System

Abstract

To provide a system that estimates the emotions of an audience and provides performance accordingly.SOLUTION: A system according to an embodiment comprises an acquisition unit, an estimation unit, a determination unit, and an execution unit. The acquisition unit acquires emotion estimation information for estimating the emotions of an audience. The estimation unit estimates the emotions of the audience on the basis of the emotion estimation information acquired by the acquisition unit. The determination unit determines performance according to the emotions of the audience as estimated by the estimation unit. The execution unit executes the performance determined by the determination unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

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

[0004] With conventional technology, it was difficult to provide a performance that responded to the audience's emotions in real time.

[0005] The system according to the embodiment aims to estimate the emotions of the audience and provide a performance in accordance with the emotions. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, an estimation unit, a determination unit, and an execution unit. The acquisition unit acquires emotion estimation information for estimating the emotion of an audience. The estimation unit estimates the emotion of the audience based on the emotion estimation information acquired by the acquisition unit. The determination unit determines a performance according to the emotion of the audience estimated by the estimation unit. The execution unit executes the performance determined by the determination unit. Effect of the Invention

[0007] The system according to the embodiment can estimate the emotions of the audience and provide a performance accordingly. [Brief description of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The performance robot system according to the embodiment of the present invention is a system that reads the emotions of the audience and performs appropriate music and performance. This system acquires emotion estimation information for estimating the emotions of the audience, and estimates the emotions of the audience based on the acquired information. An appropriate performance is determined according to the estimated emotions, and the performance is executed. For example, information such as the audience's facial expressions, movements, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content is acquired and input to an emotion engine. The emotion engine analyzes the acquired information and estimates the emotions of the audience. For example, the emotion engine can analyze the facial expressions and movements of the audience and estimate emotions such as joy, sadness, and surprise. In addition, the average or median of the emotions of multiple audience members, or the most common emotion, can be estimated as the emotion of the audience. An appropriate performance is determined according to the estimated emotions. For example, if the audience is happy, cheerful music is played, and if the audience is sad, moving music is played. In addition, a performance such as a dance performance or pantomime can be determined according to the emotions of the audience. Finally, the determined performance is executed. For example, the agent can sing, dance, or play an instrument together with the audience. In this way, the agent can read the emotions of the audience and play appropriate music and performances to achieve a more moving performance.This allows the performance robot system to read the emotions of the audience and play appropriate music and performances to achieve a more moving performance.

[0029] The performance robot system according to the embodiment includes an acquisition unit, an estimation unit, a decision unit, and an execution unit. The acquisition unit acquires emotion estimation information for estimating the emotion of the audience. The emotion estimation information for estimating the emotion of the audience includes, but is not limited to, facial expression data, voice data, and biosensor data. For example, the acquisition unit photographs the facial expressions of the audience with a camera and acquires the facial expression data using a facial expression recognition technique. The acquisition unit can also record the voice of the audience with a microphone and acquire the voice data using a voice analysis technique. Furthermore, the acquisition unit can acquire biodata such as the heart rate and blood pressure of the audience using a biosensor. For example, the acquisition unit inputs the facial expression data photographed with the camera to a generation AI, which analyzes the facial expression data to estimate the emotion. The estimation unit estimates the emotion of the audience based on the emotion estimation information acquired by the acquisition unit. The estimation unit analyzes the acquired facial expression data and voice data using, for example, a generation AI, and estimates the emotion of the audience. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, and estimates emotions based on the acquired data. For example, the generation AI analyzes facial expression data and estimates emotions such as joy, sadness, and surprise. The estimation unit can also estimate the average or median of the emotions of multiple audience members, or the most common emotion, as the emotion of the audience. The determination unit determines a performance according to the emotion of the audience estimated by the estimation unit. For example, the determination unit plays cheerful music when the audience is happy, and plays moving music when the audience is sad. The determination unit can also determine a performance such as a dance performance or pantomime according to the emotion of the audience. The determination unit uses, for example, the generation AI to determine a performance according to the emotion of the audience. The generation AI is, for example, a music generation AI or a dance generation AI, and generates a performance according to the emotion of the audience. The execution unit executes the performance determined by the determination unit. For example, the execution unit can make the agent sing, dance, or play an instrument together with the audience. The execution unit executes the determined performance using, for example, a generation AI. The generation AI may be, for example, a music generation AI or a dance generation AI, and executes the determined performance.As a result, the performance robot system according to the embodiment can read the emotions of the audience and provide appropriate music and performance, thereby achieving a more moving performance.

[0030] The acquisition unit acquires emotion estimation information for estimating the emotion of the audience. The emotion estimation information for estimating the emotion of the audience includes, but is not limited to, facial expression data, voice data, and biosensor data. For example, the acquisition unit photographs the facial expressions of the audience with a camera and acquires the facial expression data using a facial expression recognition technology. Specifically, the faces of the audience are photographed from multiple angles using a high-resolution camera, and minute changes in facial expressions are detected using a facial expression recognition algorithm using deep learning. The acquisition unit can also record the voices of the audience with a microphone and acquire the voice data using a voice analysis technology. To acquire the voice data, noise canceling technology is used to remove ambient noise and collect clear voice. Furthermore, the acquisition unit can also acquire biodata such as the heart rate and blood pressure of the audience using a biosensor. The biosensor is provided as a wearable device, and the audience wears it to collect data in real time. For example, the acquisition unit inputs the facial expression data captured by the camera to the generation AI, which analyzes the facial expression data to estimate the emotion. The generation AI has been trained in advance on a large dataset of facial expressions and can estimate emotions such as happiness, sadness, and surprise with a high degree of accuracy. This allows the acquisition unit to collect emotion estimation information from a variety of data sources and accurately grasp the emotions of the audience.

[0031] The estimation unit estimates the emotions of the audience based on the emotion estimation information acquired by the acquisition unit. The estimation unit, for example, uses a generation AI to analyze the acquired facial expression data and voice data to estimate the emotions of the audience. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, and estimates emotions based on the acquired data. Specifically, the generation AI analyzes the facial expression data, extracts facial feature points, and classifies emotions. For voice data, it analyzes features such as tone, pitch, and speed of the voice to estimate emotions. Furthermore, the estimation unit can analyze biosensor data and estimate stress and relaxation states from fluctuations in heart rate and blood pressure. For example, the generation AI analyzes the facial expression data, and estimates emotions such as joy, sadness, and surprise. The estimation unit can also estimate the average or median of the emotions of multiple audience members, or the most common emotion, as the emotion of the audience. This allows the estimation unit to grasp not only the emotions of individual audience members, but also the overall tendency of emotions. Additionally, the estimator can also predict changes in emotions, taking into account past data and trends, for example predicting how emotions will change during a particular performance and allowing for real-time responses, allowing the estimator to estimate audience emotions with high accuracy and improve overall system performance.

[0032] The determination unit determines a performance according to the emotions of the audience estimated by the estimation unit. For example, if the audience is happy, the determination unit plays cheerful music, and if the audience is sad, the determination unit plays moving music. Specifically, the determination unit uses a music generation AI to generate music according to the emotions of the audience. The music generation AI is trained in advance with music data of various genres and tempos, and can generate music that is optimal for the emotions of the audience in real time. The determination unit can also determine a performance such as a dance performance or pantomime according to the emotions of the audience. The dance generation AI generates dance choreography according to the emotions of the audience and issues instructions to the robot. Furthermore, the determination unit adjusts the timing and order of the performance to provide an optimal performance. For example, by performing a cheerful dance performance after moving music, the emotions of the audience can be effectively elicited. The determination unit uses, for example, a generation AI to determine a performance according to the emotions of the audience. The generation AI is, for example, a music generation AI or a dance generation AI, and generates a performance according to the emotions of the audience. As a result, the determination unit can provide a performance that is optimal for the emotions of the audience and realize a more moving experience.

[0033] The execution unit executes the performance determined by the determination unit. For example, the execution unit can make the agent sing, dance, or play a musical instrument together with the audience. Specifically, the execution unit controls the robot actuators to physically execute the determined performance. For example, the execution unit controls the robot's joints and motors to accurately reproduce the dance choreography. In addition, the music generated using the music generation AI is played from the speaker and delivered to the audience. Furthermore, the execution unit can receive feedback in real time and adjust the performance. For example, the reaction of the audience is detected by a sensor and the speed and intensity of the performance are adjusted. The execution unit executes the determined performance, for example, using the generation AI. The generation AI is, for example, a music generation AI or a dance generation AI, and executes the determined performance. As a result, the execution unit can execute the determined performance with high accuracy and impress the audience. Furthermore, the execution unit can also realize a complex performance by coordinating multiple robots and agents. For example, multiple robots can work together to dance and provide a visually and aurally appealing performance. As a result, the execution unit can provide a consistent, high-quality performance to the audience and maximize the effect of the entire system.

[0034] The determination unit can determine a musical performance according to the emotions of the audience as a performance according to the emotions of the audience, and the execution unit can execute the musical performance according to the emotions of the audience. For example, if the audience is happy, the determination unit plays cheerful music, and if the audience is sad, the execution unit plays moving music. The determination unit uses the generation AI to determine the musical performance according to the emotions of the audience. The generation AI is, for example, a music generation AI, and generates music according to the emotions of the audience. The execution unit executes the musical performance determined by the determination unit. For example, the execution unit can cause the agent to sing together with the audience or play an instrument. The execution unit executes the determined musical performance using the generation AI. The generation AI is, for example, a music generation AI, and executes the determined music. This allows a more moving performance to be provided by executing a musical performance according to the emotions of the audience.

[0035] The determination unit can determine a dance performance according to the emotions of the audience as a performance according to the emotions of the audience, and the execution unit can execute the dance performance according to the emotions of the audience. For example, if the audience is happy, the determination unit determines a cheerful dance performance, and if the audience is sad, the determination unit determines a moving dance performance. The determination unit uses a generation AI to determine a dance performance according to the emotions of the audience. The generation AI is, for example, a dance generation AI, and generates a dance according to the emotions of the audience. The execution unit executes the dance performance determined by the determination unit. The execution unit can, for example, allow an agent to dance together with the audience. The execution unit uses the generation AI to execute the determined dance performance. The generation AI is, for example, a dance generation AI, and executes the determined dance. This makes it possible to provide a more moving performance by executing a dance performance according to the emotions of the audience.

[0036] The determination unit determines a pantomime according to the emotions of the audience as a performance according to the emotions of the audience, and the execution unit can execute the pantomime according to the emotions of the audience. For example, if the audience is happy, the determination unit determines a cheerful pantomime, and if the audience is sad, determines a moving pantomime. The determination unit uses a generation AI to determine a pantomime according to the emotions of the audience. The generation AI is, for example, a pantomime generation AI, and generates a pantomime according to the emotions of the audience. The execution unit executes the pantomime determined by the determination unit. For example, the execution unit allows the agent to pantomime together with the audience. The execution unit uses the generation AI to execute the determined pantomime. The generation AI is, for example, a pantomime generation AI, and executes the determined pantomime. This makes it possible to provide a more moving performance by executing a pantomime according to the emotions of the audience.

[0037] The estimation unit can estimate the average or median of the emotions of multiple audience members who make up the audience as the audience's emotion. The estimation unit, for example, calculates the average of the emotions of multiple audience members and estimates the average as the audience's emotion. The estimation unit can also calculate the median of the emotions of multiple audience members and estimate the median as the audience's emotion. The estimation unit uses a generation AI to analyze the emotions of multiple audience members and calculate the average or median. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of multiple audience members. This enables more accurate emotion estimation by integrating the emotions of multiple audience members to estimate the audience's emotion.

[0038] The estimation unit can estimate the most prevalent emotion among the emotions of multiple spectators making up the audience as the emotion of the audience. The estimation unit, for example, identifies the most prevalent emotion among the emotions of the multiple spectators and estimates that emotion as the emotion of the audience. The estimation unit uses a generation AI to analyze the emotions of the multiple spectators and identify the most prevalent emotion. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the multiple spectators. This enables more accurate emotion estimation by estimating the most prevalent emotion among the emotions of the multiple spectators as the emotion of the audience.

[0039] The determination unit can determine a performance according to the audience's emotions based on the audience's emotions and the attributes of the audience. The determination unit determines a performance according to the audience's emotions, taking into account attribute information such as the audience's age, gender, and interests. The determination unit uses a generation AI to analyze the audience's emotions and attribute information and determine an optimal performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the audience's emotions and attribute information. This makes it possible to provide a more appropriate performance by determining a performance based on the audience's emotions and attributes.

[0040] The acquisition unit can acquire one or more pieces of information among the audience's facial expressions, movements, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content as emotion estimation information. For example, the acquisition unit captures the audience's facial expressions with a camera and acquires the facial expression data using facial expression recognition technology. The acquisition unit can also record the audience's voice with a microphone and acquire the voice data using voice analysis technology. Furthermore, the acquisition unit can acquire biometric data such as the audience's heart rate and blood pressure using a biosensor. For example, the acquisition unit inputs the facial expression data captured by the camera to the generation AI, which analyzes the facial expression data to estimate emotions. This allows for more accurate emotion estimation by acquiring a variety of information as emotion estimation information.

[0041] It can function as a performance robot including an acquisition unit, an estimation unit, a decision unit, an execution unit, and a robot body. The acquisition unit, the estimation unit, the decision unit, the execution unit, and the robot body function integrally as a performance robot. For example, the robot body incorporates each unit for estimating the emotions of the audience and performing an appropriate performance. The robot body includes devices such as a camera, a microphone, and a biosensor, and acquires information for estimating the emotions of the audience. The acquired information is analyzed by a generation AI in the robot body, and the emotions of the audience are estimated. Based on the estimated emotions, the generation AI in the robot body determines an appropriate performance, and the robot body executes the performance. In this way, by functioning as a performance robot, it is possible to provide an actual performance to the audience.

[0042] The acquisition unit can estimate the emotions of the audience and adjust the timing of acquiring the emotion estimation information based on the estimated emotions of the audience. For example, when the audience is excited, the acquisition unit can increase the frequency of acquiring the emotion estimation information. Also, when the audience is relaxed, the acquisition unit can reduce the frequency of acquiring the emotion estimation information. Furthermore, when the audience is focused, the acquisition unit can keep the timing of acquiring the emotion estimation information constant. The acquisition unit uses the generation AI to analyze the emotions of the audience and adjust the acquisition timing. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the timing of acquiring the emotion estimation information to be adjusted, thereby acquiring information at a more appropriate timing.

[0043] The acquisition unit can analyze the past emotion data of the audience and select the optimal acquisition method. For example, the acquisition unit can analyze from the past emotion data that emotions are likely to fluctuate during a specific time period, and acquire information focusing on that time period. The acquisition unit can also analyze from the past emotion data that emotions fluctuate during a specific event or situation, and select an acquisition method according to that situation. Furthermore, the acquisition unit can analyze from the past emotion data that a specific emotion tends to continue for a long time, and reduce the acquisition frequency while that emotion continues. The acquisition unit uses the generation AI to analyze the past emotion data and select the optimal acquisition method. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past emotion data. In this way, the optimal acquisition method can be selected by analyzing the past emotion data.

[0044] The acquisition unit can perform filtering based on the current environment and situation of the audience when acquiring the emotion estimation information. For example, when the audience is outdoors, the acquisition unit can filter environmental sounds to acquire emotion estimation information. Also, when the audience is in a quiet room, the acquisition unit can also acquire emotion estimation information by placing emphasis on subtle voices and actions. Furthermore, when there is a large audience, the acquisition unit can also acquire information for estimating the overall emotion by filtering individual emotions. The acquisition unit uses a generation AI to analyze the current environment and situation of the audience and perform filtering. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the environment and situation of the audience. As a result, more accurate emotion estimation information can be acquired by filtering based on the current environment and situation.

[0045] The acquisition unit can estimate the emotions of the audience and determine the priority of emotion estimation information to be acquired based on the estimated emotions of the audience. For example, when the audience is excited, the acquisition unit prioritizes acquiring facial expression and movement information. When the audience is relaxed, the acquisition unit can also prioritize acquiring heart rate and breathing information. Furthermore, when the audience is focused, the acquisition unit can also prioritize acquiring voice and pupil response information. The acquisition unit uses a generation AI to analyze the emotions of the audience and determine the priority of information to be acquired. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. In this way, the priority of emotion estimation information can be determined, and more important information can be acquired preferentially.

[0046] When acquiring emotion estimation information, the acquisition unit can preferentially acquire highly relevant information by taking into account the geographical location information of the audience. For example, when the audience is at a specific event venue, the acquisition unit preferentially acquires information related to the event. Also, when the audience is at a tourist spot, the acquisition unit can preferentially acquire information related to the tourist spot. Furthermore, when the audience is at home, the acquisition unit can also acquire information by referring to past emotion data at home. The acquisition unit uses the generation AI to analyze the geographical location information of the audience and preferentially acquire highly relevant information. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information of the audience. As a result, highly relevant information can be preferentially acquired by taking into account the geographical location information.

[0047] The acquisition unit can analyze the audience's social media activity and acquire related information when acquiring emotion estimation information. For example, when the audience posts about a specific event on social media, the acquisition unit acquires information related to the event. Also, when the audience expresses a specific emotion on social media, the acquisition unit can acquire information related to the emotion. Furthermore, when the audience posts about a specific place on social media, the acquisition unit can acquire information related to the place. The acquisition unit uses a generation AI to analyze the audience's social media activity and acquire related information. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the audience's social media activity. In this way, related information can be acquired by analyzing social media activity.

[0048] The estimation unit can estimate the emotions of the audience and adjust the emotion estimation algorithm based on the estimated emotions of the audience. For example, when the audience is excited, the estimation unit can increase the sensitivity of the emotion estimation algorithm. Also, when the audience is relaxed, the estimation unit can lower the sensitivity of the emotion estimation algorithm. Furthermore, when the audience is focused, the sensitivity of the emotion estimation algorithm can be kept constant. The estimation unit uses the generation AI to analyze the emotions of the audience and adjust the emotion estimation algorithm. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows for more accurate emotion estimation by adjusting the emotion estimation algorithm.

[0049] The estimation unit can adjust the level of detail of the estimation based on the importance of the emotion estimation information at the time of estimation. For example, the estimation unit preferentially analyzes information with high importance (e.g., heart rate, brain waves) and performs detailed estimation. Also, the estimation unit can simply analyze information with low importance (e.g., movement, facial expression) and reduce the level of detail of the estimation. Furthermore, the estimation unit can moderately analyze information with medium importance (e.g., voice, breathing) and keep the level of detail of the estimation at a medium level. The estimation unit uses a generation AI to analyze the importance of the emotion estimation information and adjust the level of detail of the estimation. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of the emotion estimation information. This allows for more accurate emotion estimation by adjusting the level of detail of the estimation based on the importance of the emotion estimation information.

[0050] The estimation unit can apply different estimation algorithms depending on the category of the emotion estimation information at the time of estimation. For example, the estimation unit applies an image analysis algorithm to facial expression information and an audio analysis algorithm to audio information. In addition, the estimation unit can also apply a biosignal analysis algorithm to heart rate information. The estimation unit uses a generation AI to apply an optimal estimation algorithm depending on the category of the emotion estimation information. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and performs analysis depending on the category of the emotion estimation information. This enables more accurate emotion estimation by applying an optimal estimation algorithm depending on the category of the emotion estimation information.

[0051] The estimation unit can estimate the emotions of the audience and adjust the display method of the estimation result based on the estimated emotions of the audience. For example, if the audience is excited, the estimation unit can provide a visually stimulating display method. If the audience is relaxed, the estimation unit can also provide a calm display method. Furthermore, if the audience is focused, the estimation unit can also provide a simple and highly visible display method. The estimation unit uses a generation AI to analyze the emotions of the audience and adjust the display method of the estimation result. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. As a result, more appropriate information can be provided to the audience by adjusting the display method of the estimation result.

[0052] The estimation unit can determine the priority of estimation based on the acquisition time of the emotion estimation information at the time of estimation. For example, the estimation unit preferentially analyzes the latest emotion estimation information. Also, the estimation unit can prioritize the latest information while referring to past emotion estimation information. Furthermore, the estimation unit can preferentially analyze emotion estimation information acquired in a specific time period. The estimation unit uses a generation AI to analyze the acquisition time of the emotion estimation information and determine the priority of estimation. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the acquisition time of the emotion estimation information. In this way, by determining the priority of estimation based on the acquisition time of the emotion estimation information, more appropriate information can be preferentially analyzed.

[0053] The estimation unit can adjust the order of estimation based on the relevance of the emotion estimation information at the time of estimation. For example, the estimation unit preferentially analyzes information with high relevance. Also, the estimation unit can analyze information with medium relevance next. Furthermore, the estimation unit can analyze information with low relevance last. The estimation unit uses a generation AI to analyze the relevance of the emotion estimation information and adjust the order of estimation. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of the emotion estimation information. This enables more efficient emotion estimation by adjusting the order of estimation based on the relevance of the emotion estimation information.

[0054] The decision unit can estimate the emotions of the audience and adjust the way the performance is expressed based on the estimated emotions of the audience. For example, if the audience is excited, the decision unit can select an energetic way of expression. If the audience is relaxed, the decision unit can also select a calm way of expression. Furthermore, if the audience is focused, the decision unit can select a simple and highly visible way of expression. The decision unit uses a generation AI to analyze the emotions of the audience and adjust the way the performance is expressed. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the way the performance is expressed to be adjusted to provide a more appropriate performance to the audience.

[0055] The determination unit can adjust the level of detail of the performance based on the importance of the emotion estimation result when determining the performance. For example, the determination unit can determine a detailed performance for an emotion with high importance (e.g., joy, sadness). Also, the determination unit can determine a simplified performance for an emotion with low importance (e.g., surprise, excitement). Furthermore, the determination unit can determine a performance with a moderate level of detail for an emotion with medium importance (e.g., relaxation, concentration). The determination unit uses the generation AI to analyze the importance of the emotion estimation result and adjust the level of detail of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of the emotion estimation result. This makes it possible to provide a more appropriate performance by adjusting the level of detail of the performance based on the importance of the emotion estimation result.

[0056] The determination unit can apply different performance algorithms depending on the category of the emotion estimation result when determining the performance. For example, the determination unit can apply a cheerful music performance algorithm to the emotion of joy. Also, the determination unit can apply a moving music performance algorithm to the emotion of sadness. Furthermore, the determination unit can apply a visually stimulating performance algorithm to the emotion of surprise. The determination unit uses the generation AI to apply an optimal performance algorithm depending on the category of the emotion estimation result. The generation AI is, for example, a music generation AI or a dance generation AI, and generates a performance depending on the category of the emotion estimation result. In this way, a more appropriate performance can be provided by applying an optimal performance algorithm depending on the category of the emotion estimation result.

[0057] The decision unit can estimate the emotions of the audience and adjust the length of the performance based on the estimated emotions of the audience. For example, if the audience is excited, the decision unit can determine a short and energetic performance. Also, if the audience is relaxed, the decision unit can determine a long and calm performance. Furthermore, if the audience is focused, the decision unit can determine a performance of moderate length. The decision unit uses a generation AI to analyze the emotions of the audience and adjust the length of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the length of the performance to be adjusted to provide a more appropriate performance for the audience.

[0058] The determination unit can determine the priority order of performance based on the acquisition time of emotion estimation results when determining performance. The determination unit determines the priority order of performance based on, for example, the latest emotion estimation result. Also, the determination unit can emphasize the latest result while referring to past emotion estimation results. Furthermore, the determination unit can determine the priority order of performance based on emotion estimation results acquired in a specific time period. The determination unit uses a generation AI to analyze the acquisition time of the emotion estimation result and determine the priority order of performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the acquisition time of the emotion estimation result. In this way, a more appropriate performance can be provided by determining the priority order of performance based on the acquisition time of the emotion estimation result.

[0059] The determination unit can adjust the order of performances based on the relevance of emotion estimation results when determining the performances. The determination unit can, for example, determine the order of performances based on emotions with high relevance. It can also determine the order of performances next based on emotions with medium relevance. It can also determine the order of performances last based on emotions with low relevance. The determination unit uses a generation AI to analyze the relevance of emotion estimation results and adjust the order of performances. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of emotion estimation results. This makes it possible to provide a more appropriate performance by adjusting the order of performances based on the relevance of emotion estimation results.

[0060] The execution unit can estimate the emotions of the audience and adjust the execution method of the performance based on the estimated emotions of the audience. For example, if the audience is excited, the execution unit can select an energetic execution method. If the audience is relaxed, the execution unit can also select a calm execution method. Furthermore, if the audience is focused, the execution unit can select a simple and highly visible execution method. The execution unit uses the generation AI to analyze the emotions of the audience and adjust the execution method of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the execution method of the performance to be adjusted to provide a more appropriate performance to the audience.

[0061] The execution unit can select the optimal execution method by referring to past performance data when performing a performance. The execution unit, for example, selects a successful execution method from past performance data. Also, it can avoid unsuccessful execution methods from past performance data. Furthermore, it can select an execution method that is effective for a specific emotion from past performance data. The execution unit uses a generation AI to analyze past performance data and select the optimal execution method. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past performance data. In this way, it is possible to select the optimal execution method by referring to past performance data.

[0062] The execution unit can customize the execution means based on the current situation of the audience when performing the performance. For example, if the audience is outdoors, the execution unit can adjust the volume and visual effects. If the audience is indoors, the execution unit can also adjust the lighting and sound effects. Furthermore, if there is a large audience, the execution unit can select an execution means for the entire audience. The execution unit uses a generation AI to analyze the current situation of the audience and customize the execution means. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the current situation of the audience. This makes it possible to provide a more appropriate performance by customizing the execution means based on the current situation of the audience.

[0063] The execution unit can estimate the emotions of the audience and determine the execution priority of the performance based on the estimated emotions of the audience. For example, if the audience is excited, the execution unit can prioritize an energetic performance. Also, if the audience is relaxed, the execution unit can prioritize a calm performance. Furthermore, if the audience is focused, the execution unit can prioritize a simple and highly visible performance. The execution unit uses a generation AI to analyze the emotions of the audience and determine the execution priority of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the execution priority of the performance to be determined, thereby providing a more appropriate performance.

[0064] When performing a performance, the execution unit can select the optimal execution method by taking into account the geographic location information of the audience. For example, if the audience is at a specific event venue, the execution unit selects an execution method suitable for the event. Also, if the audience is at a tourist spot, the execution unit can select an execution method related to the tourist spot. Furthermore, if the audience is at home, the execution unit can select a method that is easy to execute at home. The execution unit uses a generation AI to analyze the geographic location information of the audience and select the optimal execution method. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographic location information of the audience. This makes it possible to select the optimal execution method by taking into account the geographic location information.

[0065] The execution unit can analyze the audience's social media activity and suggest execution means when performing a performance. For example, if the audience posts about a specific event on social media, the execution unit can suggest execution means related to the event. In addition, if the audience expresses a specific emotion on social media, the execution unit can also suggest execution means related to the emotion. Furthermore, if the audience posts about a specific place on social media, the execution unit can also suggest execution means related to the place. The execution unit uses a generative AI to analyze the audience's social media activity and suggest execution means. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the audience's social media activity. This makes it possible to suggest more appropriate execution means by analyzing social media activity.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] When acquiring emotion estimation information for the audience, the acquisition unit can optimize the method of acquiring current emotion estimation information by referring to the audience's past emotion data. For example, if it is known from past data that emotions are likely to fluctuate during a specific time period, information can be acquired with a focus on that time period. Also, if it is known that emotions fluctuate during a specific event or situation, an acquisition method can be selected according to that situation. Furthermore, if a specific emotion tends to last for a long time, the acquisition frequency can be reduced while that emotion continues. This makes it possible to utilize past emotion data to perform more accurate emotion estimation.

[0068] When estimating the emotions of the audience, the estimation unit can apply different estimation algorithms depending on the category of the emotion estimation information. For example, an image analysis algorithm can be applied to facial expression information, and a voice analysis algorithm can be applied to voice information. Also, a biosignal analysis algorithm can be applied to heart rate information. In this way, more accurate emotion estimation can be achieved by applying the optimal estimation algorithm depending on the category of the emotion estimation information.

[0069] The determination unit can determine a performance according to the audience's emotions based on the audience's emotions and attributes. For example, the determination unit determines a performance according to the audience's emotions taking into account attribute information such as the audience's age, gender, and interests. In this way, a more appropriate performance can be provided by determining a performance based on the audience's emotions and attributes.

[0070] The determination unit can adjust the level of detail of the performance based on the importance of the emotion estimation result when determining the performance. For example, a detailed performance can be determined for an emotion of high importance (e.g., joy, sadness). A simplified performance can also be determined for an emotion of low importance (e.g., surprise, excitement). Furthermore, a performance with a moderate level of detail can also be determined for an emotion of medium importance (e.g., relaxation, concentration). In this way, by adjusting the level of detail of the performance based on the importance of the emotion estimation result, a more appropriate performance can be provided.

[0071] The acquisition unit can perform filtering based on the audience's current environment and situation when acquiring emotion estimation information. For example, when the audience is outdoors, the emotion estimation information is acquired by filtering environmental sounds. When the audience is in a quiet room, the emotion estimation information can be acquired by placing emphasis on subtle sounds and movements. Furthermore, when there is a large audience, the individual emotions can be filtered to acquire information for estimating the overall emotion. In this way, more accurate emotion estimation information can be acquired by filtering based on the current environment and situation.

[0072] The estimation unit can adjust the level of detail of the estimation based on the importance of the emotion estimation information at the time of estimation. For example, information with high importance (e.g., heart rate, brain waves) is preferentially analyzed to perform detailed estimation. Also, information with low importance (e.g., movement, facial expression) can be analyzed simply to reduce the level of detail of the estimation. Furthermore, information with medium importance (e.g., voice, breathing) can be appropriately analyzed to maintain the level of detail of the estimation at a medium level. In this way, by adjusting the level of detail of the estimation based on the importance of the emotion estimation information, more accurate emotion estimation is possible.

[0073] The execution unit can customize the execution means based on the current situation of the audience when performing the performance. For example, if the audience is outdoors, the volume and visual effects can be adjusted. Also, if the audience is indoors, the lighting and sound effects can be adjusted. Furthermore, if there is a large audience, an execution means for the entire audience can be selected. In this way, by customizing the execution means based on the current situation of the audience, a more appropriate performance can be provided.

[0074] The process flow of the first embodiment will be briefly described below.

[0075] Step 1: The acquisition unit acquires emotion estimation information for estimating the emotions of the audience. The emotion estimation information includes facial expression data, voice data, biosensor data, and the like. For example, the acquisition unit may photograph the facial expressions of the audience with a camera and acquire the facial expression data using facial expression recognition technology. It may also record the voices of the audience with a microphone and acquire the voice data using voice analysis technology. Furthermore, it may acquire biometric data such as the heart rate and blood pressure of the audience using a biosensor. Step 2: The estimation unit estimates the emotions of the audience based on the emotion estimation information acquired by the acquisition unit. For example, the estimation unit uses a generative AI to analyze facial expression data and voice data to estimate emotions such as joy, sadness, and surprise. Furthermore, the estimation unit can estimate the average or median of the emotions of multiple spectators, or the most common emotion, as the emotion of the audience. Step 3: The determination unit determines a performance according to the audience's emotions estimated by the estimation unit. For example, if the audience is happy, cheerful music is played, and if they are sad, moving music is played. It is also possible to determine a performance such as a dance performance or pantomime. The determination unit uses the generation AI to determine a performance according to the audience's emotions. Step 4: The execution unit executes the performance determined by the determination unit. For example, the agent can sing, dance, or play an instrument with the audience. The execution unit executes the performance determined by the generation AI.

[0076] (Example 2) The performance robot system according to the embodiment of the present invention is a system that reads the emotions of the audience and performs appropriate music and performance. This system acquires emotion estimation information for estimating the emotions of the audience, and estimates the emotions of the audience based on the acquired information. An appropriate performance is determined according to the estimated emotions, and the performance is executed. For example, information such as the audience's facial expressions, movements, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content is acquired and input to an emotion engine. The emotion engine analyzes the acquired information and estimates the emotions of the audience. For example, the emotion engine can analyze the facial expressions and movements of the audience and estimate emotions such as joy, sadness, and surprise. In addition, the average or median of the emotions of multiple audience members, or the most common emotion, can be estimated as the emotion of the audience. An appropriate performance is determined according to the estimated emotions. For example, if the audience is happy, cheerful music is played, and if the audience is sad, moving music is played. In addition, a performance such as a dance performance or pantomime can be determined according to the emotions of the audience. Finally, the determined performance is executed. For example, the agent can sing, dance, or play an instrument together with the audience. In this way, the agent can read the emotions of the audience and play appropriate music and performances to achieve a more moving performance.This allows the performance robot system to read the emotions of the audience and play appropriate music and performances to achieve a more moving performance.

[0077] The performance robot system according to the embodiment includes an acquisition unit, an estimation unit, a decision unit, and an execution unit. The acquisition unit acquires emotion estimation information for estimating the emotion of the audience. The emotion estimation information for estimating the emotion of the audience includes, but is not limited to, facial expression data, voice data, and biosensor data. For example, the acquisition unit photographs the facial expressions of the audience with a camera and acquires the facial expression data using a facial expression recognition technique. The acquisition unit can also record the voice of the audience with a microphone and acquire the voice data using a voice analysis technique. Furthermore, the acquisition unit can acquire biodata such as the heart rate and blood pressure of the audience using a biosensor. For example, the acquisition unit inputs the facial expression data photographed with the camera to a generation AI, which analyzes the facial expression data to estimate the emotion. The estimation unit estimates the emotion of the audience based on the emotion estimation information acquired by the acquisition unit. The estimation unit analyzes the acquired facial expression data and voice data using, for example, a generation AI, and estimates the emotion of the audience. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, and estimates emotions based on the acquired data. For example, the generation AI analyzes facial expression data and estimates emotions such as joy, sadness, and surprise. The estimation unit can also estimate the average or median of the emotions of multiple audience members, or the most common emotion, as the emotion of the audience. The determination unit determines a performance according to the emotion of the audience estimated by the estimation unit. For example, the determination unit plays cheerful music when the audience is happy, and plays moving music when the audience is sad. The determination unit can also determine a performance such as a dance performance or pantomime according to the emotion of the audience. The determination unit uses, for example, the generation AI to determine a performance according to the emotion of the audience. The generation AI is, for example, a music generation AI or a dance generation AI, and generates a performance according to the emotion of the audience. The execution unit executes the performance determined by the determination unit. For example, the execution unit can make the agent sing, dance, or play an instrument together with the audience. The execution unit executes the determined performance using, for example, a generation AI. The generation AI may be, for example, a music generation AI or a dance generation AI, and executes the determined performance.As a result, the performance robot system according to the embodiment can read the emotions of the audience and provide appropriate music and performance, thereby achieving a more moving performance.

[0078] The acquisition unit acquires emotion estimation information for estimating the emotion of the audience. The emotion estimation information for estimating the emotion of the audience includes, but is not limited to, facial expression data, voice data, and biosensor data. For example, the acquisition unit photographs the facial expressions of the audience with a camera and acquires the facial expression data using a facial expression recognition technology. Specifically, the faces of the audience are photographed from multiple angles using a high-resolution camera, and minute changes in facial expressions are detected using a facial expression recognition algorithm using deep learning. The acquisition unit can also record the voices of the audience with a microphone and acquire the voice data using a voice analysis technology. To acquire the voice data, noise canceling technology is used to remove ambient noise and collect clear voice. Furthermore, the acquisition unit can also acquire biodata such as the heart rate and blood pressure of the audience using a biosensor. The biosensor is provided as a wearable device, and the audience wears it to collect data in real time. For example, the acquisition unit inputs the facial expression data captured by the camera to the generation AI, which analyzes the facial expression data to estimate the emotion. The generation AI has been trained in advance on a large dataset of facial expressions and can estimate emotions such as happiness, sadness, and surprise with a high degree of accuracy. This allows the acquisition unit to collect emotion estimation information from a variety of data sources and accurately grasp the emotions of the audience.

[0079] The estimation unit estimates the emotions of the audience based on the emotion estimation information acquired by the acquisition unit. The estimation unit, for example, uses a generation AI to analyze the acquired facial expression data and voice data to estimate the emotions of the audience. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, and estimates emotions based on the acquired data. Specifically, the generation AI analyzes the facial expression data, extracts facial feature points, and classifies emotions. For voice data, it analyzes features such as tone, pitch, and speed of the voice to estimate emotions. Furthermore, the estimation unit can analyze biosensor data and estimate stress and relaxation states from fluctuations in heart rate and blood pressure. For example, the generation AI analyzes the facial expression data, and estimates emotions such as joy, sadness, and surprise. The estimation unit can also estimate the average or median of the emotions of multiple audience members, or the most common emotion, as the emotion of the audience. This allows the estimation unit to grasp not only the emotions of individual audience members, but also the overall tendency of emotions. Additionally, the estimator can also predict changes in emotions, taking into account past data and trends, for example predicting how emotions will change during a particular performance and allowing for real-time responses, allowing the estimator to estimate audience emotions with high accuracy and improve overall system performance.

[0080] The determination unit determines a performance according to the emotions of the audience estimated by the estimation unit. For example, if the audience is happy, the determination unit plays cheerful music, and if the audience is sad, the determination unit plays moving music. Specifically, the determination unit uses a music generation AI to generate music according to the emotions of the audience. The music generation AI is trained in advance with music data of various genres and tempos, and can generate music that is optimal for the emotions of the audience in real time. The determination unit can also determine a performance such as a dance performance or pantomime according to the emotions of the audience. The dance generation AI generates dance choreography according to the emotions of the audience and issues instructions to the robot. Furthermore, the determination unit adjusts the timing and order of the performance to provide an optimal performance. For example, by performing a cheerful dance performance after moving music, the emotions of the audience can be effectively elicited. The determination unit uses, for example, a generation AI to determine a performance according to the emotions of the audience. The generation AI is, for example, a music generation AI or a dance generation AI, and generates a performance according to the emotions of the audience. As a result, the determination unit can provide a performance that is optimal for the emotions of the audience and realize a more moving experience.

[0081] The execution unit executes the performance determined by the determination unit. For example, the execution unit can make the agent sing, dance, or play a musical instrument together with the audience. Specifically, the execution unit controls the robot actuators to physically execute the determined performance. For example, the execution unit controls the robot's joints and motors to accurately reproduce the dance choreography. In addition, the music generated using the music generation AI is played from the speaker and delivered to the audience. Furthermore, the execution unit can receive feedback in real time and adjust the performance. For example, the reaction of the audience is detected by a sensor and the speed and intensity of the performance are adjusted. The execution unit executes the determined performance, for example, using the generation AI. The generation AI is, for example, a music generation AI or a dance generation AI, and executes the determined performance. As a result, the execution unit can execute the determined performance with high accuracy and impress the audience. Furthermore, the execution unit can also realize a complex performance by coordinating multiple robots and agents. For example, multiple robots can work together to dance and provide a visually and aurally appealing performance. As a result, the execution unit can provide a consistent, high-quality performance to the audience and maximize the effect of the entire system.

[0082] The determination unit can determine a musical performance according to the emotions of the audience as a performance according to the emotions of the audience, and the execution unit can execute the musical performance according to the emotions of the audience. For example, if the audience is happy, the determination unit plays cheerful music, and if the audience is sad, the execution unit plays moving music. The determination unit uses the generation AI to determine the musical performance according to the emotions of the audience. The generation AI is, for example, a music generation AI, and generates music according to the emotions of the audience. The execution unit executes the musical performance determined by the determination unit. For example, the execution unit can cause the agent to sing together with the audience or play an instrument. The execution unit executes the determined musical performance using the generation AI. The generation AI is, for example, a music generation AI, and executes the determined music. This allows a more moving performance to be provided by executing a musical performance according to the emotions of the audience.

[0083] The determination unit can determine a dance performance according to the emotions of the audience as a performance according to the emotions of the audience, and the execution unit can execute the dance performance according to the emotions of the audience. For example, if the audience is happy, the determination unit determines a cheerful dance performance, and if the audience is sad, the determination unit determines a moving dance performance. The determination unit uses a generation AI to determine a dance performance according to the emotions of the audience. The generation AI is, for example, a dance generation AI, and generates a dance according to the emotions of the audience. The execution unit executes the dance performance determined by the determination unit. The execution unit can, for example, allow an agent to dance together with the audience. The execution unit uses the generation AI to execute the determined dance performance. The generation AI is, for example, a dance generation AI, and executes the determined dance. This makes it possible to provide a more moving performance by executing a dance performance according to the emotions of the audience.

[0084] The determination unit determines a pantomime according to the emotions of the audience as a performance according to the emotions of the audience, and the execution unit can execute the pantomime according to the emotions of the audience. For example, if the audience is happy, the determination unit determines a cheerful pantomime, and if the audience is sad, determines a moving pantomime. The determination unit uses a generation AI to determine a pantomime according to the emotions of the audience. The generation AI is, for example, a pantomime generation AI, and generates a pantomime according to the emotions of the audience. The execution unit executes the pantomime determined by the determination unit. For example, the execution unit allows the agent to pantomime together with the audience. The execution unit uses the generation AI to execute the determined pantomime. The generation AI is, for example, a pantomime generation AI, and executes the determined pantomime. This makes it possible to provide a more moving performance by executing a pantomime according to the emotions of the audience.

[0085] The estimation unit can estimate the average or median of the emotions of multiple audience members who make up the audience as the audience's emotion. The estimation unit, for example, calculates the average of the emotions of multiple audience members and estimates the average as the audience's emotion. The estimation unit can also calculate the median of the emotions of multiple audience members and estimate the median as the audience's emotion. The estimation unit uses a generation AI to analyze the emotions of multiple audience members and calculate the average or median. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of multiple audience members. This enables more accurate emotion estimation by integrating the emotions of multiple audience members to estimate the audience's emotion.

[0086] The estimation unit can estimate the most prevalent emotion among the emotions of multiple spectators making up the audience as the emotion of the audience. The estimation unit, for example, identifies the most prevalent emotion among the emotions of the multiple spectators and estimates that emotion as the emotion of the audience. The estimation unit uses a generation AI to analyze the emotions of the multiple spectators and identify the most prevalent emotion. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the multiple spectators. This enables more accurate emotion estimation by estimating the most prevalent emotion among the emotions of the multiple spectators as the emotion of the audience.

[0087] The determination unit can determine a performance according to the audience's emotions based on the audience's emotions and the attributes of the audience. The determination unit determines a performance according to the audience's emotions, taking into account attribute information such as the audience's age, gender, and interests. The determination unit uses a generation AI to analyze the audience's emotions and attribute information and determine an optimal performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the audience's emotions and attribute information. This makes it possible to provide a more appropriate performance by determining a performance based on the audience's emotions and attributes.

[0088] The acquisition unit can acquire one or more pieces of information among the audience's facial expressions, movements, voice, heart rate, blood pressure, pupil response, brainwaves, body temperature, breathing, and posted content as emotion estimation information. For example, the acquisition unit captures the audience's facial expressions with a camera and acquires the facial expression data using facial expression recognition technology. The acquisition unit can also record the audience's voice with a microphone and acquire the voice data using voice analysis technology. Furthermore, the acquisition unit can acquire biometric data such as the audience's heart rate and blood pressure using a biosensor. For example, the acquisition unit inputs the facial expression data captured by the camera to the generation AI, which analyzes the facial expression data to estimate emotions. This allows for more accurate emotion estimation by acquiring a variety of information as emotion estimation information.

[0089] It can function as a performance robot including an acquisition unit, an estimation unit, a decision unit, an execution unit, and a robot body. The acquisition unit, the estimation unit, the decision unit, the execution unit, and the robot body function integrally as a performance robot. For example, the robot body incorporates each unit for estimating the emotions of the audience and performing an appropriate performance. The robot body includes devices such as a camera, a microphone, and a biosensor, and acquires information for estimating the emotions of the audience. The acquired information is analyzed by a generation AI in the robot body, and the emotions of the audience are estimated. Based on the estimated emotions, the generation AI in the robot body determines an appropriate performance, and the robot body executes the performance. In this way, by functioning as a performance robot, it is possible to provide an actual performance to the audience.

[0090] The acquisition unit can estimate the emotions of the audience and adjust the timing of acquiring the emotion estimation information based on the estimated emotions of the audience. For example, when the audience is excited, the acquisition unit can increase the frequency of acquiring the emotion estimation information. Also, when the audience is relaxed, the acquisition unit can reduce the frequency of acquiring the emotion estimation information. Furthermore, when the audience is focused, the acquisition unit can keep the timing of acquiring the emotion estimation information constant. The acquisition unit uses the generation AI to analyze the emotions of the audience and adjust the acquisition timing. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the timing of acquiring the emotion estimation information to be adjusted, thereby acquiring information at a more appropriate timing.

[0091] The acquisition unit can analyze the past emotion data of the audience and select the optimal acquisition method. For example, the acquisition unit can analyze from the past emotion data that emotions are likely to fluctuate during a specific time period, and acquire information focusing on that time period. The acquisition unit can also analyze from the past emotion data that emotions fluctuate during a specific event or situation, and select an acquisition method according to that situation. Furthermore, the acquisition unit can analyze from the past emotion data that a specific emotion tends to continue for a long time, and reduce the acquisition frequency while that emotion continues. The acquisition unit uses the generation AI to analyze the past emotion data and select the optimal acquisition method. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past emotion data. In this way, the optimal acquisition method can be selected by analyzing the past emotion data.

[0092] The acquisition unit can perform filtering based on the current environment and situation of the audience when acquiring the emotion estimation information. For example, when the audience is outdoors, the acquisition unit can filter environmental sounds to acquire emotion estimation information. Also, when the audience is in a quiet room, the acquisition unit can also acquire emotion estimation information by placing emphasis on subtle voices and actions. Furthermore, when there is a large audience, the acquisition unit can also acquire information for estimating the overall emotion by filtering individual emotions. The acquisition unit uses a generation AI to analyze the current environment and situation of the audience and perform filtering. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the environment and situation of the audience. As a result, more accurate emotion estimation information can be acquired by filtering based on the current environment and situation.

[0093] The acquisition unit can estimate the emotions of the audience and determine the priority of emotion estimation information to be acquired based on the estimated emotions of the audience. For example, when the audience is excited, the acquisition unit prioritizes acquiring facial expression and movement information. When the audience is relaxed, the acquisition unit can also prioritize acquiring heart rate and breathing information. Furthermore, when the audience is focused, the acquisition unit can also prioritize acquiring voice and pupil response information. The acquisition unit uses a generation AI to analyze the emotions of the audience and determine the priority of information to be acquired. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. In this way, the priority of emotion estimation information can be determined, and more important information can be acquired preferentially.

[0094] When acquiring emotion estimation information, the acquisition unit can preferentially acquire highly relevant information by taking into account the geographical location information of the audience. For example, when the audience is at a specific event venue, the acquisition unit preferentially acquires information related to the event. Also, when the audience is at a tourist spot, the acquisition unit can preferentially acquire information related to the tourist spot. Furthermore, when the audience is at home, the acquisition unit can also acquire information by referring to past emotion data at home. The acquisition unit uses the generation AI to analyze the geographical location information of the audience and preferentially acquire highly relevant information. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information of the audience. As a result, highly relevant information can be preferentially acquired by taking into account the geographical location information.

[0095] The acquisition unit can analyze the audience's social media activity and acquire related information when acquiring emotion estimation information. For example, when the audience posts about a specific event on social media, the acquisition unit acquires information related to the event. Also, when the audience expresses a specific emotion on social media, the acquisition unit can acquire information related to the emotion. Furthermore, when the audience posts about a specific place on social media, the acquisition unit can acquire information related to the place. The acquisition unit uses a generation AI to analyze the audience's social media activity and acquire related information. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the audience's social media activity. In this way, related information can be acquired by analyzing social media activity.

[0096] The estimation unit can estimate the emotions of the audience and adjust the emotion estimation algorithm based on the estimated emotions of the audience. For example, when the audience is excited, the estimation unit can increase the sensitivity of the emotion estimation algorithm. Also, when the audience is relaxed, the estimation unit can lower the sensitivity of the emotion estimation algorithm. Furthermore, when the audience is focused, the sensitivity of the emotion estimation algorithm can be kept constant. The estimation unit uses the generation AI to analyze the emotions of the audience and adjust the emotion estimation algorithm. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows for more accurate emotion estimation by adjusting the emotion estimation algorithm.

[0097] The estimation unit can adjust the level of detail of the estimation based on the importance of the emotion estimation information at the time of estimation. For example, the estimation unit preferentially analyzes information with high importance (e.g., heart rate, brain waves) and performs detailed estimation. Also, the estimation unit can simply analyze information with low importance (e.g., movement, facial expression) and reduce the level of detail of the estimation. Furthermore, the estimation unit can moderately analyze information with medium importance (e.g., voice, breathing) and keep the level of detail of the estimation at a medium level. The estimation unit uses a generation AI to analyze the importance of the emotion estimation information and adjust the level of detail of the estimation. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of the emotion estimation information. This allows for more accurate emotion estimation by adjusting the level of detail of the estimation based on the importance of the emotion estimation information.

[0098] The estimation unit can apply different estimation algorithms depending on the category of the emotion estimation information at the time of estimation. For example, the estimation unit applies an image analysis algorithm to facial expression information and an audio analysis algorithm to audio information. In addition, the estimation unit can also apply a biosignal analysis algorithm to heart rate information. The estimation unit uses a generation AI to apply an optimal estimation algorithm depending on the category of the emotion estimation information. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and performs analysis depending on the category of the emotion estimation information. This enables more accurate emotion estimation by applying an optimal estimation algorithm depending on the category of the emotion estimation information.

[0099] The estimation unit can estimate the emotions of the audience and adjust the display method of the estimation result based on the estimated emotions of the audience. For example, if the audience is excited, the estimation unit can provide a visually stimulating display method. If the audience is relaxed, the estimation unit can also provide a calm display method. Furthermore, if the audience is focused, the estimation unit can also provide a simple and highly visible display method. The estimation unit uses a generation AI to analyze the emotions of the audience and adjust the display method of the estimation result. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. As a result, more appropriate information can be provided to the audience by adjusting the display method of the estimation result.

[0100] The estimation unit can determine the priority of estimation based on the acquisition time of the emotion estimation information at the time of estimation. For example, the estimation unit preferentially analyzes the latest emotion estimation information. Also, the estimation unit can prioritize the latest information while referring to past emotion estimation information. Furthermore, the estimation unit can preferentially analyze emotion estimation information acquired in a specific time period. The estimation unit uses a generation AI to analyze the acquisition time of the emotion estimation information and determine the priority of estimation. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the acquisition time of the emotion estimation information. In this way, by determining the priority of estimation based on the acquisition time of the emotion estimation information, more appropriate information can be preferentially analyzed.

[0101] The estimation unit can adjust the order of estimation based on the relevance of the emotion estimation information at the time of estimation. For example, the estimation unit preferentially analyzes information with high relevance. Also, the estimation unit can analyze information with medium relevance next. Furthermore, the estimation unit can analyze information with low relevance last. The estimation unit uses a generation AI to analyze the relevance of the emotion estimation information and adjust the order of estimation. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of the emotion estimation information. This enables more efficient emotion estimation by adjusting the order of estimation based on the relevance of the emotion estimation information.

[0102] The decision unit can estimate the emotions of the audience and adjust the way the performance is expressed based on the estimated emotions of the audience. For example, if the audience is excited, the decision unit can select an energetic way of expression. If the audience is relaxed, the decision unit can also select a calm way of expression. Furthermore, if the audience is focused, the decision unit can select a simple and highly visible way of expression. The decision unit uses a generation AI to analyze the emotions of the audience and adjust the way the performance is expressed. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the way the performance is expressed to be adjusted to provide a more appropriate performance to the audience.

[0103] The determination unit can adjust the level of detail of the performance based on the importance of the emotion estimation result when determining the performance. For example, the determination unit can determine a detailed performance for an emotion with high importance (e.g., joy, sadness). Also, the determination unit can determine a simplified performance for an emotion with low importance (e.g., surprise, excitement). Furthermore, the determination unit can determine a performance with a moderate level of detail for an emotion with medium importance (e.g., relaxation, concentration). The determination unit uses the generation AI to analyze the importance of the emotion estimation result and adjust the level of detail of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of the emotion estimation result. This makes it possible to provide a more appropriate performance by adjusting the level of detail of the performance based on the importance of the emotion estimation result.

[0104] The determination unit can apply different performance algorithms depending on the category of the emotion estimation result when determining the performance. For example, the determination unit can apply a cheerful music performance algorithm to the emotion of joy. Also, the determination unit can apply a moving music performance algorithm to the emotion of sadness. Furthermore, the determination unit can apply a visually stimulating performance algorithm to the emotion of surprise. The determination unit uses the generation AI to apply an optimal performance algorithm depending on the category of the emotion estimation result. The generation AI is, for example, a music generation AI or a dance generation AI, and generates a performance depending on the category of the emotion estimation result. In this way, a more appropriate performance can be provided by applying an optimal performance algorithm depending on the category of the emotion estimation result.

[0105] The decision unit can estimate the emotions of the audience and adjust the length of the performance based on the estimated emotions of the audience. For example, if the audience is excited, the decision unit can determine a short and energetic performance. Also, if the audience is relaxed, the decision unit can determine a long and calm performance. Furthermore, if the audience is focused, the decision unit can determine a performance of moderate length. The decision unit uses a generation AI to analyze the emotions of the audience and adjust the length of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the length of the performance to be adjusted to provide a more appropriate performance for the audience.

[0106] The determination unit can determine the priority order of performance based on the acquisition time of emotion estimation results when determining performance. The determination unit determines the priority order of performance based on, for example, the latest emotion estimation result. Also, the determination unit can emphasize the latest result while referring to past emotion estimation results. Furthermore, the determination unit can determine the priority order of performance based on emotion estimation results acquired in a specific time period. The determination unit uses a generation AI to analyze the acquisition time of the emotion estimation result and determine the priority order of performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the acquisition time of the emotion estimation result. In this way, a more appropriate performance can be provided by determining the priority order of performance based on the acquisition time of the emotion estimation result.

[0107] The determination unit can adjust the order of performances based on the relevance of emotion estimation results when determining the performances. The determination unit can, for example, determine the order of performances based on emotions with high relevance. It can also determine the order of performances next based on emotions with medium relevance. It can also determine the order of performances last based on emotions with low relevance. The determination unit uses a generation AI to analyze the relevance of emotion estimation results and adjust the order of performances. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of emotion estimation results. This makes it possible to provide a more appropriate performance by adjusting the order of performances based on the relevance of emotion estimation results.

[0108] The execution unit can estimate the emotions of the audience and adjust the execution method of the performance based on the estimated emotions of the audience. For example, if the audience is excited, the execution unit can select an energetic execution method. If the audience is relaxed, the execution unit can also select a calm execution method. Furthermore, if the audience is focused, the execution unit can select a simple and highly visible execution method. The execution unit uses the generation AI to analyze the emotions of the audience and adjust the execution method of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the execution method of the performance to be adjusted to provide a more appropriate performance to the audience.

[0109] The execution unit can select the optimal execution method by referring to past performance data when performing a performance. The execution unit, for example, selects a successful execution method from past performance data. Also, it can avoid unsuccessful execution methods from past performance data. Furthermore, it can select an execution method that is effective for a specific emotion from past performance data. The execution unit uses a generation AI to analyze past performance data and select the optimal execution method. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past performance data. In this way, it is possible to select the optimal execution method by referring to past performance data.

[0110] The execution unit can customize the execution means based on the current situation of the audience when performing the performance. For example, if the audience is outdoors, the execution unit can adjust the volume and visual effects. If the audience is indoors, the execution unit can also adjust the lighting and sound effects. Furthermore, if there is a large audience, the execution unit can select an execution means for the entire audience. The execution unit uses a generation AI to analyze the current situation of the audience and customize the execution means. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the current situation of the audience. This makes it possible to provide a more appropriate performance by customizing the execution means based on the current situation of the audience.

[0111] The execution unit can estimate the emotions of the audience and determine the execution priority of the performance based on the estimated emotions of the audience. For example, if the audience is excited, the execution unit can prioritize an energetic performance. Also, if the audience is relaxed, the execution unit can prioritize a calm performance. Furthermore, if the audience is focused, the execution unit can prioritize a simple and highly visible performance. The execution unit uses a generation AI to analyze the emotions of the audience and determine the execution priority of the performance. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the emotions of the audience. This allows the execution priority of the performance to be determined, thereby providing a more appropriate performance.

[0112] When performing a performance, the execution unit can select the optimal execution method by taking into account the geographic location information of the audience. For example, if the audience is at a specific event venue, the execution unit selects an execution method suitable for the event. Also, if the audience is at a tourist spot, the execution unit can select an execution method related to the tourist spot. Furthermore, if the audience is at home, the execution unit can select a method that is easy to execute at home. The execution unit uses a generation AI to analyze the geographic location information of the audience and select the optimal execution method. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographic location information of the audience. This makes it possible to select the optimal execution method by taking into account the geographic location information.

[0113] The execution unit can analyze the audience's social media activity and suggest execution means when performing a performance. For example, if the audience posts about a specific event on social media, the execution unit can suggest execution means related to the event. In addition, if the audience expresses a specific emotion on social media, the execution unit can also suggest execution means related to the emotion. Furthermore, if the audience posts about a specific place on social media, the execution unit can also suggest execution means related to the place. The execution unit uses a generative AI to analyze the audience's social media activity and suggest execution means. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the audience's social media activity. This makes it possible to suggest more appropriate execution means by analyzing social media activity.

[0114] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0115] When acquiring emotion estimation information for the audience, the acquisition unit can optimize the method of acquiring current emotion estimation information by referring to the audience's past emotion data. For example, if it is known from past data that emotions are likely to fluctuate during a specific time period, information can be acquired with a focus on that time period. Also, if it is known that emotions fluctuate during a specific event or situation, an acquisition method can be selected according to that situation. Furthermore, if a specific emotion tends to last for a long time, the acquisition frequency can be reduced while that emotion continues. This makes it possible to utilize past emotion data to perform more accurate emotion estimation.

[0116] When estimating the emotions of the audience, the estimation unit can apply different estimation algorithms depending on the category of the emotion estimation information. For example, an image analysis algorithm can be applied to facial expression information, and a voice analysis algorithm can be applied to voice information. Also, a biosignal analysis algorithm can be applied to heart rate information. In this way, more accurate emotion estimation can be achieved by applying the optimal estimation algorithm depending on the category of the emotion estimation information.

[0117] The determination unit can determine a performance according to the audience's emotions based on the audience's emotions and attributes. For example, the determination unit determines a performance according to the audience's emotions taking into account attribute information such as the audience's age, gender, and interests. In this way, a more appropriate performance can be provided by determining a performance based on the audience's emotions and attributes.

[0118] The execution unit can estimate the emotions of the audience and adjust the execution method of the performance based on the estimated emotions of the audience. For example, if the audience is excited, an energetic execution method can be selected. If the audience is relaxed, a calm execution method can be selected. Furthermore, if the audience is focused, a simple and highly visible execution method can be selected. This allows a more appropriate performance to be provided to the audience.

[0119] The estimation unit can estimate the emotions of the audience and adjust the emotion estimation algorithm based on the estimated emotions of the audience. For example, if the audience is excited, the sensitivity of the emotion estimation algorithm can be increased. Also, if the audience is relaxed, the sensitivity of the emotion estimation algorithm can be decreased. Furthermore, if the audience is focused, the sensitivity of the emotion estimation algorithm can be kept constant. In this way, by adjusting the emotion estimation algorithm, more accurate emotion estimation can be achieved.

[0120] The determination unit can adjust the level of detail of the performance based on the importance of the emotion estimation result when determining the performance. For example, a detailed performance can be determined for an emotion of high importance (e.g., joy, sadness). A simplified performance can also be determined for an emotion of low importance (e.g., surprise, excitement). Furthermore, a performance with a moderate level of detail can also be determined for an emotion of medium importance (e.g., relaxation, concentration). In this way, by adjusting the level of detail of the performance based on the importance of the emotion estimation result, a more appropriate performance can be provided.

[0121] The acquisition unit can perform filtering based on the audience's current environment and situation when acquiring emotion estimation information. For example, when the audience is outdoors, the emotion estimation information is acquired by filtering environmental sounds. When the audience is in a quiet room, the emotion estimation information can be acquired by placing emphasis on subtle sounds and movements. Furthermore, when there is a large audience, the individual emotions can be filtered to acquire information for estimating the overall emotion. In this way, more accurate emotion estimation information can be acquired by filtering based on the current environment and situation.

[0122] The estimation unit can adjust the level of detail of the estimation based on the importance of the emotion estimation information at the time of estimation. For example, information with high importance (e.g., heart rate, brain waves) is preferentially analyzed to perform detailed estimation. Also, information with low importance (e.g., movement, facial expression) can be analyzed simply to reduce the level of detail of the estimation. Furthermore, information with medium importance (e.g., voice, breathing) can be appropriately analyzed to maintain the level of detail of the estimation at a medium level. In this way, by adjusting the level of detail of the estimation based on the importance of the emotion estimation information, more accurate emotion estimation is possible.

[0123] The decision unit can estimate the emotions of the audience and adjust the manner of expression of the performance based on the estimated emotions of the audience. For example, if the audience is excited, an energetic manner of expression can be selected. If the audience is relaxed, a calm manner of expression can be selected. Furthermore, if the audience is focused, a simple and highly visible manner of expression can be selected. In this way, by adjusting the manner of expression of the performance, a more appropriate performance can be provided to the audience.

[0124] The execution unit can customize the execution means based on the current situation of the audience when performing the performance. For example, if the audience is outdoors, the volume and visual effects can be adjusted. Also, if the audience is indoors, the lighting and sound effects can be adjusted. Furthermore, if there is a large audience, an execution means for the entire audience can be selected. In this way, by customizing the execution means based on the current situation of the audience, a more appropriate performance can be provided.

[0125] The process flow of the second embodiment will be briefly described below.

[0126] Step 1: The acquisition unit acquires emotion estimation information for estimating the emotions of the audience. The emotion estimation information includes facial expression data, voice data, biosensor data, and the like. For example, the acquisition unit may photograph the facial expressions of the audience with a camera and acquire the facial expression data using facial expression recognition technology. It may also record the voices of the audience with a microphone and acquire the voice data using voice analysis technology. Furthermore, it may acquire biometric data such as the heart rate and blood pressure of the audience using a biosensor. Step 2: The estimation unit estimates the emotions of the audience based on the emotion estimation information acquired by the acquisition unit. For example, the estimation unit uses a generative AI to analyze facial expression data and voice data to estimate emotions such as joy, sadness, and surprise. Furthermore, the estimation unit can estimate the average or median of the emotions of multiple spectators, or the most common emotion, as the emotion of the audience. Step 3: The determination unit determines a performance according to the audience's emotions estimated by the estimation unit. For example, if the audience is happy, cheerful music is played, and if they are sad, moving music is played. It is also possible to determine a performance such as a dance performance or pantomime. The determination unit uses the generation AI to determine a performance according to the audience's emotions. Step 4: The execution unit executes the performance determined by the determination unit. For example, the agent can sing, dance, or play an instrument with the audience. The execution unit executes the performance determined by the generation AI.

[0127] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0128] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0129] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0130] For example, the acquisition unit acquires the facial expressions and voices of the audience using the camera 42 and microphone 38B of the smart device 14, and the acquired expressions and voices are analyzed by the specific processing unit 290 of the data processing device 12. The estimation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the emotions of the audience based on the acquired data. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines a performance according to the estimated emotions. The execution unit is realized, for example, by the control unit 46A of the smart device 14, and executes the determined performance. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0131] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0132] 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.

[0133] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0134] 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.

[0135] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0136] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0137] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0138] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0139] 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.

[0140] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0141] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0142] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0143] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0144] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0145] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0146] For example, the acquisition unit acquires the facial expressions and voices of the audience using the camera 42 and microphone 238 of the smart glasses 214, and the acquired expressions and voices are analyzed by the specific processing unit 290 of the data processing device 12. The estimation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the emotions of the audience based on the acquired data. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines a performance according to the estimated emotions. The execution unit is realized, for example, by the control unit 46A of the smart glasses 214, and executes the determined performance. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0147] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0148] 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.

[0149] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0150] 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.

[0151] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0152] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0153] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0154] 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.

[0155] 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.

[0156] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0157] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0158] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0159] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0160] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0161] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0162] For example, the acquisition unit acquires the facial expressions and voices of the audience using the camera 42 and microphone 238 of the headset type terminal 314, and the acquired expressions and voices are analyzed by the specific processing unit 290 of the data processing device 12. The estimation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the emotions of the audience based on the acquired data. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines a performance according to the estimated emotions. The execution unit is realized, for example, by the control unit 46A of the headset type terminal 314, and executes the determined performance. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0163] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0164] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0165] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0166] 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.

[0167] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0168] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0169] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0170] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0171] 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.

[0172] 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.

[0173] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0174] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0175] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0176] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0177] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0178] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0179] For example, the acquisition unit acquires the facial expressions and voices of the audience using the camera 42 and microphone 238 of the robot 414, and the acquired expressions and voices are analyzed by the specific processing unit 290 of the data processing device 12. The estimation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and estimates the emotions of the audience based on the acquired data. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines a performance according to the estimated emotions. The execution unit is realized, for example, by the control unit 46A of the robot 414, and executes the determined performance. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various modifications are possible.

[0180] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0181] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0182] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0183] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0184] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0185] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0186] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0187] 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.

[0188] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0189] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0190] 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.

[0191] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0192] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0193] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0194] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0195] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0196] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0197] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0198] (Appendix 1) An acquisition unit that acquires emotion estimation information for estimating an emotion of an audience; an estimation unit that estimates an emotion of an audience based on the emotion estimation information acquired by the acquisition unit; A determination unit that determines a performance according to the emotion of the audience estimated by the estimation unit; an execution unit that executes the performance determined by the determination unit; A system characterized by: (Appendix 2) The determination unit is determining a musical performance responsive to the audience's emotions as a performance responsive to the audience's emotions; The execution unit is Performing a musical performance according to the emotions of the audience 2. The system of claim 1, (Appendix 3) The determination unit is determining a dance performance corresponding to the emotions of the audience as a performance corresponding to the emotions of the audience; The execution unit is Perform a dance performance according to the emotions of the audience. 2. The system of claim 1, (Appendix 4) The determination unit is determining a pantomime corresponding to the emotion of the audience as a performance corresponding to the emotion of the audience; The execution unit is Perform pantomimes according to the emotions of the audience 2. The system of claim 1, (Appendix 5) The estimation unit is The average or median of the emotions of the multiple spectators constituting the audience is estimated as the emotion of the audience. 2. The system of claim 1, (Appendix 6) The estimation unit is A majority of emotions among the emotions of the multiple spectators constituting the audience are estimated as the emotions of the audience. 2. The system of claim 1, (Appendix 7) The determination unit is Determine a performance according to the emotions of the audience based on the emotions of the audience and the attributes of the audience. 2. The system of claim 1, (Appendix 8) The acquisition unit is One or more pieces of information among the audience's facial expressions, movements, voices, heart rates, blood pressure, pupil responses, brain waves, body temperatures, breathing, and posted content are acquired as the emotion estimation information. 2. The system of claim 1, (Appendix 9) A robot that functions as a performance robot including the acquisition unit, the estimation unit, the decision unit, the execution unit, and a robot body. 2. The system of claim 1, (Appendix 10) The acquisition unit is To estimate the emotion of an audience and adjust the timing of acquiring information for emotion estimation based on the estimated emotion of the audience. 2. The system of claim 1, (Appendix 11) The acquisition unit is Analyze past audience sentiment data and choose the best way to capture it 2. The system of claim 1, (Appendix 12) The acquisition unit is When acquiring information for emotion estimation, filtering is performed based on the audience's current environment and situation. 2. The system of claim 1, (Appendix 13) The acquisition unit is To estimate an audience's emotion and determine a priority order of emotion estimation information to be acquired based on the estimated audience's emotion. 2. The system of claim 1, (Appendix 14) The acquisition unit is When acquiring information for emotion estimation, the geographic location information of the audience is taken into consideration to prioritize acquisition of information with high relevance. 2. The system of claim 1, (Appendix 15) The acquisition unit is When obtaining information for sentiment estimation, analyze the audience's social media activity to obtain relevant information. 2. The system of claim 1, (Appendix 16) The estimation unit is Estimating audience sentiment and adjusting sentiment estimation algorithms based on estimated audience sentiment 2. The system of claim 1, (Appendix 17) The estimation unit is During estimation, the level of detail of the estimation is adjusted based on the importance of the emotion estimation information. 2. The system of claim 1, (Appendix 18) The estimation unit is During estimation, different estimation algorithms are applied depending on the category of emotion estimation information. 2. The system of claim 1, (Appendix 19) The estimation unit is Estimate audience sentiment and adjust how the results are displayed based on the estimated audience sentiment 2. The system of claim 1, (Appendix 20) The estimation unit is During estimation, the priority of estimation is determined based on the time when emotion estimation information was acquired. 2. The system of claim 1, (Appendix 21) The estimation unit is During estimation, the order of estimation is adjusted based on the relevance of emotion estimation information. 2. The system of claim 1, (Appendix 22) The determination unit is Estimate audience emotions and adjust performance based on estimated audience emotions 2. The system of claim 1, (Appendix 23) The determination unit is When determining performance, adjust the level of detail in performance based on the importance of emotion estimation results. 2. The system of claim 1, (Appendix 24) The determination unit is When determining performance, different performance algorithms are applied depending on the category of the emotion estimation result. 2. The system of claim 1, (Appendix 25) The determination unit is Estimate audience sentiment and adjust performance length based on estimated audience sentiment 2. The system of claim 1, (Appendix 26) The determination unit is When deciding on performance, prioritize performance based on when emotion estimation results were obtained. 2. The system of claim 1, (Appendix 27) The determination unit is When deciding on performance, adjust the order of performance based on the relevance of emotion estimation results. 2. The system of claim 1, (Appendix 28) The execution unit is Estimate audience emotions and adjust performance execution based on estimated audience emotions 2. The system of claim 1, (Appendix 29) The execution unit is When executing a performance test, the optimal execution method is selected by referring to past performance data. 2. The system of claim 1, (Appendix 30) The execution unit is Customize your delivery based on the audience's current situation during the performance 2. The system of claim 1, (Appendix 31) The execution unit is Estimate audience sentiment and prioritize performance execution based on estimated audience sentiment 2. The system of claim 1, (Appendix 32) The execution unit is When performing a performance, the optimal execution method is selected taking into account the geographic location information of the audience. 2. The system of claim 1, (Appendix 33) The execution unit is Analyze audience social media activity and suggest action steps during performance 2. The system of claim 1, [Explanation of symbols]

[0199] 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 acquisition unit that acquires emotion estimation information for estimating an emotion of an audience; an estimation unit that estimates the emotion of the audience based on the emotion estimation information acquired by the acquisition unit; A determination unit that determines a performance according to the emotion of the audience estimated by the estimation unit; an execution unit that executes the performance determined by the determination unit; A system characterized by:

2. The determination unit is determining a musical performance responsive to the audience's emotions as a performance responsive to the audience's emotions; The execution unit is Performing a musical performance according to the emotions of the audience 2. The system of claim 1 .

3. The determination unit is determining a dance performance corresponding to the emotions of the audience as a performance corresponding to the emotions of the audience; The execution unit is Perform a dance performance according to the emotions of the audience.

2. The system of claim 1 .

4. The determination unit is determining a pantomime corresponding to the emotion of the audience as a performance corresponding to the emotion of the audience; The execution unit is Perform pantomimes according to the emotions of the audience 2. The system of claim 1 .

5. The estimation unit is The average or median of the emotions of the multiple spectators constituting the audience is estimated as the emotion of the audience.

2. The system of claim 1 .

6. The estimation unit is A majority of emotions among the emotions of a plurality of spectators constituting the audience are estimated as the emotions of the audience.

2. The system of claim 1 .

Images