example, career goals and hopes for skill improvement. When generating a training plan, the training plan generation unit optimizes the plan based on the goals and hopes of the idol or comedian. For example, the AI ​​generating a training plan provides it based on the goals that the idol or comedian is aiming for. The AI ​​generating a training plan can also provide it based on the hopes of the idol or comedian. The AI ​​generating a training plan can also provide an optimal training plan by combining the goals and hopes of the idol or comedian. In this way, the effectiveness of training is improved by providing a training plan based on the goals and hopes.

[0100] When generating a training plan, the training plan generation unit can combine different training methods to create an optimal plan. Training methods include, for example, physical training and mental training. When generating a training plan, the training plan generation unit combines different training methods to create an optimal plan. For example, the generation AI provides a plan that combines singing training and dance training depending on the skills of an idol or comedian. The generation AI can also provide a plan that combines acting training and talking training depending on the goals of the idol or comedian. The generation AI can also provide a plan that combines physical training and mental training depending on the wishes of the idol or comedian. In this way, the effectiveness of training is improved by combining different training methods.

[0101] The training plan generation unit can estimate the emotions of idols and comedians and prioritize training plans based on the estimated emotions. Emotion estimation is achieved, for example, using an emotion estimation function with an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or multimodal generation AI. The training plan generation unit estimates the emotions of idols and comedians and prioritizes training plans based on the estimated emotions. For example, if the idol or comedian is nervous, training to relax can be prioritized. Also, if the idol or comedian is excited, training to stay calm can be prioritized. Also, if the idol or comedian is tired, training to increase energy can be prioritized. In this way, the effectiveness of training can be improved by prioritizing training plans according to emotions.

[0102] When generating a training plan, the training plan generation unit can adjust the plan taking into account the schedule of the idol or comedian. The schedule includes, for example, a schedule table or calendar information. When generating a training plan, the training plan generation unit adjusts the plan taking into account the schedule of the idol or comedian. For example, the training time period can be adjusted to match the idol or comedian's schedule. The frequency of training can also be adjusted to match the idol or comedian's schedule. The content of training can also be adjusted to match the idol or comedian's schedule. In this way, the effectiveness of training can be improved by providing a training plan based on the schedule.

[0103] The training plan generation unit can update the training plan by reflecting feedback from idols and comedians when generating the plan. Feedback includes, for example, survey results and evaluation comments. The training plan generation unit updates the plan by reflecting feedback from idols and comedians when generating the training plan. For example, the content of the training plan is updated based on the feedback from idols and comedians. The frequency of the training plan can also be updated based on the feedback from idols and comedians. The time period of the training plan can also be updated based on the feedback from idols and comedians. In this way, the effectiveness of training can be improved by providing a training plan based on feedback.

[0104] When generating a training plan, the training plan generation unit can customize the plan according to the specialty of the idol or comedian. Specialties include, for example, dancing, singing, and acting. When generating a training plan, the training plan generation unit customizes the plan according to the specialty of the idol or comedian. For example, an idol who aspires to be a singer can be provided with a plan centered on singing training by the generation AI. An idol who aspires to be a dancer can also be provided with a plan centered on dance training by the generation AI. Furthermore, an entertainer who aspires to be a comedian can be provided with a plan centered on talk training by the generation AI. In this way, the effectiveness of training can be improved by providing a training plan based on the specialty.

[0105] The training plan providing unit can estimate the emotions of idols or comedians and adjust the display method of the training plan based on the estimated emotions. Emotion estimation is achieved, for example, using an emotion estimation function with an emotion engine or generation AI. The generation AI is a text generation AI (e.g., LLM) or multimodal generation AI. The training plan providing unit estimates the emotions of idols or comedians and adjusts the display method of the training plan based on the estimated emotions. For example, if the idol or comedian is nervous, a simple, highly visible display method can be provided. Also, if the idol or comedian is relaxed, a display method including detailed information can be provided. Also, if the idol or comedian is in a hurry, a display method that focuses on the main points can be provided. This improves understanding of the training plan by providing a display method that corresponds to the emotion.

[0106] The training plan providing unit can monitor the current training status of the idol or comedian in real time when providing a training plan, and update the plan as necessary. Monitoring the training status is performed, for example, based on real-time motion analysis and training evaluation. The training plan providing unit can monitor the current training status of the idol or comedian in real time when providing a training plan, and update the plan as necessary. For example, if the idol or comedian is progressing faster than planned, the next training plan can be provided earlier. Also, if the idol or comedian is falling behind schedule, a training plan to speed up the progress can be provided. Also, if the idol or comedian makes a mistake, a training plan to correct the mistake can be provided in real time. In this way, by monitoring the training status in real time and updating the plan, the effectiveness of training can be improved.

[0107] When providing a training plan, the training plan providing unit can optimize the method of providing the training plan by reflecting past feedback from the idol or comedian. Past feedback includes, for example, survey results and evaluation comments. When providing a training plan, the training plan providing unit optimizes the method of providing the training plan by reflecting past feedback from the idol or comedian. For example, the training plan providing unit can prioritize and provide a display method that the idol or comedian has preferred in the past. It can also provide a display method that the idol or comedian has avoided in the past by excluding such display methods. It can also provide the optimal display method based on the idol or comedian's past feedback. In this way, optimizing the method of providing the plan based on past feedback improves understanding of the training plan.

[0108] When providing a training plan, the training plan providing unit can adjust the level of detail of the plan according to the skill level of the idol or comedian. Skill levels include, for example, beginner, intermediate, and advanced. When providing a training plan, the training plan providing unit adjusts the level of detail of the plan according to the skill level of the idol or comedian. For example, if the idol or comedian is a beginner, a detailed training plan can be provided. Also, if the idol or comedian is intermediate, a training plan that focuses on the main points can be provided. Also, if the idol or comedian is advanced, a concise training plan can be provided. In this way, by providing a training plan according to the skill level, understanding of the training plan can be improved.

[0109] The training plan providing unit can estimate the emotions of idols and comedians and prioritize training plans based on the estimated emotions. Emotion estimation is achieved, for example, using an emotion estimation function using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or multimodal generation AI. The training plan providing unit estimates the emotions of idols and comedians and prioritizes training plans based on the estimated emotions. For example, if the idol or comedian is nervous, training to relax can be prioritized. Also, if the idol or comedian is excited, training to stay calm can be prioritized. Also, if the idol or comedian is tired, training to increase energy can be prioritized. In this way, the effectiveness of training can be improved by prioritizing training plans according to emotions.

[0110] When providing a training plan, the training plan providing unit can select the optimal display method by taking into consideration the device information of the idol or comedian. Device information includes, for example, the device type (smartphone, tablet, PC, etc.) and device setting information. When providing a training plan, the training plan providing unit selects the optimal display method by taking into consideration the device information of the idol or comedian. For example, if the idol or comedian is using a smartphone, a display method that matches the screen size can be provided. Also, if the idol or comedian is using a tablet, a display method optimized for a large screen can be provided. Also, if the idol or comedian is using a smartwatch, a simple and highly visible display method can be provided. In this way, by providing a display method based on device information, understanding of the training plan can be improved.

[0111] When providing a training plan, the training plan providing unit can make the plan content multilingual in accordance with the language setting of the idol or comedian. The language setting includes, for example, language types such as Japanese, English, and Spanish, and language setting information. When providing a training plan, the training plan providing unit makes the plan content multilingual in accordance with the language setting of the idol or comedian. For example, the training plan language can be automatically set based on the language setting of the idol or comedian's device. In addition, if the idol or comedian speaks multiple languages, a language switching function can be provided. In addition, if the idol or comedian selects a specific language, the training plan can be provided in that language. In this way, by providing a training plan based on the language setting, understanding of the training plan can be improved.

[0112] When providing a training plan, the training plan providing unit can customize the method of providing it by referring to the idol's or comedian's past training data. Past training data includes, for example, past training records and evaluation data. When providing a training plan, the training plan providing unit customizes the method of providing it by referring to the idol's or comedian's past training data. For example, the training plan providing unit provides a display method that the idol or comedian has preferred in the past with priority. It can also provide a display method that the idol or comedian has avoided in the past by excluding such display methods. It can also provide an optimal display method based on the idol's or comedian's past training data. In this way, customizing the method of providing it based on past training data improves understanding of the training plan.

[0113] The reception unit can estimate the emotions of idols and entertainers and adjust the payment method for membership fees based on the estimated emotions. Emotion estimation is achieved, for example, using an emotion estimation function with an emotion engine or generative AI. Generative AI can be a text generation AI (e.g., LLM) or multimodal generation AI. The reception unit estimates the emotions of idols and entertainers and adjusts the payment method for membership fees based on the estimated emotions. For example, if the idol or entertainer is nervous, a simple, highly visible payment method can be provided. Alternatively, if the idol or entertainer is relaxed, a payment method that includes detailed information can be provided. Alternatively, if the idol or entertainer is in a hurry, a payment method that focuses on the key points can be provided. This improves the smoothness of payments by providing payment methods that correspond to emotions.

[0114] When accepting the membership fee, the reception unit can propose an optimal payment plan by referring to the idol's or entertainer's past payment history. The past payment history includes, for example, payment dates and payment amounts. When accepting the membership fee, the reception unit proposes an optimal payment plan by referring to the idol's or entertainer's past payment history. For example, the reception unit proposes an optimal payment plan based on the idol's or entertainer's past payment history. The reception unit can also customize the payment method based on the idol's or entertainer's past payment history. The reception unit can also analyze the idol's or entertainer's past payment history and propose an optimal payment plan. This improves the smoothness of payments by providing payment plans based on past payment history.

[0115] The reception unit can improve the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. Feedback includes, for example, survey results and evaluation comments. The reception unit improves the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. For example, the reception unit improves the payment method based on the idol's or comedian's feedback. The reception unit can also improve the payment plan based on the idol's or comedian's feedback. The reception unit can also provide the optimal payment method based on the idol's or comedian's feedback. In this way, providing a payment method based on feedback improves the smoothness of payments.

[0116] The reception unit can estimate the emotions of idols and entertainers and adjust the timing of membership fee payments based on the estimated emotions. Emotion estimation is achieved, for example, using an emotion estimation function with an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or multimodal generation AI. The reception unit estimates the emotions of idols and entertainers and adjusts the timing of membership fee payments based on the estimated emotions. For example, if an idol or entertainer is nervous, the payment timing can be delayed to give them time to relax. Also, if an idol or entertainer is excited, the payment timing can be advanced to keep them calm. Also, if an idol or entertainer is tired, the payment timing can be adjusted to increase their energy. This improves the smoothness of payments by providing payment timing according to emotions.

[0117] The reception unit can select the optimal payment method by taking into consideration the geographic location information of the idol or entertainer when accepting the membership fee. Geographic location information includes, for example, GPS data and address information. The reception unit selects the optimal payment method by taking into consideration the geographic location information of the idol or entertainer when accepting the membership fee. For example, if the idol or entertainer is overseas, an international payment method can be provided. Also, if the idol or entertainer is in a rural area, a local bank payment method can be provided. The optimal payment method can also be provided based on the geographic location information of the idol or entertainer. In this way, by providing a payment method based on geographic location information, the smoothness of payments is improved.

[0118] The reception unit can select the optimal payment method by taking into consideration the device information of the idol or comedian when accepting the membership fee. Device information includes, for example, the device type (smartphone, tablet, PC, etc.) and device setting information. The reception unit selects the optimal payment method by taking into consideration the device information of the idol or comedian when accepting the membership fee. For example, if the idol or comedian uses a smartphone, mobile payment can be provided. Also, if the idol or comedian uses a tablet, a payment method optimized for tablets can be provided. Also, if the idol or comedian uses a PC, online banking can be provided. In this way, by offering payment methods based on device information, the smoothness of payments is improved.

[0119] The reception unit can improve the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. Feedback includes, for example, survey results and evaluation comments. The reception unit improves the payment method by reflecting the idol's or comedian's feedback when receiving the membership fee. For example, the reception unit improves the payment method based on the idol's or comedian's feedback. The reception unit can also improve the payment plan based on the idol's or comedian's feedback. The reception unit can also provide the optimal payment method based on the idol's or comedian's feedback. In this way, providing a payment method based on feedback improves the smoothness of payments. === Hard Collateral 1-1 === Each of the multiple elements, including the instruction generation unit, instruction provision unit, training plan generation unit, training plan provision unit, and reception unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the instruction generation unit is realized by the processor 46 of the smart device 14 and generates instructions using a generation AI. The instruction provision unit is realized by the output device 40 of the smart device 14 and provides the generated instructions in real time. The training plan generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a training plan using a generation AI. The training plan provision unit is realized by the output device 40 of the smart device 14 and provides the generated training plan. The reception unit is realized by the reception device 38 of the smart device 14 and receives membership fees. === Hard Collateral 1-2 === Each of the multiple elements, including the instruction generation unit, instruction provision unit, training plan generation unit, training plan provision unit, and reception unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the instruction generation unit is realized by the processor 46 of the smart glasses 214 and generates instructions using a generation AI. The instruction provision unit is realized by the speaker 240 of the smart glasses 214 and provides the generated instructions in real time. The training plan generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a training plan using a generation AI. The training plan provision unit is realized by the speaker 240 of the smart glasses 214 and provides the generated training plan. The reception unit is realized by the microphone 238 of the smart glasses 214 and receives membership fees. === Hard Collateral 1-3 === Each of the multiple elements, including the instruction generation unit, instruction provision unit, training plan generation unit, training plan provision unit, and reception unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the instruction generation unit is realized by the processor 46 of the headset-type terminal 314 and generates instructions using a generation AI. The instruction provision unit is realized by the speaker 240 of the headset-type terminal 314 and provides the generated instructions in real time. The training plan generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a training plan using a generation AI. The training plan provision unit is realized by the speaker 240 of the headset-type terminal 314 and provides the generated training plan. The reception unit is realized by the microphone 238 of the headset-type terminal 314 and receives membership fees. === Hard Collateral 1-4 === Each of the multiple elements including the instruction generation unit, instruction provision unit, training plan generation unit, training plan provision unit, and reception unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the instruction generation unit is realized by the processor 46 of the robot 414 and generates instructions using a generation AI. The instruction provision unit is realized by the speaker 240 of the robot 414 and provides the generated instructions in real time. The training plan generation unit is realized by the specific processing unit 290 of the data processing device 12 and generates a training plan using a generation AI. The training plan provision unit is realized by the speaker 240 of the robot 414 and provides the generated training plan. The reception unit is realized by the microphone 238 of the robot 414 and receives membership fees.

[0120] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0121] The next-generation talent agency system may further include a performance evaluation unit. The performance evaluation unit evaluates the performers' performances in real time and feeds back the evaluation results to the instruction generation unit. For example, the performance evaluation unit may evaluate how the audience receives what the performers say in a talk show and adjust the next instructions based on the evaluation results. The performance evaluation unit may also analyze the performers' facial expressions and tone of voice to detect changes in their emotions. This may enable the performance evaluation unit to generate instructions to relax if the performers are nervous, or to generate instructions to encourage them to concentrate if the performers are too relaxed. Furthermore, the performance evaluation unit may analyze the viewers' real-time reactions and adjust the instructions based on the viewers' emotions. This may optimize the performers' performances and increase viewer satisfaction.

[0122] The next-generation talent agency system may further include a schedule management unit. The schedule management unit manages the schedules of performers and provides feedback to the training plan generation unit. For example, if a performer has a busy schedule, the training plan generation unit can generate a short and effective training plan. The schedule management unit can also take performers' rest times into consideration and make adjustments to avoid excessive training. Furthermore, the schedule management unit can suggest optimal training times based on the performers' schedules. This makes it possible to provide flexible training plans that fit the performers' schedules and support efficient training.

[0123] The next-generation talent agency system can further include a health management unit. The health management unit monitors the health status of performers and provides the data to the training plan generation unit. For example, it can analyze the performer's heart rate and sleep data to generate a training plan based on their health status. The health management unit can also manage the performer's diet and nutritional status and provide advice to support healthy lifestyle habits. Furthermore, the health management unit can suggest a training plan to help performers relax if they are feeling stressed. This makes it possible to provide training plans based on the performer's health status and support the improvement of their overall performance.

[0124] The next-generation talent agency system may further include a feedback collection unit. The feedback collection unit collects feedback from performers and viewers and provides the data to the instruction generation unit and the training plan generation unit. For example, the feedback collection unit may collect information about how performers feel about a training plan and adjust the plan based on the feedback. The feedback collection unit may also collect viewers' reactions and generate instructions tailored to the viewers' preferences. Furthermore, the feedback collection unit may collect evaluations of the performers' performances and provide instructions to improve the next performance based on the evaluations. This makes it possible to utilize feedback from performers and viewers to provide more effective training plans and instructions.

[0125] The next-generation talent agency system can further include an emotion analysis unit. The emotion analysis unit performs a detailed analysis of the performers' emotions and provides the results to the instruction generation unit and training plan generation unit. For example, it can analyze the performers' facial expressions and tone of voice to detect changes in their emotions. The emotion analysis unit can also generate instructions to relax the performers if they are nervous, or instructions to encourage them to concentrate if they are too relaxed. Furthermore, the emotion analysis unit can adjust the content of the training plan based on the performers' emotions. This allows the provision of instructions and training plans that are appropriate for the performers' emotions, improving the quality of their performance.

[0126] The next-generation talent agency system may further include an audience analysis unit. The audience analysis unit analyzes audience responses in real time and provides the data to the instruction generation unit. For example, the audience analysis unit may analyze audience comments and reactions to understand audience emotions and interests. The audience analysis unit may also adjust instructions to performers based on audience responses. For example, if viewers show interest in a particular topic, it may generate instructions related to that topic. The audience analysis unit may also adjust the progress of the program based on audience responses. This allows for providing instructions according to audience responses and improving the quality of the program.

[0127] The next-generation talent agency system may further include a performance prediction unit. The performance prediction unit predicts future performances based on the performer's past performance data and provides the results to the instruction generation unit. For example, the performance prediction unit may analyze the patterns of the performer's past successful performances and generate instructions to replicate similar success. The performance prediction unit may also generate instructions to help the performer avoid performances that failed in the past. Furthermore, the performance prediction unit may analyze the performer's performance trends and provide optimal instructions. This makes it possible to optimize the performer's performance by utilizing predictions based on past data.

[0128] The next-generation talent agency system can further include a content generation unit. The content generation unit generates new content based on the performers' performances and provides that content to the instruction generation unit. For example, the content generation unit can suggest the next topic based on what the performers said in a talk show. The content generation unit can also analyze the performers' performances and suggest new plans or ideas based on the results. Furthermore, the content generation unit can generate content that will interest viewers based on their reactions. This allows for the provision of new content based on the performers' performances, improving the quality of the program.

[0129] The next-generation talent agency system can further include a performance improvement unit. The performance improvement unit monitors the performers' performances in real time and, based on that data, identifies areas for improvement. For example, it can analyze the performers' tone of voice and facial expressions when they speak at a talk show and provide the instruction generation unit with areas for improvement. The performance improvement unit can also analyze the performers' movements and posture and provide advice on how to perform more effectively. Furthermore, the performance improvement unit can suggest performance styles that viewers prefer based on their reactions. This allows for continuous improvement of the performers' performances and increases viewer satisfaction.

[0130] The next-generation talent agency system can further include an emotion feedback unit. The emotion feedback unit monitors the emotions of performers in real time and provides the data to the instruction generation unit and the training plan generation unit. For example, if a performer is nervous, it can generate instructions to help them relax, and conversely, if they are too relaxed, it can generate instructions to encourage them to concentrate. The emotion feedback unit can also adjust the content of the training plan based on the performer's emotions. Furthermore, the emotion feedback unit can analyze the emotions of viewers and provide instructions according to the viewers' emotions. This allows for providing feedback based on the emotions of performers and viewers to improve the quality of performance.

[0131] The processing flow of the second embodiment will be briefly explained below.

[0132] Step 1: The instruction generation unit generates instructions using a generation AI. For example, it generates instructions to adjust the content and timing of what a performer says during a talk show. It can also estimate the performer's emotions and adjust the content of the instructions based on the estimated emotions. For example, if a performer is nervous, it can generate instructions to help them relax. Step 2: The instruction providing unit provides the generated instructions in real time. For example, the generated instructions are displayed to the performers in real time. The unit can also estimate the performers' emotions and adjust the way the instructions are displayed based on the estimated emotions. For example, if the performers are nervous, a simple, highly visible display method can be provided. Step 3: The training plan generation unit uses generation AI to generate a training plan. For example, it generates a training plan based on the idol's or comedian's goals and aspirations. It can also estimate the idol's or comedian's emotions and adjust the content of the training plan based on the estimated emotions. For example, if the idol or comedian is nervous, it can generate a training plan to help them relax. Step 4: The training plan providing unit provides the generated training plan. For example, the generated training plan is provided to an idol or comedian. The unit can also estimate the emotions of the idol or comedian and adjust the display method of the training plan based on the estimated emotions. For example, if the idol or comedian is nervous, a simple, highly visible display method can be provided. Step 5: The reception unit accepts membership fees. For example, it accepts membership fees from idols or comedians. It can also estimate the emotions of idols or comedians and adjust the payment method for the membership fees based on the estimated emotions. For example, if an idol or comedian is nervous, it can provide a simple and highly visible payment method.

[0133] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0138] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] 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.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0147] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0153] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0154] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] 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.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] 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.

[0161] 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.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0169] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0170] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0177] 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.

[0178] 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.

[0179] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0180] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0181] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0182] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0187] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0188] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0189] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0190] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0191] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0192] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0193] 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.

[0194] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0195] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0196] 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.

[0197] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0198] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0199] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0200] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0201] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0202] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0203] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0204] [Explanation of symbols]

[0205] 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. an instruction generation unit that generates an instruction; an instruction providing unit that provides the instruction generated by the instruction generating unit; a training plan generation unit that generates a training plan; a training plan providing unit that provides the training plan generated by the training plan generating unit; A reception unit that receives membership fees. A system characterized by:

2. The instruction generation unit Generate instructions using generative AI 2. The system of claim 1.

3. The instruction providing unit Provide generated instructions in real time 2. The system of claim 1.

4. The training plan generation unit Generate training plans using generative AI 2. The system of claim 1.

5. The training plan providing unit Providing generated training plans 2. The system of claim 1.

6. The reception unit Accept affiliation fees 2. The system of claim 1.

7. The instruction generation unit Estimate the emotions of the performers and adjust the instructions based on those emotions 2. The system of claim 1.

8. The instruction generation unit Analyze the program's progress in real time and generate appropriate instructions 2. The system of claim 1.

Images