system

Abstract

The system according to the embodiment aims to flexibly adjust the performance in accordance with the actions of the performers and improve the quality of the performance. [Solution] A system according to an embodiment includes an observation unit, a progression unit, an adjustment unit, a tuning unit, and a provision unit. The observation unit observes the actions of performers. The progression unit progresses the performance based on the actions observed by the observation unit. The adjustment unit fine-tunes the performance based on the performance progressed by the progression unit. The tuning unit tunes the performance plan based on the performance adjusted by the adjustment unit. The provision unit improves the quality of the performance based on the performance plan tuned by the tuning unit.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it is difficult to flexibly change the direction to accommodate ad-libs or line mistakes by performers, and there is room for improvement in the quality of the direction.

[0005] The system according to the embodiment aims to flexibly adjust the performance in accordance with the actions of the performers and improve the quality of the performance. [Means for solving the problem]

[0006] The system according to the embodiment includes an observation unit, a progression unit, an adjustment unit, a tuning unit, and a provision unit. The observation unit observes the actions of the performers. The progression unit progresses the performance based on the actions observed by the observation unit. The adjustment unit fine-tunes the performance based on the performance progressed by the progression unit. The tuning unit tunes the performance plan based on the performance adjusted by the adjustment unit. The provision unit improves the quality of the performance based on the performance plan tuned by the tuning unit. [Effects of the Invention]

[0007] The system according to the embodiment can flexibly adjust the performance according to the actions of the performers, thereby improving the quality of the 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 directing support system according to an embodiment of the present invention is a system that uses generative AI to support directing. This directing support system observes the behavior of actors, compares the script with the script to advance the performance at the appropriate timing, fine-tunes the performance, and tunes the directing plan, thereby improving the quality of the performance. This allows the directing support system to advance, fine-tune, and tune the performance based on the actors' behavior, thereby improving the quality of the performance. For example, it can control lighting, background music, and the movement of stage equipment according to the actors' facial expressions, movements, and tone of their lines. It can also adjust the directing plan according to the actors' personalities and optimize it based on the diagnostic results of rehearsals and rehearsals. This allows directors to collaborate with generative AI to improve the quality of their performances.

[0029] The production support system according to the embodiment includes an observation unit, a progression unit, an adjustment unit, a tuning unit, and a provision unit. The observation unit observes the actions of actors. For example, the observation unit can observe the actors' movements, facial expressions, and lines using a camera or microphone. The observation unit can also observe changes in the actors' body temperature using thermography. The progression unit progresses the production based on the actions observed by the observation unit. For example, the progression unit can adjust the timing of the production by comparing it with a script. The progression unit can also control lighting and background music according to the progress of the actors' movements and lines. The adjustment unit analyzes the actors' facial expressions, movements, and tone of their lines and fine-tunes the production according to the nuances. For example, the adjustment unit can estimate the actors' emotions using a generation AI and adjust the color and intensity of the lighting and the tone and tempo of the background music. The tuning unit fine-tunes the production plan according to the individual personalities of the actors or performers. The tuning unit can, for example, adjust the color of lighting to match the performer's skin color or adjust the tempo of background music to match the performer's acting style. The providing unit diagnoses how its directing is affecting the performer's performance during practice and rehearsals and adjusts the directing plan. The providing unit can observe the performer's performance using, for example, a camera, microphone, or thermography, and optimize the directing plan based on that data. As a result, the directing support system according to the embodiment can progress, fine-tune, and tune the directing based on the performer's behavior, thereby improving the quality of the directing.

[0030] The observation unit can observe the actor's actions using a camera or a microphone. The observation unit can, for example, use a camera to observe the actor's movements and facial expressions. For example, the observation unit can capture subtle changes in the actor's facial expressions using a high-resolution camera. The observation unit can also use a microphone to observe the actor's lines and tone of voice. For example, the observation unit can capture subtle changes in the actor's voice using a high-sensitivity microphone. This allows the actor's actions to be observed in detail using a camera or microphone. Some or all of the above-mentioned processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input video data acquired by a camera into the generation AI and have the generation AI analyze the actor's facial expressions and movements from the video data.

[0031] The facilitator can proceed with the performance based on the observed behavior and in comparison with the script. For example, the facilitator can proceed with the performance based on the observed behavior and in comparison with a specific scene in the script. For example, the facilitator can adjust the color and intensity of lighting according to the timing of the actor's movements and lines. The facilitator can also adjust the tone and tempo of background music according to the actor's facial expressions and movements. For example, if the actor has a sad expression, the facilitator can dim the lights and lower the tone of the background music. This allows the performance to proceed at the appropriate timing by comparing with the script. Some or all of the above-mentioned processing in the facilitator may be performed using, for example, AI, or may be performed without using AI. For example, the facilitator can input data acquired by the observation unit into a generation AI, which then compares the data with the script and executes the performance.

[0032] The adjustment unit can analyze the facial expressions, movements, and tone of the lines of an actor and fine-tune the production according to their meaning. The adjustment unit, for example, analyzes the facial expressions of an actor and adjusts the color and intensity of lighting according to the emotion. For example, if the actor is smiling, the adjustment unit can brighten the lighting and use warmer colors. The adjustment unit can also analyze the actor's movements and adjust the movement of stage equipment according to those movements. For example, if the actor moves to the center of the stage, the adjustment unit can move the stage equipment to emphasize the actor. The adjustment unit can also analyze the tone of the actor's lines and adjust the tone and tempo of the background music according to that tone. For example, if the actor is speaking in a low tone, the adjustment unit can lower the tone and slow the tempo of the background music. This allows fine-tuning the production according to the facial expressions, movements, and tone of the lines of an actor. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit inputs the data acquired by the observation unit into the generation AI, which then analyzes the actor's facial expressions, movements, and tone of dialogue to make fine adjustments to the production.

[0033] The tuning unit can tune the directing plan according to the individuality of the actor or performer. For example, the tuning unit adjusts the color of the lighting to match the actor's skin color. For example, if the actor has light skin, the tuning unit can slightly dim the lighting to bring out the skin color. The tuning unit can also adjust the tempo of the background music to match the performer's acting style. For example, if the performer is dancing vigorously, the tuning unit can speed up the tempo of the background music to enhance the performance. The tuning unit can also adjust the movement of the stage equipment according to the individuality of the actor or performer. For example, if the actor is performing a quiet scene, the tuning unit can minimize the movement of the stage equipment to allow the actor to focus on the performance. This makes it possible to provide a directing plan according to the individuality of the actor or performer. Some or all of the above-mentioned processing in the tuning unit may be performed using, or without, AI. For example, the tuning unit can input data acquired by the observation unit into a generation AI, which then tunes the directing plan according to the individuality of the actor or performer.

[0034] The data providing unit can evaluate how its direction affects the performers' performance during practice and rehearsals and adjust the directing plan. For example, the data providing unit can observe the performers' performance during practice and rehearsals and adjust the directing plan based on the data. For example, the data providing unit can observe the performers' movements and lines using a camera or microphone and analyze the data to optimize the directing plan. The data providing unit can also observe changes in the performers' body temperature using a thermograph and adjust the directing plan based on the data. For example, if the performer's body temperature is rising, the data providing unit can adjust the lighting intensity to reduce the performer's burden. This allows the directing plan to be adjusted based on the diagnosis results from practice and rehearsals. Some or all of the above-described processing by the data providing unit may be performed using, for example, AI, or may be performed without AI. For example, the data providing unit can input data acquired by the observation unit into a generation AI, which can then adjust the directing plan based on the performers' performance.

[0035] The observation unit can analyze the performer's past performance history and select the optimal observation method. For example, the observation unit can optimize the observation method for a specific scene based on the performer's past performance data. For example, the observation unit can analyze past performance data and optimize the observation method for a specific scene. The observation unit can also analyze the performer's past mistakes and successes and change the focus of observation. For example, the observation unit can analyze past mistakes and change the focus of observation to prevent similar mistakes from occurring. The observation unit can also select an observation method for a specific movement or facial expression based on the performer's past performance history. For example, the observation unit can select an observation method for a specific movement or facial expression based on the past performance history. This allows the optimal observation method to be selected based on the past performance history. Some or all of the above-mentioned processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input past performance data into a generation AI, which can select the optimal observation method.

[0036] During observation, the observation unit can perform filtering based on the actor's current role and the scene. For example, if the actor is performing a sad scene, the observation unit can focus on observing changes in facial expressions. For example, the observation unit can closely observe changes in the actor's facial expressions to capture the emotional expression of the sad scene. The observation unit can also observe the speed and accuracy of the actor's movements when the actor is performing an action scene. For example, the observation unit can observe the speed and accuracy of the actor's movements to evaluate the performance of the action scene. The observation unit can also observe the audience's reactions when the actor is performing a comedy scene and reflect them in the performance. For example, the observation unit can observe the audience's laughter and facial expressions to evaluate the effectiveness of the comedy scene. This allows filtering of observations based on the role and the scene. Some or all of the above-described processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data on the actor's role and the scene into the generation AI, which then performs filtering.

[0037] During observation, the observation unit can select the optimal observation means depending on the performer's input method. For example, when the performer speaks lines, the observation unit uses a microphone to observe audio data in detail. For example, the observation unit can use a high-sensitivity microphone to observe the tone and strength of the performer's voice in detail. Furthermore, when the performer expresses themselves through movements, the observation unit can also observe the accuracy of the movements using a camera. For example, the observation unit can use a high-resolution camera to observe the speed and accuracy of the performer's movements. Furthermore, when the performer expresses emotions through facial expressions, the observation unit can also observe changes in facial expressions using facial recognition technology. For example, the observation unit can observe subtle changes in the performer's facial expressions using facial recognition technology. This allows the optimal observation means to be selected depending on the input method. Some or all of the above-mentioned processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data on the performer's input method into the generation AI, which can select the optimal observation means.

[0038] During observation, the observation unit can prioritize observing highly relevant behavior based on the actor's geographical location information. For example, when an actor performs at a specific location, the observation unit prioritizes observing behavior related to that location. For example, when an actor performs at a specific location, the observation unit can prioritize observing behavior related to that location. Furthermore, when an actor is moving, the observation unit can prioritize observing behavior related to movement. For example, when an actor is moving, the observation unit can prioritize observing behavior related to movement. Furthermore, when an actor is at a position in a specific scene, the observation unit can prioritize observing behavior related to that scene. For example, when an actor is at a position in a specific scene, the observation unit can prioritize observing behavior related to that scene. This makes it possible to prioritize observing highly relevant behavior based on geographical location information. Some or all of the above-described processing in the observation unit may be performed using, or without, AI. For example, the observation unit can input data on the actor's geographical location information to the generation AI, which can prioritize observing highly relevant behavior.

[0039] During observation, the observation unit can analyze the social media activity of the performer and observe related behavior. The observation unit, for example, observes related behavior based on content shared by the performer on social media. For example, the observation unit can observe related behavior based on content shared by the performer on social media. The observation unit can also analyze responses of the performer's social media followers and observe related behavior. For example, the observation unit can analyze responses of the performer's social media followers and observe related behavior. The observation unit can also observe related behavior based on the performer's social media activity history. For example, the observation unit can observe related behavior based on the performer's social media activity history. In this way, related behavior can be observed based on social media activity. Some or all of the above-described processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data on the performer's social media activity into the generation AI, which can observe related behavior.

[0040] During observation, the observation unit can customize the observation method based on the performer's past feedback. The observation unit, for example, adjusts the observation method based on feedback provided by the performer in the past. For example, the observation unit can adjust the observation method based on feedback provided by the performer in the past. The observation unit can also preferentially use a specific observation method based on the performer's past feedback. For example, the observation unit can preferentially use a specific observation method based on the performer's past feedback. The observation unit can also improve the accuracy of observation by reflecting the performer's past feedback. For example, the observation unit can improve the accuracy of observation by reflecting the performer's past feedback. This allows the observation method to be customized based on the past feedback. Some or all of the above-described processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data of the performer's past feedback into the generation AI, which can customize the observation method.

[0041] The progression unit can adjust the level of detail of the progression based on the priority of a scene during progression. For example, in important scenes, the progression unit provides detailed progression and gives detailed instructions to the actor's actions and lines. For example, the progression unit can provide detailed instructions to the actor's actions and lines in important scenes to increase the precision of the direction. The progression unit can also reduce the level of detail of the progression in less important scenes to increase the actor's freedom. For example, the progression unit can increase the actor's freedom in less important scenes to enhance natural acting. The progression unit can also dynamically adjust the level of detail of the progression based on the importance of a scene. For example, the progression unit can dynamically adjust the level of detail of the progression based on the importance of a scene to maximize the effect of the direction. This allows the level of detail of the progression to be adjusted based on the importance of a scene. Some or all of the above-mentioned processing in the progression unit may be performed using, or without, AI. For example, the progression unit can input data on the importance of a scene to a generation AI, which can adjust the level of detail of the progression.

[0042] The progression unit can apply different progression algorithms depending on the scene category during progression. For example, in a drama scene, the progression unit applies a progression algorithm that emphasizes emotional expression. For example, the progression unit can apply a progression algorithm that emphasizes emotional expression in a drama scene to highlight the emotions of the actors. The progression unit can also apply a progression algorithm that emphasizes the accuracy of movements in an action scene. For example, the progression unit can apply a progression algorithm that emphasizes the accuracy of movements in an action scene to emphasize the actors' movements. The progression unit can also apply a progression algorithm that emphasizes timing in a comedy scene. For example, the progression unit can apply a progression algorithm that emphasizes timing in a comedy scene to elicit laughter from the audience. In this way, progression algorithms can be applied depending on the scene category. Some or all of the above-mentioned processing in the progression unit may be performed using AI, for example, or may be performed without using AI. For example, the progression unit can input data on the scene category into a generation AI, which can apply a different progression algorithm.

[0043] During progression, the progression unit can improve the accuracy of progression based on the performer's past progression results. The progression unit, for example, analyzes the performer's past progression results to improve the accuracy of progression. For example, the progression unit can analyze the performer's past progression results to improve the accuracy of progression. The progression unit can also optimize the progression method by referring to the performer's past successes. For example, the progression unit can optimize the progression method by referring to the performer's past successes. The progression unit can also analyze the performer's past failures to find areas for improvement in progression. For example, the progression unit can analyze the performer's past failures to find areas for improvement in progression. This allows the accuracy of progression to be improved based on the past progression results. Some or all of the above-mentioned processing in the progression unit may be performed using, for example, AI, or may be performed without using AI. For example, the progression unit can input data on the performer's past progression results into a generation AI, which can improve the accuracy of progression.

[0044] During progression, the progression unit can determine the priority of progression based on the timing of scene submission. For example, the progression unit prioritizes scenes whose submission deadline is approaching. For example, the progression unit can prioritize scenes whose submission deadline is approaching. The progression unit can also postpone scenes whose submission time is more flexible. For example, the progression unit can postpone scenes whose submission time is more flexible. The progression unit can also dynamically adjust the priority of progression based on the submission time. For example, the progression unit can dynamically adjust the priority of progression based on the submission time. This makes it possible to determine the priority of progression based on the submission time. Some or all of the above-mentioned processing in the progression unit may be performed using AI, for example, or may be performed without using AI. For example, the progression unit can input data on the submission time of scenes to a generation AI, and the generation AI can determine the priority of progression.

[0045] The progression unit can adjust the order of progression based on the relevance of scenes during progression. The progression unit, for example, progresses highly relevant scenes consecutively. For example, the progression unit can progress highly relevant scenes consecutively. The progression unit can also progress less relevant scenes at intervals. For example, the progression unit can progress less relevant scenes at intervals. The progression unit can also dynamically adjust the order of progression based on the relevance of scenes. For example, the progression unit can dynamically adjust the order of progression based on the relevance of scenes. This allows the order of progression to be adjusted based on the relevance of scenes. Some or all of the above-described processing in the progression unit may be performed using AI, for example, or may be performed without using AI. For example, the progression unit can input data on the relevance of scenes to a generation AI, and the generation AI can adjust the order of progression.

[0046] The facilitator can adjust the use of technical terms in the facilitator's presentation depending on the level of expertise of the performer. For example, the facilitator can use a lot of technical terms for a performer with high expertise. For example, the facilitator can use a lot of technical terms for a performer with high expertise. The facilitator can also use simple language for a performer with low expertise. For example, the facilitator can use simple language for a performer with low expertise. The facilitator can also dynamically adjust the use of technical terms in the facilitator's presentation depending on the performer's level of expertise. In this way, the use of technical terms in the facilitator can be adjusted depending on the level of expertise. Some or all of the above-described processing in the facilitator may be performed using, for example, AI, or may be performed without AI. For example, the facilitator can input data on the performer's level of expertise to a generation AI, which can adjust the use of technical terms in the facilitator's presentation.

[0047] During adjustment, the adjustment unit can improve the accuracy of the adjustment based on the interrelationships between scenes. The adjustment unit, for example, analyzes the interrelationships between scenes and improves the accuracy of the adjustment. For example, the adjustment unit can analyze the interrelationships between scenes and improve the accuracy of the adjustment. The adjustment unit can also optimize the adjustment method based on the interrelationships between scenes. For example, the adjustment unit can optimize the adjustment method based on the interrelationships between scenes. The adjustment unit can also change the focus of the adjustment by taking the interrelationships between scenes into consideration. For example, the adjustment unit can change the focus of the adjustment by taking the interrelationships between scenes into consideration. This can improve the accuracy of the adjustment by taking the interrelationships between scenes into consideration. Some or all of the above-described processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input data on the interrelationships between scenes to a generation AI, which can improve the accuracy of the adjustment.

[0048] The adjustment unit can make adjustments taking into account the performer's attribute information during adjustment. The adjustment unit changes the adjustment method depending on, for example, the performer's age and gender. For example, the adjustment unit can change the adjustment method depending on the performer's age and gender. The adjustment unit can also change the accuracy of the adjustment depending on the performer's experience and skill. For example, the adjustment unit can change the accuracy of the adjustment depending on the performer's experience and skill. The adjustment unit can also change the focus of the adjustment based on the performer's attribute information. For example, the adjustment unit can change the focus of the adjustment based on the performer's attribute information. This allows adjustments to be made based on the performer's attribute information. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input data on the performer's attribute information into a generation AI, and the generation AI can make the adjustments.

[0049] During adjustment, the adjustment unit can weight the adjustment based on the number of times a scene is submitted. For example, the adjustment unit prioritizes adjustment of scenes that are submitted frequently. For example, the adjustment unit can prioritize adjustment of scenes that are submitted frequently. The adjustment unit can also postpone scenes that are submitted less frequently. For example, the adjustment unit can postpone scenes that are submitted less frequently. The adjustment unit can also dynamically change the weight of the adjustment based on the submission frequency. For example, the adjustment unit can dynamically change the weight of the adjustment based on the submission frequency. This allows the weight of the adjustment to be based on the submission frequency. Some or all of the above-described processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input data on the number of times a scene is submitted to a generation AI, and the generation AI can perform the weight of the adjustment.

[0050] During adjustment, the adjustment unit can make adjustments based on the geographical distribution of the scene. For example, when a scene takes place in different locations, the adjustment unit can make adjustments appropriate for each location. For example, when a scene takes place in different locations, the adjustment unit can make adjustments appropriate for each location. The adjustment unit can also change the adjustment method based on the geographical distribution of the scene. For example, the adjustment unit can change the adjustment method based on the geographical distribution of the scene. The adjustment unit can also change the focus of the adjustment taking into account the geographical distribution of the scene. For example, the adjustment unit can change the focus of the adjustment taking into account the geographical distribution of the scene. This allows adjustments to be made based on the geographical distribution. Some or all of the above-described processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input data on the geographical distribution of the scene to a generation AI, which can then make the adjustments.

[0051] During adjustment, the adjustment unit can improve the accuracy of the adjustment by referring to literature related to the scene. For example, the adjustment unit can improve the accuracy of the adjustment by referring to literature related to the scene. The adjustment unit can also optimize the adjustment method based on literature related to the scene. For example, the adjustment unit can optimize the adjustment method based on literature related to the scene. The adjustment unit can also change the focus of the adjustment by taking into account literature related to the scene. For example, the adjustment unit can change the focus of the adjustment by taking into account literature related to the scene. This can improve the accuracy of the adjustment based on the related literature. Some or all of the above-mentioned processing in the adjustment unit can be performed using AI, for example, or can be performed without using AI. For example, the adjustment unit can input data of literature related to the scene into a generation AI, which can improve the accuracy of the adjustment.

[0052] The adjustment unit can perform the adjustment based on the market value of the scene when making the adjustment. For example, the adjustment unit prioritizes adjusting scenes with high market value. For example, the adjustment unit can prioritize adjusting scenes with high market value. The adjustment unit can also postpone scenes with low market value. For example, the adjustment unit can postpone scenes with low market value. The adjustment unit can also dynamically change the weighting of the adjustment based on the market value. For example, the adjustment unit can dynamically change the weighting of the adjustment based on the market value. This allows the adjustment to be made based on the market value. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input data on the market value of the scene to the generation AI, and the generation AI can make the adjustment.

[0053] During tuning, the tuning unit can select an optimal tuning method based on the performer's past performance. The tuning unit selects the optimal tuning method based on, for example, the performer's past performance data. For example, the tuning unit can select the optimal tuning method based on the performer's past performance data. The tuning unit can also optimize the tuning method by referring to the performer's past successes. For example, the tuning unit can optimize the tuning method by referring to the performer's past successes. The tuning unit can also analyze the performer's past failures to find areas for improvement in tuning. For example, the tuning unit can analyze the performer's past failures to find areas for improvement in tuning. This allows the optimal tuning method to be selected based on past performance. Some or all of the above-described processing in the tuning unit may be performed using, for example, AI, or may be performed without using AI. For example, the tuning unit can input the performer's past performance data into a generation AI, which can select the optimal tuning method.

[0054] The tuning unit can customize the tuning means based on the actor's current character during tuning. For example, if the actor is playing a sad character, the tuning unit can adjust the color and intensity of lighting. For example, if the actor is playing a sad character, the tuning unit can adjust the color and intensity of lighting. The tuning unit can also adjust the sound settings if the actor is playing an action scene. For example, the tuning unit can adjust the sound settings if the actor is playing an action scene. The tuning unit can also adjust the tempo of background music if the actor is playing a comedy scene. For example, the tuning unit can adjust the tempo of background music if the actor is playing a comedy scene. This allows the tuning means to be customized based on the current character. Some or all of the above-described processing in the tuning unit may be performed using AI, for example, or may be performed without using AI. For example, the tuning unit can input data of the actor's current character into a generation AI, which can customize the tuning means.

[0055] The tuning unit can improve the tuning method based on the performer's feedback during tuning. The tuning unit can improve the tuning method based on, for example, feedback provided by the performer. For example, the tuning unit can improve the tuning method based on the feedback provided by the performer. The tuning unit can also preferentially use a specific tuning method based on the performer's feedback. For example, the tuning unit can preferentially use a specific tuning method based on the performer's feedback. The tuning unit can also improve the tuning accuracy by reflecting the performer's feedback. For example, the tuning unit can improve the tuning accuracy by reflecting the performer's feedback. This allows the tuning method to be improved based on the feedback. Some or all of the above-mentioned processing in the tuning unit may be performed using, for example, AI, or may be performed without using AI. For example, the tuning unit can input data of the performer's feedback into a generation AI, which can improve the tuning method.

[0056] The tuning unit can select an optimal tuning method based on the geographical location information of the performer when tuning. For example, when a performer performs at a specific location, the tuning unit selects a tuning method appropriate for that location. For example, when a performer performs at a specific location, the tuning unit can select a tuning method appropriate for that location. The tuning unit can also change the tuning method based on the geographical location information of the performer. For example, the tuning unit can change the tuning method based on the geographical location information of the performer. The tuning unit can also change the emphasis of tuning by taking into account the geographical location information of the performer. For example, the tuning unit can change the emphasis of tuning by taking into account the geographical location information of the performer. This makes it possible to select an optimal tuning method based on the geographical location information. Some or all of the above-described processing in the tuning unit may be performed using, or without, AI. For example, the tuning unit can input data on the geographical location information of the performer to a generation AI, which can select an optimal tuning method.

[0057] During tuning, the tuning unit can analyze the social media activity of the performer and suggest tuning methods. The tuning unit can suggest tuning methods based on, for example, content shared by the performer on social media. For example, the tuning unit can suggest tuning methods based on content shared by the performer on social media. The tuning unit can also analyze the reactions of the performer's followers on social media and suggest tuning methods. For example, the tuning unit can analyze the reactions of the performer's followers on social media and suggest tuning methods. The tuning unit can also suggest tuning methods based on the performer's social media activity history. For example, the tuning unit can suggest tuning methods based on the performer's social media activity history. In this way, tuning methods can be suggested based on social media activity. Some or all of the above-described processing in the tuning unit may be performed using, for example, AI, or may be performed without using AI. For example, the tuning unit can input data on the performer's social media activity into a generation AI, which can suggest tuning methods.

[0058] The tuning unit can customize the tuning method based on the performer's past feedback during tuning. The tuning unit customizes the tuning method based on, for example, feedback provided by the performer in the past. For example, the tuning unit can customize the tuning method based on feedback provided by the performer in the past. The tuning unit can also preferentially use a specific tuning method based on the performer's past feedback. For example, the tuning unit can preferentially use a specific tuning method based on the performer's past feedback. The tuning unit can also improve the tuning accuracy by reflecting the performer's past feedback. For example, the tuning unit can improve the tuning accuracy by reflecting the performer's past feedback. This allows the tuning method to be customized based on the past feedback. Some or all of the above-described processing in the tuning unit may be performed using AI, for example, or may be performed without using AI. For example, the tuning unit can input data of the performer's past feedback into a generation AI, which can customize the tuning method.

[0059] The providing unit can optimize the providing algorithm based on past provided data at the time of providing. The providing unit, for example, analyzes past provided data and selects an optimal providing algorithm. For example, the providing unit can analyze past provided data and select an optimal providing algorithm. The providing unit can also optimize the providing algorithm by referring to past successful examples. For example, the providing unit can optimize the providing algorithm by referring to past successful examples. The providing unit can also analyze past failure examples and find improvements to the providing algorithm. For example, the providing unit can analyze past failure examples and find improvements to the providing algorithm. This allows the providing algorithm to be optimized based on the past provided data. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past provided data to a generating AI, which can optimize the providing algorithm.

[0060] The providing unit can update the provided data by reflecting the performer's feedback when providing the data. The providing unit, for example, updates the provided data based on feedback provided by the performer. For example, the providing unit can update the provided data based on feedback provided by the performer. The providing unit can also preferentially use a specific providing method based on the performer's feedback. For example, the providing unit can preferentially use a specific providing method based on the performer's feedback. The providing unit can also improve the accuracy of the provided data by reflecting the performer's feedback. For example, the providing unit can improve the accuracy of the provided data by reflecting the performer's feedback. This allows the provided data to be updated based on the feedback. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the performer's feedback data to the generating AI, which can update the provided data.

[0061] At the time of provision, the provision unit can select the optimal provision method by analyzing the performer's past performance. The provision unit selects the optimal provision method, for example, based on the performer's past performance data. For example, the provision unit can select the optimal provision method based on the performer's past performance data. The provision unit can also optimize the provision method by referring to the performer's past success stories. For example, the provision unit can optimize the provision method by referring to the performer's past success stories. The provision unit can also analyze the performer's past failure stories and find areas for improvement in the provision method. For example, the provision unit can analyze the performer's past failure stories and find areas for improvement in the provision method. This makes it possible to select the optimal provision method based on past performance. Some or all of the above-described processing in the provision unit may be performed using, for example, AI, or may be performed without using AI. For example, the provision unit can input the performer's past performance data into a generation AI, which can select the optimal provision method.

[0062] The providing unit can weight the provided data based on the submission timing of the scene when providing the data. For example, the providing unit preferentially weights the provided data of a scene whose submission deadline is approaching. For example, the providing unit can preferentially weight the provided data of a scene whose submission deadline is approaching. The providing unit can also postpone the provided data of a scene whose submission timing is more flexible. For example, the providing unit can postpone the provided data of a scene whose submission timing is more flexible. The providing unit can also dynamically adjust the weighting of the provided data based on the submission timing. For example, the providing unit can dynamically adjust the weighting of the provided data based on the submission timing. This makes it possible to weight the provided data based on the submission timing. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input data on the submission timing of a scene to the generating AI, and the generating AI can weight the provided data.

[0063] The providing unit can integrate information from different data sources to enhance the provided data when providing the data. The providing unit, for example, integrates information from different data sources to enhance the provided data. For example, the providing unit can integrate information from different data sources to enhance the provided data. The providing unit can also analyze information from different data sources to improve the accuracy of the provided data. For example, the providing unit can analyze information from different data sources to improve the accuracy of the provided data. The providing unit can also adjust the weighting of the provided data based on the information from different data sources. For example, the providing unit can adjust the weighting of the provided data based on the information from different data sources. This allows the information from different data sources to be integrated and enhanced. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input information from different data sources to a generation AI, which can integrate the information and enhance the provided data.

[0064] The providing unit can make a proposal based on the schedule based on the performer's calendar information at the time of providing. The providing unit, for example, refers to a schedule registered in the performer's calendar and adjusts the provided data. For example, the providing unit can refer to a schedule registered in the performer's calendar and adjust the provided data. The providing unit can also propose provided data related to a specific event from the performer's calendar information. For example, the providing unit can propose provided data related to a specific event from the performer's calendar information. The providing unit can also propose optimal provided data tailored to the schedule based on the performer's calendar information. For example, the providing unit can propose optimal provided data tailored to the schedule based on the performer's calendar information. This makes it possible to make a proposal tailored to the schedule based on the calendar information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the performer's calendar information to the generation AI, which can then make a proposal based on the schedule.

[0065] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0066] The observation unit can not only observe the actions of the performers, but also the status of the stage equipment. For example, the observation unit can capture the movements and positions of stage equipment with a camera and monitor the status of the stage equipment in real time. This allows for early detection of abnormalities in the stage equipment and a prompt response. The observation unit can also analyze the operation logs of the stage equipment and create maintenance plans for the equipment based on past operation history. Furthermore, the observation unit can obtain sensor information from the stage equipment and grasp the status of the stage equipment in detail. This makes it possible to monitor the status of the stage equipment and improve the quality of the production.

[0067] The performance unit not only advances the performance based on the actions of the performers, but can also adjust the timing of the performance based on the status of the stage equipment. For example, the performance unit can advance the next scene if the stage equipment is in the correct position. Also, if an abnormality occurs in the stage equipment, the performance unit can pause the performance and correct the abnormality. Furthermore, the performance unit can analyze the operation log of the stage equipment and optimize the timing of the performance based on the past operation history. This allows the performance to advance based on the status of the stage equipment, improving the quality of the performance.

[0068] The adjustment unit can not only analyze the facial expressions, movements, and tone of the lines of the performers, but also the state of the stage equipment to fine-tune the production. For example, the adjustment unit can adjust the color and intensity of the lighting according to the movement of the stage equipment. The adjustment unit can also adjust the tone and tempo of the background music according to the position of the stage equipment. Furthermore, the adjustment unit can analyze sensor information from the stage equipment and fine-tune the production based on the state of the stage equipment. This makes it possible to fine-tune the production based on the state of the stage equipment and improve the quality of the production.

[0069] The tuning unit can not only tune the directing plan according to the individuality of the actors and performers, but also adjust the directing plan based on the state of the stage equipment. For example, the tuning unit can adjust the color of the lighting according to the movement of the stage equipment. The tuning unit can also adjust the tempo of the background music according to the position of the stage equipment. Furthermore, the tuning unit can analyze sensor information from the stage equipment and adjust the directing plan based on the state of the stage equipment. This makes it possible to adjust the directing plan based on the state of the stage equipment and improve the quality of the performance.

[0070] The data provision unit can not only evaluate how its own direction is affecting the performers' performance during rehearsals and rehearsals, but also evaluate the state of the stage equipment and adjust the directing plan accordingly. For example, the data provision unit can analyze the operation log of the stage equipment and optimize the directing plan based on that data. The data provision unit can also acquire sensor information from the stage equipment and adjust the directing plan based on that data. Furthermore, the data provision unit can monitor the state of the stage equipment in real time and respond quickly if an abnormality occurs. This allows the directing plan to be adjusted based on the state of the stage equipment, improving the quality of the performance.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The observation unit observes the actor's actions. For example, the observation unit can use a camera or microphone to observe the actor's movements, facial expressions, and lines. It can also use thermography to observe changes in the actor's body temperature. Step 2: The facilitator advances the performance based on the actions observed by the observer. For example, the facilitator can adjust the timing of the performance by checking it against the script. The facilitator can also control lighting and background music according to the progress of the actors' movements and lines. Step 3: The adjustment unit analyzes the performer's facial expressions, movements, and tone of the lines, and fine-tunes the production accordingly. For example, the adjustment unit can use generative AI to estimate the performer's emotions and adjust the color and intensity of the lighting, the tone and tempo of the background music, etc. Step 4: The tuning department fine-tunes the production plan to suit the individuality of the actors and performers. For example, the tuning department can adjust the color of the lighting to match the actor's skin tone or the tempo of the background music to match the actor's acting style. Step 5: The production department assesses how their direction is affecting the performers' performance during rehearsals and rehearsals, and adjusts the production plan. For example, the production department can observe the performers' performance using cameras, microphones, and thermography, and use that data to optimize the production plan.

[0073] (Example 2) A directing support system according to an embodiment of the present invention is a system that uses generative AI to support directing. This directing support system observes the behavior of actors, compares the script with the script to advance the performance at the appropriate timing, fine-tunes the performance, and tunes the directing plan, thereby improving the quality of the performance. This allows the directing support system to advance, fine-tune, and tune the performance based on the actors' behavior, thereby improving the quality of the performance. For example, it can control lighting, background music, and the movement of stage equipment according to the actors' facial expressions, movements, and tone of their lines. It can also adjust the directing plan according to the actors' personalities and optimize it based on the diagnostic results of rehearsals and rehearsals. This allows directors to collaborate with generative AI to improve the quality of their performances.

[0074] The production support system according to the embodiment includes an observation unit, a progression unit, an adjustment unit, a tuning unit, and a provision unit. The observation unit observes the actions of actors. For example, the observation unit can observe the actors' movements, facial expressions, and lines using a camera or microphone. The observation unit can also observe changes in the actors' body temperature using thermography. The progression unit progresses the production based on the actions observed by the observation unit. For example, the progression unit can adjust the timing of the production by comparing it with a script. The progression unit can also control lighting and background music according to the progress of the actors' movements and lines. The adjustment unit analyzes the actors' facial expressions, movements, and tone of their lines and fine-tunes the production according to the nuances. For example, the adjustment unit can estimate the actors' emotions using a generation AI and adjust the color and intensity of the lighting and the tone and tempo of the background music. The tuning unit fine-tunes the production plan according to the individual personalities of the actors or performers. The tuning unit can, for example, adjust the color of lighting to match the performer's skin color or adjust the tempo of background music to match the performer's acting style. The providing unit diagnoses how its directing is affecting the performer's performance during practice and rehearsals and adjusts the directing plan. The providing unit can observe the performer's performance using, for example, a camera, microphone, or thermography, and optimize the directing plan based on that data. As a result, the directing support system according to the embodiment can progress, fine-tune, and tune the directing based on the performer's behavior, thereby improving the quality of the directing.

[0075] The observation unit can observe the actor's actions using a camera or a microphone. The observation unit can, for example, use a camera to observe the actor's movements and facial expressions. For example, the observation unit can capture subtle changes in the actor's facial expressions using a high-resolution camera. The observation unit can also use a microphone to observe the actor's lines and tone of voice. For example, the observation unit can capture subtle changes in the actor's voice using a high-sensitivity microphone. This allows the actor's actions to be observed in detail using a camera or microphone. Some or all of the above-mentioned processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input video data acquired by a camera into the generation AI and have the generation AI analyze the actor's facial expressions and movements from the video data.

[0076] The facilitator can proceed with the performance based on the observed behavior and in comparison with the script. For example, the facilitator can proceed with the performance based on the observed behavior and in comparison with a specific scene in the script. For example, the facilitator can adjust the color and intensity of lighting according to the timing of the actor's movements and lines. The facilitator can also adjust the tone and tempo of background music according to the actor's facial expressions and movements. For example, if the actor has a sad expression, the facilitator can dim the lights and lower the tone of the background music. This allows the performance to proceed at the appropriate timing by comparing with the script. Some or all of the above-mentioned processing in the facilitator may be performed using, for example, AI, or may be performed without using AI. For example, the facilitator can input data acquired by the observation unit into a generation AI, which then compares the data with the script and executes the performance.

[0077] The adjustment unit can analyze the facial expressions, movements, and tone of the lines of an actor and fine-tune the production according to their meaning. The adjustment unit, for example, analyzes the facial expressions of an actor and adjusts the color and intensity of lighting according to the emotion. For example, if the actor is smiling, the adjustment unit can brighten the lighting and use warmer colors. The adjustment unit can also analyze the actor's movements and adjust the movement of stage equipment according to those movements. For example, if the actor moves to the center of the stage, the adjustment unit can move the stage equipment to emphasize the actor. The adjustment unit can also analyze the tone of the actor's lines and adjust the tone and tempo of the background music according to that tone. For example, if the actor is speaking in a low tone, the adjustment unit can lower the tone and slow the tempo of the background music. This allows fine-tuning the production according to the facial expressions, movements, and tone of the lines of an actor. Some or all of the above-mentioned processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit inputs the data acquired by the observation unit into the generation AI, which then analyzes the actor's facial expressions, movements, and tone of dialogue to make fine adjustments to the production.

[0078] The tuning unit can tune the directing plan according to the individuality of the actor or performer. For example, the tuning unit adjusts the color of the lighting to match the actor's skin color. For example, if the actor has light skin, the tuning unit can slightly dim the lighting to bring out the skin color. The tuning unit can also adjust the tempo of the background music to match the performer's acting style. For example, if the performer is dancing vigorously, the tuning unit can speed up the tempo of the background music to enhance the performance. The tuning unit can also adjust the movement of the stage equipment according to the individuality of the actor or performer. For example, if the actor is performing a quiet scene, the tuning unit can minimize the movement of the stage equipment to allow the actor to focus on the performance. This makes it possible to provide a directing plan according to the individuality of the actor or performer. Some or all of the above-mentioned processing in the tuning unit may be performed using, or without, AI. For example, the tuning unit can input data acquired by the observation unit into a generation AI, which then tunes the directing plan according to the individuality of the actor or performer.

[0079] The data providing unit can evaluate how its direction affects the performers' performance during practice and rehearsals and adjust the directing plan. For example, the data providing unit can observe the performers' performance during practice and rehearsals and adjust the directing plan based on the data. For example, the data providing unit can observe the performers' movements and lines using a camera or microphone and analyze the data to optimize the directing plan. The data providing unit can also observe changes in the performers' body temperature using a thermograph and adjust the directing plan based on the data. For example, if the performer's body temperature is rising, the data providing unit can adjust the lighting intensity to reduce the performer's burden. This allows the directing plan to be adjusted based on the diagnosis results from practice and rehearsals. Some or all of the above-described processing by the data providing unit may be performed using, for example, AI, or may be performed without AI. For example, the data providing unit can input data acquired by the observation unit into a generation AI, which can then adjust the directing plan based on the performers' performance.

[0080] The observation unit can estimate the actor's emotions and adjust the timing of observation based on the estimated actor's emotions. For example, if the actor is nervous, the observation unit increases the frequency of observation to collect detailed data. For example, the observation unit can frequently observe the actor's facial expressions and movements to grasp the actor's level of nervousness in detail. Furthermore, if the actor is relaxed, the observation unit can reduce the frequency of observation to respect a natural performance. For example, the observation unit can observe the actor's movements and lines less frequently to enhance natural acting. Furthermore, if the actor is excited, the observation unit can adjust the timing of observation to avoid missing important moments. For example, the observation unit can observe the actor's facial expressions and movements in real time to capture peaks of excitement. This allows the timing of observation to be adjusted according to the actor's emotions. Some or all of the above-mentioned processing in the observation unit may be performed using, for example, AI, or may be performed without AI. For example, the observation unit can input data on the actor's facial expressions and movements into a generation AI, which can estimate the actor's emotions and adjust the timing of observation.

[0081] The observation unit can analyze the performer's past performance history and select the optimal observation method. For example, the observation unit can optimize the observation method for a specific scene based on the performer's past performance data. For example, the observation unit can analyze past performance data and optimize the observation method for a specific scene. The observation unit can also analyze the performer's past mistakes and successes and change the focus of observation. For example, the observation unit can analyze past mistakes and change the focus of observation to prevent similar mistakes from occurring. The observation unit can also select an observation method for a specific movement or facial expression based on the performer's past performance history. For example, the observation unit can select an observation method for a specific movement or facial expression based on the past performance history. This allows the optimal observation method to be selected based on the past performance history. Some or all of the above-mentioned processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input past performance data into a generation AI, which can select the optimal observation method.

[0082] During observation, the observation unit can perform filtering based on the actor's current role and the scene. For example, if the actor is performing a sad scene, the observation unit can focus on observing changes in facial expressions. For example, the observation unit can closely observe changes in the actor's facial expressions to capture the emotional expression of the sad scene. The observation unit can also observe the speed and accuracy of the actor's movements when the actor is performing an action scene. For example, the observation unit can observe the speed and accuracy of the actor's movements to evaluate the performance of the action scene. The observation unit can also observe the audience's reactions when the actor is performing a comedy scene and reflect them in the performance. For example, the observation unit can observe the audience's laughter and facial expressions to evaluate the effectiveness of the comedy scene. This allows filtering of observations based on the role and the scene. Some or all of the above-described processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data on the actor's role and the scene into the generation AI, which then performs filtering.

[0083] During observation, the observation unit can select the optimal observation means depending on the performer's input method. For example, when the performer speaks lines, the observation unit uses a microphone to observe audio data in detail. For example, the observation unit can use a high-sensitivity microphone to observe the tone and strength of the performer's voice in detail. Furthermore, when the performer expresses themselves through movements, the observation unit can also observe the accuracy of the movements using a camera. For example, the observation unit can use a high-resolution camera to observe the speed and accuracy of the performer's movements. Furthermore, when the performer expresses emotions through facial expressions, the observation unit can also observe changes in facial expressions using facial recognition technology. For example, the observation unit can observe subtle changes in the performer's facial expressions using facial recognition technology. This allows the optimal observation means to be selected depending on the input method. Some or all of the above-mentioned processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data on the performer's input method into the generation AI, which can select the optimal observation means.

[0084] The observation unit can estimate the actor's emotions and determine the priority of actions to be observed based on the estimated actor's emotions. For example, if the actor is nervous, the observation unit can prioritize observing actions that relieve tension. For example, the observation unit can observe the actor's facial expressions and movements and prioritize observing actions that relieve tension. Furthermore, if the actor is relaxed, the observation unit can select actions to be observed with an emphasis on natural performance. For example, the observation unit can observe the actor's movements and lines and prioritize observing natural performance. Furthermore, if the actor is excited, the observation unit can prioritize observing actions that enhance the actor's excitement. For example, the observation unit can observe the actor's facial expressions and movements and prioritize observing actions that enhance the actor's excitement. In this way, the priority of actions to be observed can be determined based on the actor's emotions. Some or all of the above-described processing in the observation unit may be performed using, or without, AI. For example, the observation unit can input data on the actor's emotions into the generation AI and determine the priority of actions to be observed by the generation AI.

[0085] During observation, the observation unit can prioritize observing highly relevant behavior based on the actor's geographical location information. For example, when an actor performs at a specific location, the observation unit prioritizes observing behavior related to that location. For example, when an actor performs at a specific location, the observation unit can prioritize observing behavior related to that location. Furthermore, when an actor is moving, the observation unit can prioritize observing behavior related to movement. For example, when an actor is moving, the observation unit can prioritize observing behavior related to movement. Furthermore, when an actor is at a position in a specific scene, the observation unit can prioritize observing behavior related to that scene. For example, when an actor is at a position in a specific scene, the observation unit can prioritize observing behavior related to that scene. This makes it possible to prioritize observing highly relevant behavior based on geographical location information. Some or all of the above-described processing in the observation unit may be performed using, or without, AI. For example, the observation unit can input data on the actor's geographical location information to the generation AI, which can prioritize observing highly relevant behavior.

[0086] During observation, the observation unit can analyze the social media activity of the performer and observe related behavior. The observation unit, for example, observes related behavior based on content shared by the performer on social media. For example, the observation unit can observe related behavior based on content shared by the performer on social media. The observation unit can also analyze responses of the performer's social media followers and observe related behavior. For example, the observation unit can analyze responses of the performer's social media followers and observe related behavior. The observation unit can also observe related behavior based on the performer's social media activity history. For example, the observation unit can observe related behavior based on the performer's social media activity history. In this way, related behavior can be observed based on social media activity. Some or all of the above-described processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data on the performer's social media activity into the generation AI, which can observe related behavior.

[0087] During observation, the observation unit can customize the observation method based on the performer's past feedback. The observation unit, for example, adjusts the observation method based on feedback provided by the performer in the past. For example, the observation unit can adjust the observation method based on feedback provided by the performer in the past. The observation unit can also preferentially use a specific observation method based on the performer's past feedback. For example, the observation unit can preferentially use a specific observation method based on the performer's past feedback. The observation unit can also improve the accuracy of observation by reflecting the performer's past feedback. For example, the observation unit can improve the accuracy of observation by reflecting the performer's past feedback. This allows the observation method to be customized based on the past feedback. Some or all of the above-described processing in the observation unit may be performed using, for example, AI, or may be performed without using AI. For example, the observation unit can input data of the performer's past feedback into the generation AI, which can customize the observation method.

[0088] The facilitator can estimate the emotions of the actor and adjust the way the progression is expressed based on the estimated emotions of the actor. For example, if the actor is nervous, the facilitator can slow down the pace of the progression to relax the actor. For example, the facilitator can slow down the progression of the actor's movements and lines to relax the actor. Furthermore, if the actor is relaxed, the facilitator can speed up the pace of the progression to increase the tempo. For example, the facilitator can speed up the progression of the actor's movements and lines to increase the tempo. Furthermore, if the actor is excited, the facilitator can emphasize the expression of the progression to highlight the emotion. For example, the facilitator can emphasize the progression of the actor's movements and lines to highlight the emotion. In this way, the way the progression is expressed can be adjusted based on the actor's emotions. Some or all of the above-mentioned processing in the facilitator may be performed using, or without, AI. For example, the facilitator can input data on the actor's emotions into a generation AI, which can adjust the way the progression is expressed.

[0089] The progression unit can adjust the level of detail of the progression based on the priority of a scene during progression. For example, in important scenes, the progression unit provides detailed progression and gives detailed instructions to the actor's actions and lines. For example, the progression unit can provide detailed instructions to the actor's actions and lines in important scenes to increase the precision of the direction. The progression unit can also reduce the level of detail of the progression in less important scenes to increase the actor's freedom. For example, the progression unit can increase the actor's freedom in less important scenes to enhance natural acting. The progression unit can also dynamically adjust the level of detail of the progression based on the importance of a scene. For example, the progression unit can dynamically adjust the level of detail of the progression based on the importance of a scene to maximize the effect of the direction. This allows the level of detail of the progression to be adjusted based on the importance of a scene. Some or all of the above-mentioned processing in the progression unit may be performed using, or without, AI. For example, the progression unit can input data on the importance of a scene to a generation AI, which can adjust the level of detail of the progression.

[0090] The progression unit can apply different progression algorithms depending on the scene category during progression. For example, in a drama scene, the progression unit applies a progression algorithm that emphasizes emotional expression. For example, the progression unit can apply a progression algorithm that emphasizes emotional expression in a drama scene to highlight the emotions of the actors. The progression unit can also apply a progression algorithm that emphasizes the accuracy of movements in an action scene. For example, the progression unit can apply a progression algorithm that emphasizes the accuracy of movements in an action scene to emphasize the actors' movements. The progression unit can also apply a progression algorithm that emphasizes timing in a comedy scene. For example, the progression unit can apply a progression algorithm that emphasizes timing in a comedy scene to elicit laughter from the audience. In this way, progression algorithms can be applied depending on the scene category. Some or all of the above-mentioned processing in the progression unit may be performed using AI, for example, or may be performed without using AI. For example, the progression unit can input data on the scene category into a generation AI, which can apply a different progression algorithm.

[0091] During progression, the progression unit can improve the accuracy of progression based on the performer's past progression results. The progression unit, for example, analyzes the performer's past progression results to improve the accuracy of progression. For example, the progression unit can analyze the performer's past progression results to improve the accuracy of progression. The progression unit can also optimize the progression method by referring to the performer's past successes. For example, the progression unit can optimize the progression method by referring to the performer's past successes. The progression unit can also analyze the performer's past failures to find areas for improvement in progression. For example, the progression unit can analyze the performer's past failures to find areas for improvement in progression. This allows the accuracy of progression to be improved based on the past progression results. Some or all of the above-mentioned processing in the progression unit may be performed using, for example, AI, or may be performed without using AI. For example, the progression unit can input data on the performer's past progression results into a generation AI, which can improve the accuracy of progression.

[0092] The facilitator can estimate the actor's emotions and adjust the length of the progression based on the estimated actor's emotions. For example, if the actor is nervous, the facilitator can shorten the length of the progression to reduce the actor's burden. For example, the facilitator can shorten the progression of the actor's movements or lines to reduce the actor's burden. Furthermore, if the actor is relaxed, the facilitator can lengthen the length of the progression to encourage detailed acting. For example, the facilitator can lengthen the progression of the actor's movements or lines to encourage detailed acting. Furthermore, if the actor is excited, the facilitator can adjust the length of the progression to highlight the peak of the actor's emotions. For example, the facilitator can adjust the progression of the actor's movements or lines to highlight the peak of the actor's emotions. In this way, the length of the progression can be adjusted based on the actor's emotions. Some or all of the above-mentioned processing in the facilitator may be performed using, or without, AI. For example, the facilitator can input data on the actor's emotions into a generation AI, which can adjust the length of the progression.

[0093] During progression, the progression unit can determine the priority of progression based on the timing of scene submission. For example, the progression unit prioritizes scenes whose submission deadline is approaching. For example, the progression unit can prioritize scenes whose submission deadline is approaching. The progression unit can also postpone scenes whose submission time is more flexible. For example, the progression unit can postpone scenes whose submission time is more flexible. The progression unit can also dynamically adjust the priority of progression based on the submission time. For example, the progression unit can dynamically adjust the priority of progression based on the submission time. This makes it possible to determine the priority of progression based on the submission time. Some or all of the above-mentioned processing in the progression unit may be performed using AI, for example, or may be performed without using AI. For example, the progression unit can input data on the submission time of scenes to a generation AI, and the generation AI can determine the priority of progression.

[0094] The progression unit can adjust the order of progression based on the relevance of scenes during progression. The progression unit, for example, progresses highly relevant scenes consecutively. For example, the progression unit can progress highly relevant scenes consecutively. The progression unit can also progress less relevant scenes at intervals. For example, the progression unit can progress less relevant scenes at intervals. The progression unit can also dynamically adjust the order of progression based on the relevance of scenes. For example, the progression unit can dynamically adjust the order of progression based on the relevance of scenes. This allows the order of progression to be adjusted based on the relevance of scenes. Some or all of the above-described processing in the progression unit may be performed using AI, for example, or may be performed without using AI. For example, the progression unit can input data on the relevance of scenes to a generation AI, and the generation AI can adjust the order of progression.

[0095] The facilitator can adjust the use of technical terms in the facilitator's presentation depending on the level of expertise of the performer. For example, the facilitator can use a lot of technical terms for a performer with high expertise. For example, the facilitator can use a lot of technical terms for a performer with high expertise. The facilitator can also use simple language for a performer with low expertise. For example, the facilitator can use simple language for a performer with low expertise. The facilitator can also dynamically adjust the use of technical terms in the facilitator's presentation depending on the performer's level of expertise. In this way, the use of technical terms in the facilitator can be adjusted depending on the level of expertise. Some or all of the above-described processing in the facilitator may be performed using, for example, AI, or may be performed without AI. For example, the facilitator can input data on the performer's level of expertise to a generation AI, which can adjust the use of technical terms in the facilitator's presentation.

[0096] The adjustment unit can estimate the actor's emotions and adjust the adjustment criteria based on the estimated actor's emotions. For example, if the actor is nervous, the adjustment unit can relax the adjustment criteria to allow the actor to relax. For example, the adjustment unit can relax the adjustment criteria for the actor's movements and lines to allow the actor to relax. Furthermore, if the actor is relaxed, the adjustment unit can tighten the adjustment criteria to improve accuracy. For example, the adjustment unit can tighten the adjustment criteria for the actor's movements and lines to improve accuracy. Furthermore, if the actor is excited, the adjustment unit can dynamically change the adjustment criteria to enhance the actor's emotions. For example, the adjustment unit can dynamically change the adjustment criteria for the actor's movements and lines to enhance the actor's emotions. In this way, the adjustment criteria can be adjusted based on the actor's emotions. Some or all of the above-described processing in the adjustment unit may be performed using, or without, AI. For example, the adjustment unit can input data on the actor's emotions into a generation AI, which can adjust the adjustment criteria.

[0097] During adjustment, the adjustment unit can improve the accuracy of the adjustment based on the interrelationships between scenes. The adjustment unit, for example, analyzes the interrelationships between scenes and improves the accuracy of the adjustment. For example, the adjustment unit can analyze the interrelationships between scenes and improve the accuracy of the adjustment. The adjustment unit can also optimize the adjustment method based on the interrelationships between scenes. For example, the adjustment unit can optimize the adjustment method based on the interrelationships between scenes. The adjustment unit can also change the focus of the adjustment by taking the interrelationships between scenes into consideration. For example, the adjustment unit can change the focus of the adjustment by taking the interrelationships between scenes into consideration. This can improve the accuracy of the adjustment by taking the interrelationships between scenes into consideration. Some or all of the above-described processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input data on the interrelationships between scenes to a generation AI, which can improve the accuracy of the adjustment.

[0098] The adjustment unit can make adjustments taking into account the performer's attribute information during adjustment. The adjustment unit changes the adjustment method depending on, for example, the performer's age and gender. For example, the adjustment unit can change the adjustment method depending on the performer's age and gender. The adjustment unit can also change the accuracy of the adjustment depending on the performer's experience and skill. For example, the adjustment unit can change the accuracy of the adjustment depending on the performer's experience and skill. The adjustment unit can also change the focus of the adjustment based on the performer's attribute information. For example, the adjustment unit can change the focus of the adjustment based on the performer's attribute information. This allows adjustments to be made based on the performer's attribute information. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input data on the performer's attribute information into a generation AI, and the generation AI can make the adjustments.

[0099] During adjustment, the adjustment unit can weight the adjustment based on the number of times a scene is submitted. For example, the adjustment unit prioritizes adjustment of scenes that are submitted frequently. For example, the adjustment unit can prioritize adjustment of scenes that are submitted frequently. The adjustment unit can also postpone scenes that are submitted less frequently. For example, the adjustment unit can postpone scenes that are submitted less frequently. The adjustment unit can also dynamically change the weight of the adjustment based on the submission frequency. For example, the adjustment unit can dynamically change the weight of the adjustment based on the submission frequency. This allows the weight of the adjustment to be based on the submission frequency. Some or all of the above-described processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input data on the number of times a scene is submitted to a generation AI, and the generation AI can perform the weight of the adjustment.

[0100] The adjustment unit can estimate the emotions of the performer and adjust the order in which the adjustment results are displayed based on the estimated emotions of the performer. For example, if the performer is nervous, the adjustment unit can first display important adjustment results to reassure the performer. For example, if the performer is nervous, the adjustment unit can first display important adjustment results to reassure the performer. Furthermore, if the performer is relaxed, the adjustment unit can later display detailed adjustment results to maintain the performer's concentration. For example, if the performer is relaxed, the adjustment unit can later display detailed adjustment results to maintain the performer's concentration. Furthermore, if the performer is excited, the adjustment unit can first display adjustment results that enhance the performer's emotions. For example, if the performer is excited, the adjustment unit can first display adjustment results that enhance the performer's emotions. In this way, the order in which the adjustment results are displayed can be adjusted based on the performer's emotions. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input data of the performer's emotions into the generation AI and adjust the order in which the generation AI displays the adjustment results.

[0101] During adjustment, the adjustment unit can make adjustments based on the geographical distribution of the scene. For example, when a scene takes place in different locations, the adjustment unit can make adjustments appropriate for each location. For example, when a scene takes place in different locations, the adjustment unit can make adjustments appropriate for each location. The adjustment unit can also change the adjustment method based on the geographical distribution of the scene. For example, the adjustment unit can change the adjustment method based on the geographical distribution of the scene. The adjustment unit can also change the focus of the adjustment taking into account the geographical distribution of the scene. For example, the adjustment unit can change the focus of the adjustment taking into account the geographical distribution of the scene. This allows adjustments to be made based on the geographical distribution. Some or all of the above-described processing in the adjustment unit may be performed using AI, for example, or may be performed without using AI. For example, the adjustment unit can input data on the geographical distribution of the scene to a generation AI, which can then make the adjustments.

[0102] During adjustment, the adjustment unit can improve the accuracy of the adjustment by referring to literature related to the scene. For example, the adjustment unit can improve the accuracy of the adjustment by referring to literature related to the scene. The adjustment unit can also optimize the adjustment method based on literature related to the scene. For example, the adjustment unit can optimize the adjustment method based on literature related to the scene. The adjustment unit can also change the focus of the adjustment by taking into account literature related to the scene. For example, the adjustment unit can change the focus of the adjustment by taking into account literature related to the scene. This can improve the accuracy of the adjustment based on the related literature. Some or all of the above-mentioned processing in the adjustment unit can be performed using AI, for example, or can be performed without using AI. For example, the adjustment unit can input data of literature related to the scene into a generation AI, which can improve the accuracy of the adjustment.

[0103] The adjustment unit can perform the adjustment based on the market value of the scene when making the adjustment. For example, the adjustment unit prioritizes adjusting scenes with high market value. For example, the adjustment unit can prioritize adjusting scenes with high market value. The adjustment unit can also postpone scenes with low market value. For example, the adjustment unit can postpone scenes with low market value. The adjustment unit can also dynamically change the weighting of the adjustment based on the market value. For example, the adjustment unit can dynamically change the weighting of the adjustment based on the market value. This allows the adjustment to be made based on the market value. Some or all of the above-described processing in the adjustment unit may be performed using, for example, AI, or may be performed without using AI. For example, the adjustment unit can input data on the market value of the scene to the generation AI, and the generation AI can make the adjustment.

[0104] The tuning unit can estimate the emotion of the actor and adjust the tuning method based on the estimated emotion of the actor. For example, if the actor is nervous, the tuning unit can relax the tuning method to relax the actor. For example, the tuning unit can relax the tuning method of the actor's movements and lines to relax the actor. Furthermore, if the actor is relaxed, the tuning unit can tighten the tuning method to increase accuracy. For example, the tuning unit can tighten the tuning method of the actor's movements and lines to increase accuracy. Furthermore, if the actor is excited, the tuning unit can dynamically change the tuning method to enhance the emotion. For example, the tuning unit can dynamically change the tuning method of the actor's movements and lines to enhance the emotion. In this way, the tuning method can be adjusted based on the emotion of the actor. Some or all of the above-described processing in the tuning unit may be performed using, or without, AI. For example, the tuning unit can input data of the actor's emotion into a generation AI, which can adjust the tuning method.

[0105] During tuning, the tuning unit can select an optimal tuning method based on the performer's past performance. The tuning unit selects the optimal tuning method based on, for example, the performer's past performance data. For example, the tuning unit can select the optimal tuning method based on the performer's past performance data. The tuning unit can also optimize the tuning method by referring to the performer's past successes. For example, the tuning unit can optimize the tuning method by referring to the performer's past successes. The tuning unit can also analyze the performer's past failures to find areas for improvement in tuning. For example, the tuning unit can analyze the performer's past failures to find areas for improvement in tuning. This allows the optimal tuning method to be selected based on past performance. Some or all of the above-described processing in the tuning unit may be performed using, for example, AI, or may be performed without using AI. For example, the tuning unit can input the performer's past performance data into a generation AI, which can select the optimal tuning method.

[0106] The tuning unit can customize the tuning means based on the actor's current character during tuning. For example, if the actor is playing a sad character, the tuning unit can adjust the color and intensity of lighting. For example, if the actor is playing a sad character, the tuning unit can adjust the color and intensity of lighting. The tuning unit can also adjust the sound settings if the actor is playing an action scene. For example, the tuning unit can adjust the sound settings if the actor is playing an action scene. The tuning unit can also adjust the tempo of background music if the actor is playing a comedy scene. For example, the tuning unit can adjust the tempo of background music if the actor is playing a comedy scene. This allows the tuning means to be customized based on the current character. Some or all of the above-described processing in the tuning unit may be performed using AI, for example, or may be performed without using AI. For example, the tuning unit can input data of the actor's current character into a generation AI, which can customize the tuning means.

[0107] The tuning unit can improve the tuning method based on the performer's feedback during tuning. The tuning unit can improve the tuning method based on, for example, feedback provided by the performer. For example, the tuning unit can improve the tuning method based on the feedback provided by the performer. The tuning unit can also preferentially use a specific tuning method based on the performer's feedback. For example, the tuning unit can preferentially use a specific tuning method based on the performer's feedback. The tuning unit can also improve the tuning accuracy by reflecting the performer's feedback. For example, the tuning unit can improve the tuning accuracy by reflecting the performer's feedback. This allows the tuning method to be improved based on the feedback. Some or all of the above-mentioned processing in the tuning unit may be performed using, for example, AI, or may be performed without using AI. For example, the tuning unit can input data of the performer's feedback into a generation AI, which can improve the tuning method.

[0108] The tuning unit can estimate the emotions of the performer and determine tuning priorities based on the estimated emotions of the performer. For example, if the performer is nervous, the tuning unit can prioritize tuning that will make the performer relaxed. For example, if the performer is nervous, the tuning unit can prioritize tuning that will make the performer relaxed. Furthermore, if the performer is relaxed, the tuning unit can prioritize tuning that will increase accuracy. For example, if the performer is relaxed, the tuning unit can prioritize tuning that will increase accuracy. Furthermore, if the performer is excited, the tuning unit can prioritize tuning that will enhance the performer's emotions. For example, if the performer is excited, the tuning unit can prioritize tuning that will enhance the performer's emotions. In this way, tuning priorities can be determined based on the performer's emotions. Some or all of the above-described processing in the tuning unit may be performed using, or without, AI. For example, the tuning unit can input data on the performer's emotions into a generation AI, which can determine tuning priorities.

[0109] The tuning unit can select an optimal tuning method based on the geographical location information of the performer when tuning. For example, when a performer performs at a specific location, the tuning unit selects a tuning method appropriate for that location. For example, when a performer performs at a specific location, the tuning unit can select a tuning method appropriate for that location. The tuning unit can also change the tuning method based on the geographical location information of the performer. For example, the tuning unit can change the tuning method based on the geographical location information of the performer. The tuning unit can also change the emphasis of tuning by taking into account the geographical location information of the performer. For example, the tuning unit can change the emphasis of tuning by taking into account the geographical location information of the performer. This makes it possible to select an optimal tuning method based on the geographical location information. Some or all of the above-described processing in the tuning unit may be performed using, or without, AI. For example, the tuning unit can input data on the geographical location information of the performer to a generation AI, which can select an optimal tuning method.

[0110] During tuning, the tuning unit can analyze the social media activity of the performer and suggest tuning methods. The tuning unit can suggest tuning methods based on, for example, content shared by the performer on social media. For example, the tuning unit can suggest tuning methods based on content shared by the performer on social media. The tuning unit can also analyze the reactions of the performer's followers on social media and suggest tuning methods. For example, the tuning unit can analyze the reactions of the performer's followers on social media and suggest tuning methods. The tuning unit can also suggest tuning methods based on the performer's social media activity history. For example, the tuning unit can suggest tuning methods based on the performer's social media activity history. In this way, tuning methods can be suggested based on social media activity. Some or all of the above-described processing in the tuning unit may be performed using, for example, AI, or may be performed without using AI. For example, the tuning unit can input data on the performer's social media activity into a generation AI, which can suggest tuning methods.

[0111] The tuning unit can customize the tuning method based on the performer's past feedback during tuning. The tuning unit customizes the tuning method based on, for example, feedback provided by the performer in the past. For example, the tuning unit can customize the tuning method based on feedback provided by the performer in the past. The tuning unit can also preferentially use a specific tuning method based on the performer's past feedback. For example, the tuning unit can preferentially use a specific tuning method based on the performer's past feedback. The tuning unit can also improve the tuning accuracy by reflecting the performer's past feedback. For example, the tuning unit can improve the tuning accuracy by reflecting the performer's past feedback. This allows the tuning method to be customized based on the past feedback. Some or all of the above-described processing in the tuning unit may be performed using AI, for example, or may be performed without using AI. For example, the tuning unit can input data of the performer's past feedback into a generation AI, which can customize the tuning method.

[0112] The providing unit can estimate the emotions of the performer and select a directing plan to provide based on the estimated emotions of the performer. For example, if the performer is nervous, the providing unit can provide a directing plan that relaxes the performer. For example, if the performer is nervous, the providing unit can provide a directing plan that relaxes the performer. The providing unit can also provide a directing plan that increases accuracy if the performer is relaxed. For example, if the performer is relaxed, the providing unit can provide a directing plan that increases accuracy. The providing unit can also provide a directing plan that enhances the performer's emotions if the performer is excited. For example, if the performer is excited, the providing unit can provide a directing plan that enhances the performer's emotions. This makes it possible to provide an optimal directing plan based on the performer's emotions. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input data on the performer's emotions into a generation AI and select a directing plan to be provided by the generation AI.

[0113] The providing unit can optimize the providing algorithm based on past provided data at the time of providing. The providing unit, for example, analyzes past provided data and selects an optimal providing algorithm. For example, the providing unit can analyze past provided data and select an optimal providing algorithm. The providing unit can also optimize the providing algorithm by referring to past successful examples. For example, the providing unit can optimize the providing algorithm by referring to past successful examples. The providing unit can also analyze past failure examples and find improvements to the providing algorithm. For example, the providing unit can analyze past failure examples and find improvements to the providing algorithm. This allows the providing algorithm to be optimized based on the past provided data. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input past provided data to a generating AI, which can optimize the providing algorithm.

[0114] The providing unit can update the provided data by reflecting the performer's feedback when providing the data. The providing unit, for example, updates the provided data based on feedback provided by the performer. For example, the providing unit can update the provided data based on feedback provided by the performer. The providing unit can also preferentially use a specific providing method based on the performer's feedback. For example, the providing unit can preferentially use a specific providing method based on the performer's feedback. The providing unit can also improve the accuracy of the provided data by reflecting the performer's feedback. For example, the providing unit can improve the accuracy of the provided data by reflecting the performer's feedback. This allows the provided data to be updated based on the feedback. Some or all of the above-mentioned processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input the performer's feedback data to the generating AI, which can update the provided data.

[0115] At the time of provision, the provision unit can select the optimal provision method by analyzing the performer's past performance. The provision unit selects the optimal provision method, for example, based on the performer's past performance data. For example, the provision unit can select the optimal provision method based on the performer's past performance data. The provision unit can also optimize the provision method by referring to the performer's past success stories. For example, the provision unit can optimize the provision method by referring to the performer's past success stories. The provision unit can also analyze the performer's past failure stories and find areas for improvement in the provision method. For example, the provision unit can analyze the performer's past failure stories and find areas for improvement in the provision method. This makes it possible to select the optimal provision method based on past performance. Some or all of the above-described processing in the provision unit may be performed using, for example, AI, or may be performed without using AI. For example, the provision unit can input the performer's past performance data into a generation AI, which can select the optimal provision method.

[0116] The providing unit can estimate the performer's emotions and adjust the frequency of the information provided based on the estimated performer's emotions. For example, if the performer is nervous, the providing unit can increase the frequency of the information provided to reassure the performer. For example, if the performer is nervous, the providing unit can increase the frequency of the information provided to reassure the performer. The providing unit can also reduce the frequency of the information provided to respect a natural performance when the performer is relaxed. For example, if the performer is relaxed, the providing unit can reduce the frequency of the information provided to respect a natural performance when the performer is relaxed. The providing unit can also adjust the frequency of the information provided to avoid missing important moments when the performer is excited. For example, if the performer is excited, the providing unit can adjust the frequency of the information provided to avoid missing important moments. In this way, the frequency of the information provided can be adjusted based on the performer's emotions. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or may be performed without using AI. For example, the providing unit can input data on the performer's emotions into the generation AI, and the generation AI can adjust the frequency of the information provided.

[0117] The providing unit can weight the provided data based on the submission timing of the scene when providing the data. For example, the providing unit preferentially weights the provided data of a scene whose submission deadline is approaching. For example, the providing unit can preferentially weight the provided data of a scene whose submission deadline is approaching. The providing unit can also postpone the provided data of a scene whose submission timing is more flexible. For example, the providing unit can postpone the provided data of a scene whose submission timing is more flexible. The providing unit can also dynamically adjust the weighting of the provided data based on the submission timing. For example, the providing unit can dynamically adjust the weighting of the provided data based on the submission timing. This makes it possible to weight the provided data based on the submission timing. Some or all of the above-described processing in the providing unit may be performed using AI, or may be performed without using AI. For example, the providing unit can input data on the submission timing of a scene to the generating AI, and the generating AI can weight the provided data.

[0118] The providing unit can integrate information from different data sources to enhance the provided data when providing the data. The providing unit, for example, integrates information from different data sources to enhance the provided data. For example, the providing unit can integrate information from different data sources to enhance the provided data. The providing unit can also analyze information from different data sources to improve the accuracy of the provided data. For example, the providing unit can analyze information from different data sources to improve the accuracy of the provided data. The providing unit can also adjust the weighting of the provided data based on the information from different data sources. For example, the providing unit can adjust the weighting of the provided data based on the information from different data sources. This allows the information from different data sources to be integrated and enhanced. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input information from different data sources to a generation AI, which can integrate the information and enhance the provided data.

[0119] The providing unit can make a proposal based on the schedule based on the performer's calendar information at the time of providing. The providing unit, for example, refers to a schedule registered in the performer's calendar and adjusts the provided data. For example, the providing unit can refer to a schedule registered in the performer's calendar and adjust the provided data. The providing unit can also propose provided data related to a specific event from the performer's calendar information. For example, the providing unit can propose provided data related to a specific event from the performer's calendar information. The providing unit can also propose optimal provided data tailored to the schedule based on the performer's calendar information. For example, the providing unit can propose optimal provided data tailored to the schedule based on the performer's calendar information. This makes it possible to make a proposal tailored to the schedule based on the calendar information. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the performer's calendar information to the generation AI, which can then make a proposal based on the schedule. === Hard Collateral 1-1 === Each of the multiple elements, including the observation unit, progression unit, adjustment unit, tuning unit, and provision 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 observation unit observes the movements, facial expressions, and lines of the performers using the camera 42 and microphone 38B of the smart device 14, and analyzes the performers' actions using the control unit 46A. The progression unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the timing of the performance in accordance with the script. The adjustment unit, realized, for example, by the control unit 46A of the smart device 14, estimates the performers' emotions and adjusts lighting and background music. The tuning unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the performance plan according to the performers' personalities. The provision unit, for example, observes the performers' performance using the camera 42 and microphone 38B of the smart device 14, and optimizes the performance plan based on the data. === Hard Collateral 1-2 === Each of the multiple elements, including the observation unit, progression unit, adjustment unit, tuning unit, and provision 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 observation unit observes the movements, facial expressions, and lines of the performers using the camera 42 and microphone 238 of the smart glasses 214, and analyzes the performers' actions using the control unit 46A. The progression unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the timing of the performance in accordance with the script. The adjustment unit, realized, for example, by the control unit 46A of the smart glasses 214, estimates the performers' emotions and adjusts lighting and background music. The tuning unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the performance plan according to the performers' personalities. The provision unit, for example, observes the performers' performance using the camera 42 and microphone 238 of the smart glasses 214, and optimizes the performance plan based on the data. === Hard Collateral 1-3 === Each of the multiple elements, including the observation unit, progression unit, adjustment unit, tuning unit, and provision unit, described above, is realized, for example, by at least one of the headset terminal 314 and the data processing device 12. For example, the observation unit observes the movements, facial expressions, and lines of the performers using the camera 42 and microphone 238 of the headset terminal 314, and analyzes the performers' actions using the control unit 46A. The progression unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the timing of the performance in accordance with the script. The adjustment unit, realized, for example, by the control unit 46A of the headset terminal 314, estimates the performers' emotions and adjusts lighting and background music. The tuning unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the performance plan according to the performers' personalities. The provision unit, for example, observes the performers' performance using the camera 42 and microphone 238 of the headset terminal 314, and optimizes the performance plan based on the data. === Hard Collateral 1-4 === Each of the multiple elements, including the observation unit, progression unit, adjustment unit, tuning unit, and provision unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the observation unit observes the movements, facial expressions, and lines of the performers using the camera 42 and microphone 238 of the robot 414, and analyzes the performers' actions using the control unit 46A. The progression unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the timing of the performance in accordance with the script. The adjustment unit, realized, for example, by the control unit 46A of the robot 414, estimates the performers' emotions and adjusts lighting and background music. The tuning unit, realized, for example, by the specific processing unit 290 of the data processing device 12, adjusts the performance plan according to the performers' personalities. The provision unit, for example, observes the performers' performance using the camera 42 and microphone 238 of the robot 414, and optimizes the performance plan based on the data.

[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 observation unit can not only observe the actions of the performers, but also the reactions of the audience. For example, the observation unit can capture the audience's facial expressions and movements with a camera and estimate their emotions. This allows for fine-tuning of the performance based on the audience's reactions. The observation unit can also pick up the audience's applause and laughter with a microphone and analyze the data to evaluate the audience's satisfaction. Furthermore, the observation unit can obtain information on the audience's seating positions and focus on observing the reactions of audience members in specific areas. This allows for the quality of the performance to be improved based on the audience's reactions.

[0122] The host not only advances the performance based on the actions of the performers, but can also adjust the timing of the performance based on the audience's reactions. For example, if the audience is laughing, the host can delay the next line slightly to enhance the laughter. Also, if the audience is moved, the host can dim the lights to leave the audience with a lingering sense of emotion. Furthermore, the host can adjust the tone and tempo of the background music according to the audience's reactions to enhance their emotions. In this way, the performance can be advanced based on the audience's reactions, increasing audience satisfaction.

[0123] The adjustment unit not only analyzes the performers' facial expressions, movements, and tone of their lines, but also analyzes the audience's reactions to fine-tune the performance. For example, if the audience is surprised, the adjustment unit can momentarily dim the lights to emphasize their surprise. If the audience is laughing, the adjustment unit can speed up the tempo of the background music to heighten the laughter. Furthermore, the adjustment unit can adjust the movement of the stage equipment based on the audience's reactions to heighten their emotions. This allows the production to be fine-tuned based on the audience's reactions, increasing audience satisfaction.

[0124] The tuning unit can not only tune the production plan according to the individuality of the actors and performers, but also adjust the production plan based on the audience's reaction. For example, if the audience is moved, the tuning unit can warm the lighting color to enhance the emotion. Also, if the audience is excited, the tuning unit can speed up the tempo of the background music to enhance the excitement. Furthermore, the tuning unit can adjust the movement of the stage equipment based on the audience's reaction to enhance the audience's emotions. In this way, the production plan can be adjusted based on the audience's reaction, increasing audience satisfaction.

[0125] The data processing unit can not only evaluate how its direction affects the performers' performances during rehearsals and rehearsals, but also evaluate audience reactions and adjust the direction plan accordingly. For example, the data processing unit can observe the audience's facial expressions and movements and optimize the direction plan based on that data. The data processing unit can also analyze the audience's applause and laughter and adjust the direction plan based on that data. Furthermore, the data processing unit can obtain information on the audience's seating positions and focus its evaluation on the reactions of audience members in specific areas. This allows the direction plan to be adjusted based on the audience's reactions, increasing audience satisfaction.

[0126] The observation unit can not only observe the actions of the performers, but also the status of the stage equipment. For example, the observation unit can capture the movements and positions of stage equipment with a camera and monitor the status of the stage equipment in real time. This allows for early detection of abnormalities in the stage equipment and a prompt response. The observation unit can also analyze the operation logs of the stage equipment and create maintenance plans for the equipment based on past operation history. Furthermore, the observation unit can obtain sensor information from the stage equipment and grasp the status of the stage equipment in detail. This makes it possible to monitor the status of the stage equipment and improve the quality of the production.

[0127] The performance unit not only advances the performance based on the actions of the performers, but can also adjust the timing of the performance based on the status of the stage equipment. For example, the performance unit can advance the next scene if the stage equipment is in the correct position. Also, if an abnormality occurs in the stage equipment, the performance unit can pause the performance and correct the abnormality. Furthermore, the performance unit can analyze the operation log of the stage equipment and optimize the timing of the performance based on the past operation history. This allows the performance to advance based on the status of the stage equipment, improving the quality of the performance.

[0128] The adjustment unit can not only analyze the facial expressions, movements, and tone of the lines of the performers, but also the state of the stage equipment to fine-tune the production. For example, the adjustment unit can adjust the color and intensity of the lighting according to the movement of the stage equipment. The adjustment unit can also adjust the tone and tempo of the background music according to the position of the stage equipment. Furthermore, the adjustment unit can analyze sensor information from the stage equipment and fine-tune the production based on the state of the stage equipment. This makes it possible to fine-tune the production based on the state of the stage equipment and improve the quality of the production.

[0129] The tuning unit can not only tune the directing plan according to the individuality of the actors and performers, but also adjust the directing plan based on the state of the stage equipment. For example, the tuning unit can adjust the color of the lighting according to the movement of the stage equipment. The tuning unit can also adjust the tempo of the background music according to the position of the stage equipment. Furthermore, the tuning unit can analyze sensor information from the stage equipment and adjust the directing plan based on the state of the stage equipment. This makes it possible to adjust the directing plan based on the state of the stage equipment and improve the quality of the performance.

[0130] The data provision unit can not only evaluate how its own direction is affecting the performers' performance during rehearsals and rehearsals, but also evaluate the state of the stage equipment and adjust the directing plan accordingly. For example, the data provision unit can analyze the operation log of the stage equipment and optimize the directing plan based on that data. The data provision unit can also acquire sensor information from the stage equipment and adjust the directing plan based on that data. Furthermore, the data provision unit can monitor the state of the stage equipment in real time and respond quickly if an abnormality occurs. This allows the directing plan to be adjusted based on the state of the stage equipment, improving the quality of the performance.

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

[0132] Step 1: The observation unit observes the actor's actions. For example, the observation unit can use a camera or microphone to observe the actor's movements, facial expressions, and lines. It can also use thermography to observe changes in the actor's body temperature. Step 2: The facilitator advances the performance based on the actions observed by the observer. For example, the facilitator can adjust the timing of the performance by checking it against the script. The facilitator can also control lighting and background music according to the progress of the actors' movements and lines. Step 3: The adjustment unit analyzes the performer's facial expressions, movements, and tone of the lines, and fine-tunes the production accordingly. For example, the adjustment unit can use generative AI to estimate the performer's emotions and adjust the color and intensity of the lighting, the tone and tempo of the background music, etc. Step 4: The tuning department fine-tunes the production plan to suit the individuality of the actors and performers. For example, the tuning department can adjust the color of the lighting to match the actor's skin tone or the tempo of the background music to match the actor's acting style. Step 5: The production department assesses how their direction is affecting the performers' performance during rehearsals and rehearsals, and adjusts the production plan. For example, the production department can observe the performers' performance using cameras, microphones, and thermography, and use that data to optimize the production plan.

[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 the 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 type 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 observation unit that observes the actions of the performers; a progression unit that progresses a performance based on the behavior observed by the observation unit; an adjustment unit that fine-tunes the performance based on the performance progressed by the progress unit; a tuning unit that tunes the presentation plan based on the presentation adjusted by the adjustment unit; a providing unit that improves the quality of the presentation based on the presentation plan tuned by the tuning unit; Equipped with A system characterized by:

2. The observation unit Observing the performer's actions using a camera or microphone 2. The system of claim 1.

3. The progression section Based on observed behavior, proceed with the performance in accordance with the script.

2. The system of claim 1.

4. The adjustment unit Analyzing the performers' facial expressions, movements, and tone of their lines, and fine-tuning the direction based on their meaning 2. The system of claim 1.

5. The tuning unit Fine-tune the production plan to suit the individuality of the actors and performers 2. The system of claim 1.

6. The providing unit Evaluate how your direction affects the performers' performance during rehearsals and rehearsals, and adjust your directing plan accordingly.

2. The system of claim 1.

7. The observation unit Estimate the emotion of the actor and adjust the timing of observations based on the estimated emotion of the actor.

2. The system of claim 1.

8. The observation unit Analyze the performer's past performance history and select the most appropriate observation method 2. The system of claim 1.

Images