system

Abstract

We provide the system. [Solution] Methods for collecting data from past talent contests, A means for analyzing the aforementioned data to extract language structure and evaluation trends, A generation means for generating a new script based on the analyzed data, A method for selecting performers to use the generated script and for them to practice together, An evaluation means that records and analyzes the aforementioned practice process and provides feedback, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Among the various artificial intelligence technologies emerging, it is required to clearly show the strength of domestic generative AI to the world. However, there is a lack of means to easily perceive the superiority of generative AI and express it in a form including cultural elements. As a result, it has become difficult to properly evaluate the performance and applicable range of generative AI. In response to this problem, it is necessary to show specific application examples in which generative AI skillfully uses language.

Means for Solving the Problems

[0005] This system utilizes data from past talent contests to generate new scripts using a generative AI, selects performers during the process, and provides support from rehearsal to the actual performance. Specifically, it analyzes collected data to extract linguistic structure and evaluation trends, and the generative AI creates multiple script variations. Then, it practices with the selected performers, recording and analyzing the process to provide feedback and optimize performance. This entire process makes it possible to concretely and effectively demonstrate the linguistic capabilities and practicality of the generative AI.

[0006] "Data" refers to information resources such as scripts, performance videos, and judges' evaluations obtained from past talent contests.

[0007] "Analysis" is the process of extracting linguistic structures and evaluation trends from collected data to obtain useful insights.

[0008] "Generation means" refers to algorithms and processes that automatically create new scripts based on analyzed information.

[0009] "Selection" refers to the process of choosing performers to act out the generated script.

[0010] "Rehearsal" refers to a series of activities in which selected performers prepare their performance based on a generated script.

[0011] "Recording" refers to the act of saving footage of practice sessions or performances on media such as video.

[0012] "Evaluation means" refers to means and methods for analyzing recorded information and indicating areas for performance improvement.

[0013] "Optimization" is a series of processes that improve the quality of the script and acting based on feedback. [Brief explanation of the drawing]

[0014] [Figure 1]It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

MODE FOR CARRYING OUT THE INVENTION

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units 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), and the like.

[0018] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, the numbered 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), or magnetic tapes, etc.

[0020] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] This invention relates to a system that utilizes generative AI to gain an advantage in performing arts contests. In this system, the process from data collection to final performance is carried out seamlessly through the collaboration of a server, terminals, and users (administrators and performers).

[0036] First, the server collects data from past talent contests from the internet and stores it in a database. This data includes unformatted scripts, video recordings, and evaluation metadata. Next, the server analyzes the collected data using natural language processing techniques and machine learning algorithms. Specifically, it identifies the characteristics of language structure, factors that induce laughter, and elements that influence performance evaluations. This analysis identifies useful patterns and trends.

[0037] Based on the analysis results, the server's generation AI model generates a new script. At this stage, multiple script variations are created based on different themes and contexts. This generated script is then provided to performers selected by the user. The selection process is conducted in an audition format, where performers are evaluated to determine which performer is best suited to deliver a performance using parts of the script provided by the generation AI.

[0038] Next, the terminal assists the selected performer in a practice session. During practice, the performer adjusts their performance based on the generated script and repeatedly tries and fails. The terminal records this process on video and sends the data to the server. Based on the transmitted data, the server's evaluation system generates detailed feedback and provides areas for improvement in the practice. This feedback covers a wide range of aspects, including timing of utterances, expression of emotion, and pacing.

[0039] The final performance is optimized through the aforementioned feedback loop. Users leverage the insights gained throughout the entire process to prepare for the actual production environment. A documentary recording this entire process is also created and used to widely publicize the capabilities of the generative AI.

[0040] Thus, this system can maximize the linguistic capabilities of generative AI and demonstrate an advantage in performing arts competitions. Specifically, it provides a series of processes for achieving a mature performance through practice and optimization based on AI-generated scripts.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server collects data related to past talent contests from the internet. This data includes script text, performance videos, and judges' evaluations. The server stores this data in a database.

[0044] Step 2:

[0045] The server preprocesses the collected data. Specifically, it tokenizes text data and transcribes audio from video data. It also removes unnecessary data and converts it into a format suitable for analysis.

[0046] Step 3:

[0047] The server analyzes pre-processed data using natural language processing techniques. This analysis aims to identify common patterns in successful scripts from the contest and elements that received particularly high ratings. Machine learning algorithms are used to extract useful trends.

[0048] Step 4:

[0049] The server generates a new script based on the analysis results. Using generation AI, it creates multiple script variations suitable for various themes and styles. The generated results are presented to the user, who selects the most suitable one.

[0050] Step 5:

[0051] The user holds auditions to select suitable performers to act out the chosen scripts. The selected performers then perform trial acting based on the server-generated scripts to check their fit.

[0052] Step 6:

[0053] The device records the performer's practice sessions and sends them to the server. During practice, the performance is fine-tuned based on the generated script. All practice sessions are recorded in detail using the device's recording function.

[0054] Step 7:

[0055] The server analyzes the practice data sent from the terminal and generates feedback. Specifically, it analyzes performance elements such as speech timing, emotional expression, and pacing in detail and provides suggestions for improvement.

[0056] Step 8:

[0057] Based on feedback from the server, users optimize the performer's performance and the script. By repeatedly practicing with the improvements incorporated, they prepare for the final performance in the best possible state.

[0058] Step 9:

[0059] After the user completes their final preparations, they will participate in the actual talent show competition, showcasing the results of their training. This process will be recorded and later used to create a documentary widely promoting the capabilities of the generative AI.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] In entertainment contests, high-quality performances require performers to prepare appropriate scripts and to practice them repeatedly to perform them effectively. However, traditional methods have challenges in terms of efficiency and accuracy in generating appropriate scripts and optimizing the practice process. In particular, the lack of objective, data-driven feedback makes improving performance time-consuming and labor-intensive.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes means for acquiring information on past performing arts competitions, means for analyzing the information to extract language structure and evaluation characteristics, and means for generating new documents based on the analyzed information. This enables performers to efficiently obtain high-quality scripts and prepare for optimal performances while receiving objective, data-driven feedback.

[0065] "Information" refers to a collection of various data related to past entertainment competitions, specifically including scripts, video recordings, and metadata related to evaluations.

[0066] "Analysis" is the act of processing collected information and extracting linguistic structures and evaluation characteristics to identify useful patterns and trends.

[0067] A "document" refers to a new script or content generated based on the analyzed data, which serves as a guideline for performers to carry out their performance.

[0068] "Performers" refer to individuals or groups who perform acts such as acting or speeches based on the generated documents.

[0069] "Improvement suggestions" include specific advice and feedback on performance, such as timing and pauses in speech, based on records and analysis of the practice process.

[0070] "Means" refers to the components or technical elements used to realize the specific functions or processing processes described within the patent claims.

[0071] This invention is designed as a system that improves the quality of performances in entertainment contests by utilizing a generative AI model. Specific embodiments are described below.

[0072] The server first retrieves information related to past entertainment competitions that is publicly available on the internet. This information includes various metadata related to scripts, video recordings, and evaluations. Web scraping techniques are used for retrieval, such as utilizing the Python BeautifulSoup library. This data is then formatted by the server and stored in a database.

[0073] Next, the server analyzes the collected information using natural language processing techniques and machine learning algorithms. This process involves using the Python spaCy library to analyze language structure and extract laughter-inducing language patterns. Additionally, it trains a machine learning model using TENSORFLOW® to identify factors influencing performance evaluation.

[0074] Once the analysis is complete, the server generates a new document using a generative AI model. This AI model might use, for example, OpenAI®'s GPT, and is given prompts such as, "Generate a script for a comedy performance. The theme is 'Everyday Humor'." This generated document is then used by the user to select the most suitable performer.

[0075] The terminal supports the practice session with the selected performer. The terminal records the performer's practice on video and sends the data to the server. The server analyzes the transmitted video data and generates feedback that provides the performer with multifaceted improvement suggestions. This feedback includes aspects such as speech timing and emotional expression.

[0076] Ultimately, users optimize performance based on feedback from the executor. Leveraging the insights gained throughout the entire process, they are prepared to deliver successful final performance. A documentary recording this entire process serves as crucial material demonstrating the capabilities of the generative AI model.

[0077] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0078] Step 1:

[0079] The server retrieves information about past performing arts competitions from the internet. It uses publicly available data related to these competitions as input. This data includes scripts, video recordings, and evaluation metadata. Specifically, the server uses web scraping tools, for example, the BeautifulSoup library in Python, to parse HTML pages, extract data, and store it in a database. The output is a formalized database record.

[0080] Step 2:

[0081] The server analyzes the acquired information using natural language processing techniques. The input consists of text data and metadata stored in a database. Specifically, the server uses the Python spaCy library to analyze language patterns and identify elements that induce laughter. It also trains a machine learning model using TensorFlow to extract factors that influence performance evaluation. The output is data on language structure and evaluation characteristics obtained through the analysis.

[0082] Step 3:

[0083] The server launches a generative AI model to generate documents based on the analyzed data. The inputs used are patterns and evaluation characteristics obtained in the analysis step. Specifically, the generative AI model is prompted with a sentence, for example, "Generate a script for a comedy performance. The theme is 'Everyday Humor'," which generates multiple document variations. The output is the generated script candidates.

[0084] Step 4:

[0085] The user selects performers based on the generated documents. The input includes multiple generated script variations. Specifically, the user holds auditions and has each performer perform a script-based routine. The user then uses a terminal to video record the performance and sends the data to the server. The output is the selected, best performer.

[0086] Step 5:

[0087] The terminal conducts practice sessions with a selected performer. The inputs used are a generated script and feedback data from the server. Specifically, the terminal videotapes the performer during practice and sends the data to the server. The server analyzes the data and provides detailed feedback on timing and emotional expression. The output is an improved performance based on the feedback.

[0088] (Application Example 1)

[0089] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] In the process of practicing and preparing for acting, performers are required to efficiently improve their skills and achieve better performances. However, with conventional methods, it is not easy to provide instruction and feedback tailored to the individual needs of each user, resulting in the challenge of not being able to provide an effective practice environment.

[0091] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0092] In this invention, the server includes means for collecting information on past performance events, means for analyzing the information to extract language structure and evaluation trends, and means for generating new scripts based on the analyzed information. This enables feedback and optimization of practice based on the individual user's performance.

[0093] "Information" refers to historical data and metadata related to performance events, which form the basis for analysis.

[0094] A "generative AI model" is an artificial intelligence system that generates new manuscripts and performance guidelines based on user input and conditions.

[0095] A "script" refers to a text script for acting or performance created by a generative AI model, which forms the basis of the performance.

[0096] "Performer" refers to an individual or group that performs or acts using a generated script.

[0097] "User" refers to any entity that uses this system to improve their acting or performance, and may include performers.

[0098] "Feedback" refers to specific areas for improvement and evaluations of a performer's performance, providing users with information to optimize their performance during practice and actual performances.

[0099] "Means of collection" refers to the processes and technologies used to obtain data from past performance events.

[0100] "Analysis methods" refer to techniques that analyze collected information using natural language processing and machine learning technologies to extract useful patterns and trends.

[0101] "Generation means" refers to the techniques and algorithms used to create a new manuscript based on the analysis results.

[0102] The system for implementing this invention consists of a server, a terminal, and a user. The server first collects relevant information from past performance events via the internet and stores this information in a dedicated database. The database contains raw scripts, video recordings, and metadata related to evaluations. The server analyzes the collected information using natural language processing and generative AI models such as Google's TensorFlow and OpenAI's GPT series to extract characteristics of language structure and evaluation trends.

[0103] The server's AI model generates new scripts based on these analysis results, creating several script variations tailored to different themes and contexts. Users can receive this information via their device and select the script best suited to their performance.

[0104] Based on the selected script, users practice acting using a device. The device uses its built-in camera and microphone to record the performance, and the data is sent to a server. The server uses evaluation tools to analyze the recorded audio and video, providing detailed feedback on timing, emotional expression, and pacing. This allows users to identify specific areas for improvement to optimize their acting.

[0105] For example, if a user aspires to be a stand-up comedian, they can use this system to generate their own stand-up comedy script and practice when and what kind of jokes and retorts they should deliver. The generating AI will advise on which style is most effective. A possible example of a specific prompt would be, "I want to come up with a new stand-up comedy routine, so could you create a funny script based on everyday life?"

[0106] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0107] Step 1:

[0108] The server collects information on past performance events from the internet and stores this data in a database. Its input is information about past events, and its output is the accumulation of this information in the database. This data includes raw scripts, video recordings, and metadata related to evaluations. The server retrieves these datasets using HTTP requests and stores them in a storage system.

[0109] Step 2:

[0110] The server analyzes the collected data using natural language processing and machine learning techniques. The input is raw information stored in a database, and the output is the extraction of language structure and evaluation trends. The server uses libraries such as TensorFlow to perform the process of analyzing and extracting important patterns from the information.

[0111] Step 3:

[0112] The server's generation AI model generates new manuscripts based on the analyzed data. The input is data on language structure and evaluation tendencies, and the output is the new manuscript and its variations. The server uses OpenAI's GPT series to generate multiple manuscripts that meet the user's needs and prepares them for the user.

[0113] Step 4:

[0114] The user selects a script suitable for their performance from those provided via the terminal. The input is a variation of the script sent from the server, and the output is the specific script selected by the user. The user considers multiple options through the terminal's UI and decides on the script that best suits their individual practice needs.

[0115] Step 5:

[0116] The user practices their performance using a device based on a selected script. The input is the selected script, and the output is recorded performance data from the practice. As the user performs, the device's camera and microphone record the performance and send the data to the server.

[0117] Step 6:

[0118] The server analyzes the received practice data and generates detailed feedback. The input is recorded practice data, and the output is feedback information. The server uses speech recognition algorithms and video analysis technology for analysis, generating feedback on speech timing and emotional expression, and providing it to the user.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention enhances performance in entertainment contests through a generative AI system that combines an emotion engine. The system is implemented through collaboration between a server, terminals, and users (administrators and performers), and provides consistent support from preparation to execution of performances through data collection, analysis, script generation, and emotion recognition.

[0121] First, the server collects data related to past talent contests from internet resources and stores it in a database. This data includes scripts, performance videos, judges' evaluations, and data on audience reactions and emotional expressions. The server uses this data and employs natural language processing techniques to analyze the language structure and evaluation trends in detail.

[0122] Based on the analyzed information, the server's AI model generates a new script. During this process, the emotion engine creates multiple script variations, taking into account the user's emotional history and estimated audience emotional responses. The generated results are presented to the user, and the script predicted to have the greatest emotional impact is selected.

[0123] Based on the selected script, the user holds auditions to choose the most suitable performer. The selected performer practices their performance based on the given script via a device. The device records this practice on video and sends it to a server. The server generates feedback on speaking timing and voice adjustments from the recorded practice.

[0124] Furthermore, the emotion engine analyzes emotional data from the voices and facial expressions of users and audience members, and provides suggestions for adjusting performance. For example, if the engine determines that a user is nervous during practice, it provides advice to help them relax by adjusting their vocalization and timing. With feedback from the server and advice from the emotion engine, users optimize their performance.

[0125] This entire process incorporates the analysis results of the emotion engine, shaping a real-time, adaptable performance based on a script created by the generative AI. Finally, the user participates in a live talent competition, utilizing all the data and feedback. The process is documented to produce a documentary, extensively demonstrating the advantages of the generative AI and emotion engine.

[0126] In this embodiment of the present invention, by integrating a generative AI with an emotion engine, it is possible to achieve more emotionally and technically sophisticated performances.

[0127] The following describes the processing flow.

[0128] Step 1:

[0129] The server collects data related to past talent contests from the internet. This data includes scripts, performance videos, judges' evaluations, and audience reaction data. All of this is stored in a database.

[0130] Step 2:

[0131] The server preprocesses the collected data. Specifically, it formats text data into a parseable format and extracts facial expressions and voices from video data and converts them into text.

[0132] Step 3:

[0133] The server analyzes pre-processed data using natural language processing algorithms. This analysis identifies factors contributing to the success of the performance and points emphasized in evaluation, and extracts characteristic features of the language structure.

[0134] Step 4:

[0135] The server utilizes a generation AI model to generate new scripts based on the analysis results. Furthermore, the emotion engine assists in generating multiple script variations while considering the user's emotional data.

[0136] Step 5:

[0137] The user reviews the generated script and selects the most appropriate variation. Based on the selected script, the user conducts auditions for performers and selects the best performers.

[0138] Step 6:

[0139] The terminal records the practice sessions of selected performers and sends the data to the server. The terminal records video and audio in high resolution, playing a role in comprehensively documenting the practice process.

[0140] Step 7:

[0141] The server analyzes the practice data sent from the terminal and generates feedback. The feedback provides specific suggestions for improvement regarding the timing of speech, intonation, and pauses.

[0142] Step 8:

[0143] The emotion engine analyzes the user's or performer's emotions during practice, recognizing emotional states such as tension and anxiety. Based on this, the emotion engine provides advice on adjusting performance.

[0144] Step 9:

[0145] Users incorporate feedback from the server and advice from the emotion engine to further improve performance. Rehearsals are repeated to prepare for the live broadcast in an optimized state.

[0146] Step 10:

[0147] The user completes their final preparations and participates in the actual talent show competition. The entire process is recorded and edited into a documentary to promote the achievements of the generative AI and emotion engine.

[0148] (Example 2)

[0149] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0150] In traditional performing arts competitions, achieving emotionally impactful performances is a challenging task. There is a need for a system that effectively utilizes past data to generate scripts that take into account predicted audience emotional responses, as well as to select and train performers.

[0151] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0152] In this invention, the server includes means for collecting data from past performing arts competitions, means for analyzing the data to extract linguistic structure and evaluation trends, means for generating a new script based on the analyzed data, and means for analyzing emotions to provide suggestions for adjusting the performance. This enables the generation of optimal scripts for emotionally impactful performances, as well as the selection and training of performers.

[0153] "Data" refers to facts, figures, and observational results collected for the purpose of storing, analyzing, and utilizing information.

[0154] "Analysis" refers to the process of thoroughly examining collected data to reveal its structure and trends.

[0155] "Generation means" refers to a mechanism that executes a technical process to create new deliverables or information based on analyzed data.

[0156] A "script" refers to a document that describes the lines, instructions, and elements used to construct an act or performance.

[0157] "Performers" refers to individuals or groups who actually act or perform based on a script or screenplay.

[0158] "Training" refers to a systematic process of practice and learning aimed at improving specific skills or abilities.

[0159] "Emotion" refers to the psychological and emotional reactions and states of individuals and audiences, encompassing a wide range of sensations and expressions.

[0160] A "proposal for adjustment" refers to specific suggestions for improving or modifying existing plans or activities in order to achieve better results.

[0161] To implement this invention, a server, terminal, and user cooperate to perform a series of processes. The server collects data on past performing arts competitions via the internet, including scripts, performance videos, judges' evaluations, and audience reactions and emotional expressions. This data is stored in a database and used in the next analysis step. The server uses natural language processing techniques to analyze the language structure and evaluation trends from the collected data. In this process, commonly used natural language processing libraries (e.g., NLTK, spaCy) are often utilized.

[0162] The server's generation AI model generates a new script based on the analysis results. The generation AI model uses a large-scale language model (e.g., GPT-3®) and integrates sentiment analysis algorithms to create scripts that take into account the emotional responses of the audience.

[0163] Users conduct auditions based on the generated script and select the most suitable performers. The selected performers train using the device. Performances during training are recorded by the device's camera and microphone and uploaded to a server. The server analyzes the recordings and provides feedback on timing and voice adjustments. During this process, voice analysis software is used to measure voice tone and pitch.

[0164] Furthermore, the emotion engine analyzes the voices and facial expressions of the user and audience, and provides suggestions for adjusting the performance. For example, if nervousness is detected during practice, the server will give the user specific advice such as "Speak more slowly" or "Speaking more brightly will give a more positive impression."

[0165] As a concrete example, the server analyzes patterns that generate laughter using data from past comedy shows, and a generative AI model generates a new humorous script. Based on this script, the user can hold auditions, and selected performers can undergo training before performing in the actual show. The following prompt can be used: "Based on data from past comedy shows, generate three new jokes that are likely to make the audience laugh. In the process, take the audience's emotional reactions into consideration."

[0166] In this way, the invention makes it possible to realize theatrical arts that have enhanced emotional impact and technical precision.

[0167] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0168] Step 1:

[0169] The server collects data on past performing arts competitions via the internet. It takes publicly available scripts, performance videos, judges' evaluations, and audience reaction data as input, and stores this data in a database as output. Specifically, it uses web scraping techniques to gather information from various online sources, converts it to JSON format, and saves it to storage.

[0170] Step 2:

[0171] The server analyzes the collected data. It receives script and performance video information from the database as input, processes the data to extract language structure and evaluation trends, and outputs the analysis results. Specifically, it performs text analysis using natural language processing libraries (e.g., NLTK and spaCy), and converts it into structured data through morphological analysis and sentiment classification.

[0172] Step 3:

[0173] The server's generation AI model generates a new script based on the analysis results. It takes a prompt as input and generates a new script as output. Specifically, the generation AI model (e.g., GPT-3) creates a template script based on the prompt, preparing multiple variations.

[0174] Step 4:

[0175] The user conducts auditions based on the generated script to select the most suitable performer. The input consists of multiple generated script variations, and the output determines the performer best suited to the selected script. Specifically, the user and performer collaborate to conduct auditions to select the most suitable candidate from among the candidates.

[0176] Step 5:

[0177] Selected performers use a device to practice the script. The device receives recorded practice videos as input and uploads the recorded data to a server as output. Specific operations include recording practice sessions using the device's camera and microphone.

[0178] Step 6:

[0179] The server analyzes recorded practice data and generates feedback. It analyzes uploaded practice videos as input and provides feedback on speech timing and voice adjustments as output. Specifically, it uses voice analysis software to suggest areas for improvement in performance through voice tone, pitch, and facial expression recognition.

[0180] Step 7:

[0181] Using an emotion engine, the system analyzes emotional responses from the voices and facial expressions of users and audience members, and provides suggestions for performance adjustments. Audio and video data recorded during concerts and rehearsals are provided as input, and emotion-based adjustment suggestions are generated as output. Specific actions include providing concrete advice to the user, such as "it would be good to pause slowly" or "use a different tone of voice."

[0182] (Application Example 2)

[0183] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0184] In traditional in-store customer service events, the individual performance quality of staff members significantly impacts the customer experience, making it difficult to maintain high-quality service. Furthermore, staff members may be unable to deliver appropriate performance due to nervousness or stress, potentially compromising the consistency of the customer service experience.

[0185] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0186] In this invention, the server includes means for collecting past event data, means for analyzing the data to extract language structure and evaluation trends, and means for generating a new script based on the analyzed data. This makes it possible to generate effective and emotionally sensitive customer service scenarios in physical stores.

[0187] "Event data" refers to a collection of information about past events, including participant reactions, scripts, performance details, and evaluations.

[0188] "Linguistic structure" refers to the constituent elements of a text or script, such as the arrangement of words and phrases and grammar, and is extracted by analyzing the formal characteristics of language.

[0189] "Evaluation trends" refer to patterns and tendencies in evaluations derived from past data, and represent tendencies in value judgments based on specific criteria.

[0190] "Generative means" refers to methods and processes for creating new information or structures using data based on a specific purpose.

[0191] A "physical store" refers to a real place of sale or provision where consumers can physically visit and receive goods or services.

[0192] A "customer service scenario" refers to a series of actions and response methods used when dealing with customers in a store, and is a plan that defines how store employees should interact with customers.

[0193] "Emotional analysis means" refers to techniques or methods for determining and analyzing a person's emotional state based on their facial expressions and voice.

[0194] "A state of tension" refers to a state of anxiety or stress that a person experiences psychologically or physiologically in a particular situation, and it is often a factor that affects performance.

[0195] To realize this invention, the server first collects past event data and analyzes it. The collected data includes scripts, evaluation comments, and audience reactions. The server uses natural language processing technology to extract language structure and evaluation trends from this data. Then, based on the analysis results, it generates new customer service scenarios using a generative AI model.

[0196] The generated customer service scenarios are referenced by store employees via smartphones or head-mounted displays. Users practice based on these scenarios, and the device records their practice and transmits the footage to a server. The server analyzes the employee's tension level from the practice video using emotion analysis tools and provides suggestions for adjusting their performance. This allows users to achieve more optimal performance.

[0197] A concrete example is a new product promotion event where, based on data obtained through emotion analysis, advice is given on how to alleviate tension, and a script generated by AI is used to ensure that store staff interact with customers in a fun and relaxed manner.

[0198] An example of a prompt message is: "Please generate a script for the next product sales event, taking customer feedback into consideration. This should include methods to help staff members relax if they appear nervous, so that they can provide more effective customer service."

[0199] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0200] Step 1:

[0201] The server collects historical event data from resources on the internet. The collected data includes scripts, audience reactions, and evaluation comments. This data is stored in a database for analysis. The input for this step is internet resources, and the output is the event data stored in the database.

[0202] Step 2:

[0203] The server analyzes the collected event data using natural language processing techniques. It uses language analysis algorithms to extract the linguistic structure and evaluation trends of the script. The input for this step is event data read from a database, and the output is the linguistic structure and evaluation trends as a result of the analysis.

[0204] Step 3:

[0205] The server generates new customer service scenarios using a generative AI model based on the analysis results. It generates multiple script variations, each aiming to maximize the audience's response. The input for this step is language structure and evaluation tendencies, and the output is the generated customer service scenario.

[0206] Step 4:

[0207] The user (store clerk) receives a customer service scenario generated through the terminal and practices according to it. The terminal records the practice session on video. The input for this step is the generated customer service scenario, and the output is the video data of the practice session.

[0208] Step 5:

[0209] The recorded practice video is transferred to a server. The server uses emotion analysis tools to analyze the employee's facial expressions and voice from the video data and determine their level of tension and emotional state. The input for this step is the video data, and the output is emotional data that determines the level of tension.

[0210] Step 6:

[0211] The server provides feedback to the employee based on the emotion analysis results. It sends specific advice to alleviate tension and performance adjustment suggestions to the terminal. The input for this step is emotion data and a generated customer service scenario, and the output is emotion-based feedback.

[0212] Step 7:

[0213] Users optimize their performance based on feedback from the server. Through this process, users can relax and provide more effective customer service. The input in this step is feedback, and the output is optimized performance.

[0214] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0230] This invention relates to a system that utilizes generative AI to gain an advantage in performing arts contests. In this system, the process from data collection to final performance is carried out seamlessly through the collaboration of a server, terminals, and users (administrators and performers).

[0231] First, the server collects data from past talent contests from the internet and stores it in a database. This data includes unformatted scripts, video recordings, and evaluation metadata. Next, the server analyzes the collected data using natural language processing techniques and machine learning algorithms. Specifically, it identifies the characteristics of language structure, factors that induce laughter, and elements that influence performance evaluations. This analysis identifies useful patterns and trends.

[0232] Based on the analysis results, the server's generation AI model generates a new script. At this stage, multiple script variations are created based on different themes and contexts. This generated script is then provided to performers selected by the user. The selection process is conducted in an audition format, where performers are evaluated to determine which performer is best suited to deliver a performance using parts of the script provided by the generation AI.

[0233] Next, the terminal assists the selected performer in a practice session. During practice, the performer adjusts their performance based on the generated script and repeatedly tries and fails. The terminal records this process on video and sends the data to the server. Based on the transmitted data, the server's evaluation system generates detailed feedback and provides areas for improvement in the practice. This feedback covers a wide range of aspects, including timing of utterances, expression of emotion, and pacing.

[0234] The final performance is optimized through the aforementioned feedback loop. Users leverage the insights gained throughout the entire process to prepare for the actual production environment. A documentary recording this entire process is also created and used to widely publicize the capabilities of the generative AI.

[0235] Thus, this system can maximize the linguistic capabilities of generative AI and demonstrate an advantage in performing arts competitions. Specifically, it provides a series of processes for achieving a mature performance through practice and optimization based on AI-generated scripts.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server collects data related to past talent contests from the internet. This data includes script text, performance videos, and judges' evaluations. The server stores this data in a database.

[0239] Step 2:

[0240] The server preprocesses the collected data. Specifically, it tokenizes text data and transcribes audio from video data. It also removes unnecessary data and converts it into a format suitable for analysis.

[0241] Step 3:

[0242] The server analyzes pre-processed data using natural language processing techniques. This analysis aims to identify common patterns in successful scripts from the contest and elements that received particularly high ratings. Machine learning algorithms are used to extract useful trends.

[0243] Step 4:

[0244] The server generates a new script based on the analysis results. Using generation AI, it creates multiple script variations suitable for various themes and styles. The generated results are presented to the user, who selects the most suitable one.

[0245] Step 5:

[0246] The user holds auditions to select suitable performers to act out the chosen scripts. The selected performers then perform trial acting based on the server-generated scripts to check their fit.

[0247] Step 6:

[0248] The device records the performer's practice sessions and sends them to the server. During practice, the performance is fine-tuned based on the generated script. All practice sessions are recorded in detail using the device's recording function.

[0249] Step 7:

[0250] The server analyzes the practice data sent from the terminal and generates feedback. Specifically, it analyzes performance elements such as speech timing, emotional expression, and pacing in detail and provides suggestions for improvement.

[0251] Step 8:

[0252] Based on feedback from the server, users optimize the performer's performance and the script. By repeatedly practicing with the improvements incorporated, they prepare for the final performance in the best possible state.

[0253] Step 9:

[0254] After the user completes their final preparations, they will participate in the actual talent show competition, showcasing the results of their training. This process will be recorded and later used to create a documentary widely promoting the capabilities of the generative AI.

[0255] (Example 1)

[0256] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0257] In entertainment contests, high-quality performances require performers to prepare appropriate scripts and to practice them repeatedly to perform them effectively. However, traditional methods have challenges in terms of efficiency and accuracy in generating appropriate scripts and optimizing the practice process. In particular, the lack of objective, data-driven feedback makes improving performance time-consuming and labor-intensive.

[0258] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0259] In this invention, the server includes means for acquiring information on past performing arts competitions, means for analyzing the information to extract language structure and evaluation characteristics, and means for generating new documents based on the analyzed information. This enables performers to efficiently obtain high-quality scripts and prepare for optimal performances while receiving objective, data-driven feedback.

[0260] "Information" refers to a collection of various data related to past entertainment competitions, specifically including scripts, video recordings, and metadata related to evaluations.

[0261] "Analysis" is the act of processing collected information and extracting linguistic structures and evaluation characteristics to identify useful patterns and trends.

[0262] A "document" refers to a new script or content generated based on the analyzed data, which serves as a guideline for performers to carry out their performance.

[0263] "Performers" refer to individuals or groups who perform acts such as acting or speeches based on the generated documents.

[0264] "Improvement suggestions" include specific advice and feedback on performance, such as timing and pauses in speech, based on records and analysis of the practice process.

[0265] "Means" refers to the components or technical elements used to realize the specific functions or processing processes described within the patent claims.

[0266] This invention is designed as a system that improves the quality of performances in entertainment contests by utilizing a generative AI model. Specific embodiments are described below.

[0267] The server first retrieves information related to past entertainment competitions that is publicly available on the internet. This information includes various metadata related to scripts, video recordings, and evaluations. Web scraping techniques are used for retrieval, such as utilizing the Python BeautifulSoup library. This data is then formatted by the server and stored in a database.

[0268] Next, the server analyzes the collected information using natural language processing techniques and machine learning algorithms. This process involves using the Python spaCy library to analyze language structure and extract language patterns that evoke laughter. Additionally, TensorFlow is used to train a machine learning model and identify factors that influence performance evaluation.

[0269] Once the analysis is complete, the server generates a new document using a generative AI model. This AI model might use OpenAI's GPT, for example, and is given prompts such as, "Generate a script for a comedy performance. The theme is 'Everyday Humor'." This generated document is then used by the user to select the most suitable performer.

[0270] The terminal supports the practice session with the selected performer. The terminal records the performer's practice on video and sends the data to the server. The server analyzes the transmitted video data and generates feedback that provides the performer with multifaceted improvement suggestions. This feedback includes aspects such as speech timing and emotional expression.

[0271] Ultimately, users optimize performance based on feedback from the executor. Leveraging the insights gained throughout the entire process, they are prepared to deliver successful final performance. A documentary recording this entire process serves as crucial material demonstrating the capabilities of the generative AI model.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server retrieves information about past performing arts competitions from the internet. It uses publicly available data related to these competitions as input. This data includes scripts, video recordings, and evaluation metadata. Specifically, the server uses web scraping tools, for example, the BeautifulSoup library in Python, to parse HTML pages, extract data, and store it in a database. The output is a formalized database record.

[0275] Step 2:

[0276] The server analyzes the acquired information using natural language processing techniques. The input consists of text data and metadata stored in a database. Specifically, the server uses the Python spaCy library to analyze language patterns and identify elements that induce laughter. It also trains a machine learning model using TensorFlow to extract factors that influence performance evaluation. The output is data on language structure and evaluation characteristics obtained through the analysis.

[0277] Step 3:

[0278] The server activates a generative AI model for generating documents based on the analyzed data. As inputs, the patterns and evaluation characteristics obtained in the analysis step are used. The specific operation is to input a prompt sentence into the generative AI model. For example, an instruction like "Please generate a script for a comedy performance. The theme is 'humor in daily life.'" is given, and multiple document variations are generated. The output is the generated script candidates.

[0279] Step 4:

[0280] The user selects an executor based on the generated document. As inputs, the multiple script variations generated are included. As a specific operation, the user holds an audition and has each executor perform a performance based on the script. The performance is video-recorded using the terminal, and the data is sent to the server. The output is the selected optimal executor.

[0281] Step 5:

[0282] The terminal conducts a practice session with the selected executor. As inputs, the generated script and feedback data from the server are used. Specifically, the terminal records the executor during practice in video and sends the data to the server. The server analyzes the data and provides detailed feedback regarding timing and emotional expression. The output is an improved performance based on the feedback.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server," and the smart glasses 214 are referred to as the "terminal."

[0285] In the process of acting practice and preparation, it is required that actors efficiently improve their skills and achieve better performances. However, with conventional methods, it is not easy to provide guidance and feedback tailored to the individual needs of users, and as a result, there has been a problem in that it is difficult to provide an effective practice environment.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0287] In this invention, the server includes means for collecting information on past acting events, means for analyzing the information to extract language structures and evaluation trends, and generating means for generating a new manuscript based on the analyzed information. This enables feedback and optimization of practice based on the acting performance of individual users.

[0288] "Information" refers to past data and metadata related to acting events and serves as the basis for analysis.

[0289] "Generative AI model" is an artificial intelligence system that generates new manuscripts and performance guidelines based on user inputs and conditions.

[0290] "Manuscript" refers to a text script for acting or performance created by the generative AI model and serves as the basis for actual performance.

[0291] "Actor" refers to an individual or group that performs acting or performance using the generated manuscript.

[0292] "User" refers to the entity that uses this system to improve acting or performance and may include actors.

[0293] "Feedback" refers to specific improvement points and evaluations of an actor's performance and is information for users to optimize practice and performance in the actual performance.

[0294] "Means of collection" refers to the processes and technologies used to obtain data from past performance events.

[0295] "Analysis methods" refer to techniques that analyze collected information using natural language processing and machine learning technologies to extract useful patterns and trends.

[0296] "Generation means" refers to the techniques and algorithms used to create a new manuscript based on the analysis results.

[0297] The system for implementing this invention consists of a server, a terminal, and a user. The server first collects relevant information from past performance events via the internet and stores this information in a dedicated database. The database contains raw scripts, video recordings, and metadata related to evaluations. The server analyzes the collected information using natural language processing and generative AI models such as Google's TensorFlow and OpenAI's GPT series to extract characteristics of language structure and evaluation trends.

[0298] The server's AI model generates new scripts based on these analysis results, creating several script variations tailored to different themes and contexts. Users can receive this information via their device and select the script best suited to their performance.

[0299] Based on the selected script, users practice acting using a device. The device uses its built-in camera and microphone to record the performance, and the data is sent to a server. The server uses evaluation tools to analyze the recorded audio and video, providing detailed feedback on timing, emotional expression, and pacing. This allows users to identify specific areas for improvement to optimize their acting.

[0300] For example, if a user aspires to be a stand-up comedian, they can use this system to generate their own stand-up comedy script and practice when and what kind of jokes and retorts they should deliver. The generating AI will advise on which style is most effective. A possible example of a specific prompt would be, "I want to come up with a new stand-up comedy routine, so could you create a funny script based on everyday life?"

[0301] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0302] Step 1:

[0303] The server collects information on past performance events from the internet and stores this data in a database. Its input is information about past events, and its output is the accumulation of this information in the database. This data includes raw scripts, video recordings, and metadata related to evaluations. The server retrieves these datasets using HTTP requests and stores them in a storage system.

[0304] Step 2:

[0305] The server analyzes the collected data using natural language processing and machine learning techniques. The input is raw information stored in a database, and the output is the extraction of language structure and evaluation trends. The server uses libraries such as TensorFlow to perform the process of analyzing and extracting important patterns from the information.

[0306] Step 3:

[0307] The server's generation AI model generates new manuscripts based on the analyzed data. The input is data on language structure and evaluation tendencies, and the output is the new manuscript and its variations. The server uses OpenAI's GPT series to generate multiple manuscripts that meet the user's needs and prepares them for the user.

[0308] Step 4:

[0309] The user selects, via the terminal, what is suitable for the performance from the manuscripts provided. The input is the variations of the manuscripts sent from the server, and the output is the specific manuscript selected by the user. The user examines multiple options through the UI of the terminal and determines the manuscript that best suits their individual practice needs.

[0310] Step 5:

[0311] The user practices the performance using the terminal based on the selected manuscript. The input is the selected manuscript, and the output is the recorded performance data of the practice. When the user performs, the camera and microphone of the terminal record the performance and transmit the data to the server.

[0312] Step 6:

[0313] The server analyzes the received practice data and generates detailed feedback. The input is the recorded practice data, and the output is the feedback information. The server uses speech recognition algorithms and video analysis techniques for analysis, generates feedback regarding the timing of speech and emotional expressions, and provides it to the user.

[0314] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0315] The present invention enhances the performance in a performing arts contest by a generation AI system combined with an emotion engine. The system is implemented through the cooperation of a server, a terminal, and a user (administrator / actor), and consistently supports from the preparation to the implementation of the performing arts through data collection, analysis, script generation, and emotion recognition.

[0316] First, the server collects data related to past talent contests from internet resources and stores it in a database. This data includes scripts, performance videos, judges' evaluations, and data on audience reactions and emotional expressions. The server uses this data and employs natural language processing techniques to analyze the language structure and evaluation trends in detail.

[0317] Based on the analyzed information, the server's AI model generates a new script. During this process, the emotion engine creates multiple script variations, taking into account the user's emotional history and estimated audience emotional responses. The generated results are presented to the user, and the script predicted to have the greatest emotional impact is selected.

[0318] Based on the selected script, the user holds auditions to choose the most suitable performer. The selected performer practices their performance based on the given script via a device. The device records this practice on video and sends it to a server. The server generates feedback on speaking timing and voice adjustments from the recorded practice.

[0319] Furthermore, the emotion engine analyzes emotional data from the voices and facial expressions of users and audience members, and provides suggestions for adjusting performance. For example, if the engine determines that a user is nervous during practice, it provides advice to help them relax by adjusting their vocalization and timing. With feedback from the server and advice from the emotion engine, users optimize their performance.

[0320] This entire process incorporates the analysis results of the emotion engine, shaping a real-time, adaptable performance based on a script created by the generative AI. Finally, the user participates in a live talent competition, utilizing all the data and feedback. The process is documented to produce a documentary, extensively demonstrating the advantages of the generative AI and emotion engine.

[0321] In this embodiment of the present invention, by integrating a generative AI with an emotion engine, it is possible to achieve more emotionally and technically sophisticated performances.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The server collects data related to past talent contests from the internet. This data includes scripts, performance videos, judges' evaluations, and audience reaction data. All of this is stored in a database.

[0325] Step 2:

[0326] The server preprocesses the collected data. Specifically, it formats text data into a parseable format and extracts facial expressions and voices from video data and converts them into text.

[0327] Step 3:

[0328] The server analyzes pre-processed data using natural language processing algorithms. This analysis identifies factors contributing to the success of the performance and points emphasized in evaluation, and extracts characteristic features of the language structure.

[0329] Step 4:

[0330] The server utilizes a generation AI model to generate new scripts based on the analysis results. Furthermore, the emotion engine assists in generating multiple script variations while considering the user's emotional data.

[0331] Step 5:

[0332] The user reviews the generated script and selects the most appropriate variation. Based on the selected script, the user conducts auditions for performers and selects the best performers.

[0333] Step 6:

[0334] The terminal records the practice sessions of selected performers and sends the data to the server. The terminal records video and audio in high resolution, playing a role in comprehensively documenting the practice process.

[0335] Step 7:

[0336] The server analyzes the practice data sent from the terminal and generates feedback. The feedback provides specific suggestions for improvement regarding the timing of speech, intonation, and pauses.

[0337] Step 8:

[0338] The emotion engine analyzes the user's or performer's emotions during practice, recognizing emotional states such as tension and anxiety. Based on this, the emotion engine provides advice on adjusting performance.

[0339] Step 9:

[0340] Users incorporate feedback from the server and advice from the emotion engine to further improve performance. Rehearsals are repeated to prepare for the live broadcast in an optimized state.

[0341] Step 10:

[0342] The user completes their final preparations and participates in the actual talent show competition. The entire process is recorded and edited into a documentary to promote the achievements of the generative AI and emotion engine.

[0343] (Example 2)

[0344] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0345] In traditional performing arts competitions, achieving emotionally impactful performances is a challenging task. There is a need for a system that effectively utilizes past data to generate scripts that take into account predicted audience emotional responses, as well as to select and train performers.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes means for collecting data from past performing arts competitions, means for analyzing the data to extract linguistic structure and evaluation trends, means for generating a new script based on the analyzed data, and means for analyzing emotions to provide suggestions for adjusting the performance. This enables the generation of optimal scripts for emotionally impactful performances, as well as the selection and training of performers.

[0348] "Data" refers to facts, figures, and observational results collected for the purpose of storing, analyzing, and utilizing information.

[0349] "Analysis" refers to the process of thoroughly examining collected data to reveal its structure and trends.

[0350] "Generation means" refers to a mechanism that executes a technical process to create new deliverables or information based on analyzed data.

[0351] A "script" refers to a document that describes the lines, instructions, and elements used to construct an act or performance.

[0352] "Performers" refers to individuals or groups who actually act or perform based on a script or screenplay.

[0353] "Training" refers to a systematic process of practice and learning aimed at improving specific skills or abilities.

[0354] "Emotion" refers to the psychological and emotional reactions and states of individuals and audiences, encompassing a wide range of sensations and expressions.

[0355] A "proposal for adjustment" refers to specific suggestions for improving or modifying existing plans or activities in order to achieve better results.

[0356] To implement this invention, a server, terminal, and user cooperate to perform a series of processes. The server collects data on past performing arts competitions via the internet, including scripts, performance videos, judges' evaluations, and audience reactions and emotional expressions. This data is stored in a database and used in the next analysis step. The server uses natural language processing techniques to analyze the language structure and evaluation trends from the collected data. In this process, commonly used natural language processing libraries (e.g., NLTK, spaCy) are often utilized.

[0357] The server's generation AI model generates a new script based on the analysis results. The generation AI model uses a large-scale language model (e.g., GPT-3) and integrates sentiment analysis algorithms to create scripts that take into account the emotional responses of the audience.

[0358] Users conduct auditions based on the generated script and select the most suitable performers. The selected performers train using the device. Performances during training are recorded by the device's camera and microphone and uploaded to a server. The server analyzes the recordings and provides feedback on timing and voice adjustments. During this process, voice analysis software is used to measure voice tone and pitch.

[0359] Furthermore, the emotion engine analyzes the voices and facial expressions of the user and audience, and provides suggestions for adjusting the performance. For example, if nervousness is detected during practice, the server will give the user specific advice such as "Speak more slowly" or "Speaking more brightly will give a more positive impression."

[0360] As a concrete example, the server analyzes patterns that generate laughter using data from past comedy shows, and a generative AI model generates a new humorous script. Based on this script, the user can hold auditions, and selected performers can undergo training before performing in the actual show. The following prompt can be used: "Based on data from past comedy shows, generate three new jokes that are likely to make the audience laugh. In the process, take the audience's emotional reactions into consideration."

[0361] In this way, the invention makes it possible to realize theatrical arts that have enhanced emotional impact and technical precision.

[0362] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0363] Step 1:

[0364] The server collects data on past performing arts competitions via the internet. It takes publicly available scripts, performance videos, judges' evaluations, and audience reaction data as input, and stores this data in a database as output. Specifically, it uses web scraping techniques to gather information from various online sources, converts it to JSON format, and saves it to storage.

[0365] Step 2:

[0366] The server analyzes the collected data. It receives script and performance video information from the database as input, processes the data to extract language structure and evaluation trends, and outputs the analysis results. Specifically, it performs text analysis using natural language processing libraries (e.g., NLTK and spaCy), and converts it into structured data through morphological analysis and sentiment classification.

[0367] Step 3:

[0368] The server's generation AI model generates a new script based on the analysis results. It takes a prompt as input and generates a new script as output. Specifically, the generation AI model (e.g., GPT-3) creates a template script based on the prompt, preparing multiple variations.

[0369] Step 4:

[0370] The user conducts auditions based on the generated script to select the most suitable performer. The input consists of multiple generated script variations, and the output determines the performer best suited to the selected script. Specifically, the user and performer collaborate to conduct auditions to select the most suitable candidate from among the candidates.

[0371] Step 5:

[0372] Selected performers use a device to practice the script. The device receives recorded practice videos as input and uploads the recorded data to a server as output. Specific operations include recording practice sessions using the device's camera and microphone.

[0373] Step 6:

[0374] The server analyzes recorded practice data and generates feedback. It analyzes uploaded practice videos as input and provides feedback on speech timing and voice adjustments as output. Specifically, it uses voice analysis software to suggest areas for improvement in performance through voice tone, pitch, and facial expression recognition.

[0375] Step 7:

[0376] Using an emotion engine, the system analyzes emotional responses from the voices and facial expressions of users and audience members, and provides suggestions for performance adjustments. Audio and video data recorded during concerts and rehearsals are provided as input, and emotion-based adjustment suggestions are generated as output. Specific actions include providing concrete advice to the user, such as "it would be good to pause slowly" or "use a different tone of voice."

[0377] (Application Example 2)

[0378] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0379] In traditional in-store customer service events, the individual performance quality of staff members significantly impacts the customer experience, making it difficult to maintain high-quality service. Furthermore, staff members may be unable to deliver appropriate performance due to nervousness or stress, potentially compromising the consistency of the customer service experience.

[0380] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0381] In this invention, the server includes means for collecting past event data, means for analyzing the data to extract language structure and evaluation trends, and means for generating a new script based on the analyzed data. This makes it possible to generate effective and emotionally sensitive customer service scenarios in physical stores.

[0382] "Event data" refers to a collection of information about past events, including participant reactions, scripts, performance details, and evaluations.

[0383] "Linguistic structure" refers to the constituent elements of a text or script, such as the arrangement of words and phrases and grammar, and is extracted by analyzing the formal characteristics of language.

[0384] "Evaluation trends" refer to patterns and tendencies in evaluations derived from past data, and represent tendencies in value judgments based on specific criteria.

[0385] "Generative means" refers to methods and processes for creating new information or structures using data based on a specific purpose.

[0386] A "physical store" refers to a real place of sale or provision where consumers can physically visit and receive goods or services.

[0387] A "customer service scenario" refers to a series of actions and response methods used when dealing with customers in a store, and is a plan that defines how store employees should interact with customers.

[0388] "Emotional analysis means" refers to techniques or methods for determining and analyzing a person's emotional state based on their facial expressions and voice.

[0389] "A state of tension" refers to a state of anxiety or stress that a person experiences psychologically or physiologically in a particular situation, and it is often a factor that affects performance.

[0390] To realize this invention, the server first collects past event data and analyzes it. The collected data includes scripts, evaluation comments, and audience reactions. The server uses natural language processing technology to extract language structure and evaluation trends from this data. Then, based on the analysis results, it generates new customer service scenarios using a generative AI model.

[0391] The generated customer service scenarios are referenced by store employees via smartphones or head-mounted displays. Users practice based on these scenarios, and the device records their practice and transmits the footage to a server. The server analyzes the employee's tension level from the practice video using emotion analysis tools and provides suggestions for adjusting their performance. This allows users to achieve more optimal performance.

[0392] A concrete example is a new product promotion event where, based on data obtained through emotion analysis, advice is given on how to alleviate tension, and a script generated by AI is used to ensure that store staff interact with customers in a fun and relaxed manner.

[0393] An example of a prompt message is: "Please generate a script for the next product sales event, taking customer feedback into consideration. This should include methods to help staff members relax if they appear nervous, so that they can provide more effective customer service."

[0394] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0395] Step 1:

[0396] The server collects historical event data from resources on the internet. The collected data includes scripts, audience reactions, and evaluation comments. This data is stored in a database for analysis. The input for this step is internet resources, and the output is the event data stored in the database.

[0397] Step 2:

[0398] The server analyzes the collected event data using natural language processing techniques. It uses language analysis algorithms to extract the linguistic structure and evaluation trends of the script. The input for this step is event data read from a database, and the output is the linguistic structure and evaluation trends as a result of the analysis.

[0399] Step 3:

[0400] The server generates new customer service scenarios using a generative AI model based on the analysis results. It generates multiple script variations, each aiming to maximize the audience's response. The input for this step is language structure and evaluation tendencies, and the output is the generated customer service scenario.

[0401] Step 4:

[0402] The user (store clerk) receives a customer service scenario generated through the terminal and practices according to it. The terminal records the practice session on video. The input for this step is the generated customer service scenario, and the output is the video data of the practice session.

[0403] Step 5:

[0404] The recorded practice video is transferred to a server. The server uses emotion analysis tools to analyze the employee's facial expressions and voice from the video data and determine their level of tension and emotional state. The input for this step is the video data, and the output is emotional data that determines the level of tension.

[0405] Step 6:

[0406] The server provides feedback to the employee based on the emotion analysis results. It sends specific advice to alleviate tension and performance adjustment suggestions to the terminal. The input for this step is emotion data and a generated customer service scenario, and the output is emotion-based feedback.

[0407] Step 7:

[0408] Users optimize their performance based on feedback from the server. Through this process, users can relax and provide more effective customer service. The input in this step is feedback, and the output is optimized performance.

[0409] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0410] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0411] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0412] [Third Embodiment]

[0413] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0414] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0415] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0416] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0417] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0418] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0419] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0420] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0421] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0422] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0423] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0424] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0425] This invention relates to a system that utilizes generative AI to gain an advantage in performing arts contests. In this system, the process from data collection to final performance is carried out seamlessly through the collaboration of a server, terminals, and users (administrators and performers).

[0426] First, the server collects data from past talent contests from the internet and stores it in a database. This data includes unformatted scripts, video recordings, and evaluation metadata. Next, the server analyzes the collected data using natural language processing techniques and machine learning algorithms. Specifically, it identifies the characteristics of language structure, factors that induce laughter, and elements that influence performance evaluations. This analysis identifies useful patterns and trends.

[0427] Based on the analysis results, the server's generation AI model generates a new script. At this stage, multiple script variations are created based on different themes and contexts. This generated script is then provided to performers selected by the user. The selection process is conducted in an audition format, where performers are evaluated to determine which performer is best suited to deliver a performance using parts of the script provided by the generation AI.

[0428] Next, the terminal assists the selected performer in a practice session. During practice, the performer adjusts their performance based on the generated script and repeatedly tries and fails. The terminal records this process on video and sends the data to the server. Based on the transmitted data, the server's evaluation system generates detailed feedback and provides areas for improvement in the practice. This feedback covers a wide range of aspects, including timing of utterances, expression of emotion, and pacing.

[0429] The final performance is optimized through the aforementioned feedback loop. Users leverage the insights gained throughout the entire process to prepare for the actual production environment. A documentary recording this entire process is also created and used to widely publicize the capabilities of the generative AI.

[0430] Thus, this system can maximize the linguistic capabilities of generative AI and demonstrate an advantage in performing arts competitions. Specifically, it provides a series of processes for achieving a mature performance through practice and optimization based on AI-generated scripts.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] The server collects data related to past talent contests from the internet. This data includes script text, performance videos, and judges' evaluations. The server stores this data in a database.

[0434] Step 2:

[0435] The server preprocesses the collected data. Specifically, it tokenizes text data and transcribes audio from video data. It also removes unnecessary data and converts it into a format suitable for analysis.

[0436] Step 3:

[0437] The server analyzes pre-processed data using natural language processing techniques. This analysis aims to identify common patterns in successful scripts from the contest and elements that received particularly high ratings. Machine learning algorithms are used to extract useful trends.

[0438] Step 4:

[0439] The server generates a new script based on the analysis results. Using generation AI, it creates multiple script variations suitable for various themes and styles. The generated results are presented to the user, who selects the most suitable one.

[0440] Step 5:

[0441] The user holds auditions to select suitable performers to act out the chosen scripts. The selected performers then perform trial acting based on the server-generated scripts to check their fit.

[0442] Step 6:

[0443] The device records the performer's practice sessions and sends them to the server. During practice, the performance is fine-tuned based on the generated script. All practice sessions are recorded in detail using the device's recording function.

[0444] Step 7:

[0445] The server analyzes the practice data sent from the terminal and generates feedback. Specifically, it analyzes performance elements such as speech timing, emotional expression, and pacing in detail and provides suggestions for improvement.

[0446] Step 8:

[0447] Based on feedback from the server, users optimize the performer's performance and the script. By repeatedly practicing with the improvements incorporated, they prepare for the final performance in the best possible state.

[0448] Step 9:

[0449] After the user completes their final preparations, they will participate in the actual talent show competition, showcasing the results of their training. This process will be recorded and later used to create a documentary widely promoting the capabilities of the generative AI.

[0450] (Example 1)

[0451] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0452] In entertainment contests, high-quality performances require performers to prepare appropriate scripts and to practice them repeatedly to perform them effectively. However, traditional methods have challenges in terms of efficiency and accuracy in generating appropriate scripts and optimizing the practice process. In particular, the lack of objective, data-driven feedback makes improving performance time-consuming and labor-intensive.

[0453] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0454] In this invention, the server includes means for acquiring information on past performing arts competitions, means for analyzing the information to extract language structure and evaluation characteristics, and means for generating new documents based on the analyzed information. This enables performers to efficiently obtain high-quality scripts and prepare for optimal performances while receiving objective, data-driven feedback.

[0455] "Information" refers to a collection of various data related to past entertainment competitions, specifically including scripts, video recordings, and metadata related to evaluations.

[0456] "Analysis" is the act of processing collected information and extracting linguistic structures and evaluation characteristics to identify useful patterns and trends.

[0457] A "document" refers to a new script or content generated based on the analyzed data, which serves as a guideline for performers to carry out their performance.

[0458] "Performers" refer to individuals or groups who perform acts such as acting or speeches based on the generated documents.

[0459] "Improvement suggestions" include specific advice and feedback on performance, such as timing and pauses in speech, based on records and analysis of the practice process.

[0460] "Means" refers to the components or technical elements used to realize the specific functions or processing processes described within the patent claims.

[0461] This invention is designed as a system that improves the quality of performances in entertainment contests by utilizing a generative AI model. Specific embodiments are described below.

[0462] The server first retrieves information related to past entertainment competitions that is publicly available on the internet. This information includes various metadata related to scripts, video recordings, and evaluations. Web scraping techniques are used for retrieval, such as utilizing the Python BeautifulSoup library. This data is then formatted by the server and stored in a database.

[0463] Next, the server analyzes the collected information using natural language processing techniques and machine learning algorithms. This process involves using the Python spaCy library to analyze language structure and extract language patterns that evoke laughter. Additionally, TensorFlow is used to train a machine learning model and identify factors that influence performance evaluation.

[0464] Once the analysis is complete, the server generates a new document using a generative AI model. This AI model might use OpenAI's GPT, for example, and is given prompts such as, "Generate a script for a comedy performance. The theme is 'Everyday Humor'." This generated document is then used by the user to select the most suitable performer.

[0465] The terminal supports the practice session with the selected performer. The terminal records the performer's practice on video and sends the data to the server. The server analyzes the transmitted video data and generates feedback that provides the performer with multifaceted improvement suggestions. This feedback includes aspects such as speech timing and emotional expression.

[0466] Ultimately, users optimize performance based on feedback from the executor. Leveraging the insights gained throughout the entire process, they are prepared to deliver successful final performance. A documentary recording this entire process serves as crucial material demonstrating the capabilities of the generative AI model.

[0467] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0468] Step 1:

[0469] The server retrieves information about past performing arts competitions from the internet. It uses publicly available data related to these competitions as input. This data includes scripts, video recordings, and evaluation metadata. Specifically, the server uses web scraping tools, for example, the BeautifulSoup library in Python, to parse HTML pages, extract data, and store it in a database. The output is a formalized database record.

[0470] Step 2:

[0471] The server analyzes the acquired information using natural language processing techniques. The input consists of text data and metadata stored in a database. Specifically, the server uses the Python spaCy library to analyze language patterns and identify elements that induce laughter. It also trains a machine learning model using TensorFlow to extract factors that influence performance evaluation. The output is data on language structure and evaluation characteristics obtained through the analysis.

[0472] Step 3:

[0473] The server launches a generative AI model to generate documents based on the analyzed data. The inputs used are patterns and evaluation characteristics obtained in the analysis step. Specifically, the generative AI model is prompted with a sentence, for example, "Generate a script for a comedy performance. The theme is 'Everyday Humor'," which generates multiple document variations. The output is the generated script candidates.

[0474] Step 4:

[0475] The user selects performers based on the generated documents. The input includes multiple generated script variations. Specifically, the user holds auditions and has each performer perform a script-based routine. The user then uses a terminal to video record the performance and sends the data to the server. The output is the selected, best performer.

[0476] Step 5:

[0477] The terminal conducts practice sessions with a selected performer. The inputs used are a generated script and feedback data from the server. Specifically, the terminal videotapes the performer during practice and sends the data to the server. The server analyzes the data and provides detailed feedback on timing and emotional expression. The output is an improved performance based on the feedback.

[0478] (Application Example 1)

[0479] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0480] In the process of practicing and preparing for acting, performers are required to efficiently improve their skills and achieve better performances. However, with conventional methods, it is not easy to provide instruction and feedback tailored to the individual needs of each user, resulting in the challenge of not being able to provide an effective practice environment.

[0481] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0482] In this invention, the server includes means for collecting information on past performance events, means for analyzing the information to extract language structure and evaluation trends, and means for generating new scripts based on the analyzed information. This enables feedback and optimization of practice based on the individual user's performance.

[0483] "Information" refers to historical data and metadata related to performance events, which form the basis for analysis.

[0484] A "generative AI model" is an artificial intelligence system that generates new manuscripts and performance guidelines based on user input and conditions.

[0485] A "script" refers to a text script for acting or performance created by a generative AI model, which forms the basis of the performance.

[0486] "Performer" refers to an individual or group that performs or acts using a generated script.

[0487] "User" refers to any entity that uses this system to improve their acting or performance, and may include performers.

[0488] "Feedback" refers to specific areas for improvement and evaluations of a performer's performance, providing users with information to optimize their performance during practice and actual performances.

[0489] "Means of collection" refers to the processes and technologies used to obtain data from past performance events.

[0490] "Analysis methods" refer to techniques that analyze collected information using natural language processing and machine learning technologies to extract useful patterns and trends.

[0491] "Generation means" refers to the techniques and algorithms used to create a new manuscript based on the analysis results.

[0492] The system for implementing this invention consists of a server, a terminal, and a user. The server first collects relevant information from past performance events via the internet and stores this information in a dedicated database. The database contains raw scripts, video recordings, and metadata related to evaluations. The server analyzes the collected information using natural language processing and generative AI models such as Google's TensorFlow and OpenAI's GPT series to extract characteristics of language structure and evaluation trends.

[0493] The server's AI model generates new scripts based on these analysis results, creating several script variations tailored to different themes and contexts. Users can receive this information via their device and select the script best suited to their performance.

[0494] Based on the selected script, users practice acting using a device. The device uses its built-in camera and microphone to record the performance, and the data is sent to a server. The server uses evaluation tools to analyze the recorded audio and video, providing detailed feedback on timing, emotional expression, and pacing. This allows users to identify specific areas for improvement to optimize their acting.

[0495] For example, if a user aspires to be a stand-up comedian, they can use this system to generate their own stand-up comedy script and practice when and what kind of jokes and retorts they should deliver. The generating AI will advise on which style is most effective. A possible example of a specific prompt would be, "I want to come up with a new stand-up comedy routine, so could you create a funny script based on everyday life?"

[0496] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0497] Step 1:

[0498] The server collects information on past performance events from the internet and stores this data in a database. Its input is information about past events, and its output is the accumulation of this information in the database. This data includes raw scripts, video recordings, and metadata related to evaluations. The server retrieves these datasets using HTTP requests and stores them in a storage system.

[0499] Step 2:

[0500] The server analyzes the collected data using natural language processing and machine learning techniques. The input is raw information stored in a database, and the output is the extraction of language structure and evaluation trends. The server uses libraries such as TensorFlow to perform the process of analyzing and extracting important patterns from the information.

[0501] Step 3:

[0502] The server's generation AI model generates new manuscripts based on the analyzed data. The input is data on language structure and evaluation tendencies, and the output is the new manuscript and its variations. The server uses OpenAI's GPT series to generate multiple manuscripts that meet the user's needs and prepares them for the user.

[0503] Step 4:

[0504] The user selects a script suitable for their performance from those provided via the terminal. The input is a variation of the script sent from the server, and the output is the specific script selected by the user. The user considers multiple options through the terminal's UI and decides on the script that best suits their individual practice needs.

[0505] Step 5:

[0506] The user practices their performance using a device based on a selected script. The input is the selected script, and the output is recorded performance data from the practice. As the user performs, the device's camera and microphone record the performance and send the data to the server.

[0507] Step 6:

[0508] The server analyzes the received practice data and generates detailed feedback. The input is recorded practice data, and the output is feedback information. The server uses speech recognition algorithms and video analysis technology for analysis, generating feedback on speech timing and emotional expression, and providing it to the user.

[0509] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0510] This invention enhances performance in entertainment contests through a generative AI system that combines an emotion engine. The system is implemented through collaboration between a server, terminals, and users (administrators and performers), and provides consistent support from preparation to execution of performances through data collection, analysis, script generation, and emotion recognition.

[0511] First, the server collects data related to past talent contests from internet resources and stores it in a database. This data includes scripts, performance videos, judges' evaluations, and data on audience reactions and emotional expressions. The server uses this data and employs natural language processing techniques to analyze the language structure and evaluation trends in detail.

[0512] Based on the analyzed information, the server's AI model generates a new script. During this process, the emotion engine creates multiple script variations, taking into account the user's emotional history and estimated audience emotional responses. The generated results are presented to the user, and the script predicted to have the greatest emotional impact is selected.

[0513] Based on the selected script, the user holds auditions to choose the most suitable performer. The selected performer practices their performance based on the given script via a device. The device records this practice on video and sends it to a server. The server generates feedback on speaking timing and voice adjustments from the recorded practice.

[0514] Furthermore, the emotion engine analyzes emotional data from the voices and facial expressions of users and audience members, and provides suggestions for adjusting performance. For example, if the engine determines that a user is nervous during practice, it provides advice to help them relax by adjusting their vocalization and timing. With feedback from the server and advice from the emotion engine, users optimize their performance.

[0515] This entire process incorporates the analysis results of the emotion engine, shaping a real-time, adaptable performance based on a script created by the generative AI. Finally, the user participates in a live talent competition, utilizing all the data and feedback. The process is documented to produce a documentary, extensively demonstrating the advantages of the generative AI and emotion engine.

[0516] In this embodiment of the present invention, by integrating a generative AI with an emotion engine, it is possible to achieve more emotionally and technically sophisticated performances.

[0517] The following describes the processing flow.

[0518] Step 1:

[0519] The server collects data related to past talent contests from the internet. This data includes scripts, performance videos, judges' evaluations, and audience reaction data. All of this is stored in a database.

[0520] Step 2:

[0521] The server preprocesses the collected data. Specifically, it formats text data into a parseable format and extracts facial expressions and voices from video data and converts them into text.

[0522] Step 3:

[0523] The server analyzes pre-processed data using natural language processing algorithms. This analysis identifies factors contributing to the success of the performance and points emphasized in evaluation, and extracts characteristic features of the language structure.

[0524] Step 4:

[0525] The server utilizes a generation AI model to generate new scripts based on the analysis results. Furthermore, the emotion engine assists in generating multiple script variations while considering the user's emotional data.

[0526] Step 5:

[0527] The user reviews the generated script and selects the most appropriate variation. Based on the selected script, the user conducts auditions for performers and selects the best performers.

[0528] Step 6:

[0529] The terminal records the practice sessions of selected performers and sends the data to the server. The terminal records video and audio in high resolution, playing a role in comprehensively documenting the practice process.

[0530] Step 7:

[0531] The server analyzes the practice data sent from the terminal and generates feedback. The feedback provides specific suggestions for improvement regarding the timing of speech, intonation, and pauses.

[0532] Step 8:

[0533] The emotion engine analyzes the user's or performer's emotions during practice, recognizing emotional states such as tension and anxiety. Based on this, the emotion engine provides advice on adjusting performance.

[0534] Step 9:

[0535] Users incorporate feedback from the server and advice from the emotion engine to further improve performance. Rehearsals are repeated to prepare for the live broadcast in an optimized state.

[0536] Step 10:

[0537] The user completes their final preparations and participates in the actual talent show competition. The entire process is recorded and edited into a documentary to promote the achievements of the generative AI and emotion engine.

[0538] (Example 2)

[0539] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0540] In traditional performing arts competitions, achieving emotionally impactful performances is a challenging task. There is a need for a system that effectively utilizes past data to generate scripts that take into account predicted audience emotional responses, as well as to select and train performers.

[0541] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0542] In this invention, the server includes means for collecting data from past performing arts competitions, means for analyzing the data to extract linguistic structure and evaluation trends, means for generating a new script based on the analyzed data, and means for analyzing emotions to provide suggestions for adjusting the performance. This enables the generation of optimal scripts for emotionally impactful performances, as well as the selection and training of performers.

[0543] "Data" refers to facts, figures, and observational results collected for the purpose of storing, analyzing, and utilizing information.

[0544] "Analysis" refers to the process of thoroughly examining collected data to reveal its structure and trends.

[0545] "Generation means" refers to a mechanism that executes a technical process to create new deliverables or information based on analyzed data.

[0546] A "script" refers to a document that describes the lines, instructions, and elements used to construct an act or performance.

[0547] "Performers" refers to individuals or groups who actually act or perform based on a script or screenplay.

[0548] "Training" refers to a systematic process of practice and learning aimed at improving specific skills or abilities.

[0549] "Emotion" refers to the psychological and emotional reactions and states of individuals and audiences, encompassing a wide range of sensations and expressions.

[0550] A "proposal for adjustment" refers to specific suggestions for improving or modifying existing plans or activities in order to achieve better results.

[0551] To implement this invention, a server, terminal, and user cooperate to perform a series of processes. The server collects data on past performing arts competitions via the internet, including scripts, performance videos, judges' evaluations, and audience reactions and emotional expressions. This data is stored in a database and used in the next analysis step. The server uses natural language processing techniques to analyze the language structure and evaluation trends from the collected data. In this process, commonly used natural language processing libraries (e.g., NLTK, spaCy) are often utilized.

[0552] The server's generation AI model generates a new script based on the analysis results. The generation AI model uses a large-scale language model (e.g., GPT-3) and integrates sentiment analysis algorithms to create scripts that take into account the emotional responses of the audience.

[0553] Users conduct auditions based on the generated script and select the most suitable performers. The selected performers train using the device. Performances during training are recorded by the device's camera and microphone and uploaded to a server. The server analyzes the recordings and provides feedback on timing and voice adjustments. During this process, voice analysis software is used to measure voice tone and pitch.

[0554] Furthermore, the emotion engine analyzes the voices and facial expressions of the user and audience, and provides suggestions for adjusting the performance. For example, if nervousness is detected during practice, the server will give the user specific advice such as "Speak more slowly" or "Speaking more brightly will give a more positive impression."

[0555] As a concrete example, the server analyzes patterns that generate laughter using data from past comedy shows, and a generative AI model generates a new humorous script. Based on this script, the user can hold auditions, and selected performers can undergo training before performing in the actual show. The following prompt can be used: "Based on data from past comedy shows, generate three new jokes that are likely to make the audience laugh. In the process, take the audience's emotional reactions into consideration."

[0556] In this way, the invention makes it possible to realize theatrical arts that have enhanced emotional impact and technical precision.

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1:

[0559] The server collects data on past performing arts competitions via the internet. It takes publicly available scripts, performance videos, judges' evaluations, and audience reaction data as input, and stores this data in a database as output. Specifically, it uses web scraping techniques to gather information from various online sources, converts it to JSON format, and saves it to storage.

[0560] Step 2:

[0561] The server analyzes the collected data. It receives script and performance video information from the database as input, processes the data to extract language structure and evaluation trends, and outputs the analysis results. Specifically, it performs text analysis using natural language processing libraries (e.g., NLTK and spaCy), and converts it into structured data through morphological analysis and sentiment classification.

[0562] Step 3:

[0563] The server's generation AI model generates a new script based on the analysis results. It takes a prompt as input and generates a new script as output. Specifically, the generation AI model (e.g., GPT-3) creates a template script based on the prompt, preparing multiple variations.

[0564] Step 4:

[0565] The user conducts auditions based on the generated script to select the most suitable performer. The input consists of multiple generated script variations, and the output determines the performer best suited to the selected script. Specifically, the user and performer collaborate to conduct auditions to select the most suitable candidate from among the candidates.

[0566] Step 5:

[0567] Selected performers use a device to practice the script. The device receives recorded practice videos as input and uploads the recorded data to a server as output. Specific operations include recording practice sessions using the device's camera and microphone.

[0568] Step 6:

[0569] The server analyzes recorded practice data and generates feedback. It analyzes uploaded practice videos as input and provides feedback on speech timing and voice adjustments as output. Specifically, it uses voice analysis software to suggest areas for improvement in performance through voice tone, pitch, and facial expression recognition.

[0570] Step 7:

[0571] Using an emotion engine, the system analyzes emotional responses from the voices and facial expressions of users and audience members, and provides suggestions for performance adjustments. Audio and video data recorded during concerts and rehearsals are provided as input, and emotion-based adjustment suggestions are generated as output. Specific actions include providing concrete advice to the user, such as "it would be good to pause slowly" or "use a different tone of voice."

[0572] (Application Example 2)

[0573] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0574] In traditional in-store customer service events, the individual performance quality of staff members significantly impacts the customer experience, making it difficult to maintain high-quality service. Furthermore, staff members may be unable to deliver appropriate performance due to nervousness or stress, potentially compromising the consistency of the customer service experience.

[0575] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0576] In this invention, the server includes means for collecting past event data, means for analyzing the data to extract language structure and evaluation trends, and means for generating a new script based on the analyzed data. This makes it possible to generate effective and emotionally sensitive customer service scenarios in physical stores.

[0577] "Event data" refers to a collection of information about past events, including participant reactions, scripts, performance details, and evaluations.

[0578] "Linguistic structure" refers to the constituent elements of a text or script, such as the arrangement of words and phrases and grammar, and is extracted by analyzing the formal characteristics of language.

[0579] "Evaluation trends" refer to patterns and tendencies in evaluations derived from past data, and represent tendencies in value judgments based on specific criteria.

[0580] "Generative means" refers to methods and processes for creating new information or structures using data based on a specific purpose.

[0581] A "physical store" refers to a real place of sale or provision where consumers can physically visit and receive goods or services.

[0582] A "customer service scenario" refers to a series of actions and response methods used when dealing with customers in a store, and is a plan that defines how store employees should interact with customers.

[0583] "Emotional analysis means" refers to techniques or methods for determining and analyzing a person's emotional state based on their facial expressions and voice.

[0584] "A state of tension" refers to a state of anxiety or stress that a person experiences psychologically or physiologically in a particular situation, and it is often a factor that affects performance.

[0585] To realize this invention, the server first collects past event data and analyzes it. The collected data includes scripts, evaluation comments, and audience reactions. The server uses natural language processing technology to extract language structure and evaluation trends from this data. Then, based on the analysis results, it generates new customer service scenarios using a generative AI model.

[0586] The generated customer service scenarios are referenced by store employees via smartphones or head-mounted displays. Users practice based on these scenarios, and the device records their practice and transmits the footage to a server. The server analyzes the employee's tension level from the practice video using emotion analysis tools and provides suggestions for adjusting their performance. This allows users to achieve more optimal performance.

[0587] A concrete example is a new product promotion event where, based on data obtained through emotion analysis, advice is given on how to alleviate tension, and a script generated by AI is used to ensure that store staff interact with customers in a fun and relaxed manner.

[0588] An example of a prompt message is: "Please generate a script for the next product sales event, taking customer feedback into consideration. This should include methods to help staff members relax if they appear nervous, so that they can provide more effective customer service."

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server collects historical event data from resources on the internet. The collected data includes scripts, audience reactions, and evaluation comments. This data is stored in a database for analysis. The input for this step is internet resources, and the output is the event data stored in the database.

[0592] Step 2:

[0593] The server analyzes the collected event data using natural language processing techniques. It uses language analysis algorithms to extract the linguistic structure and evaluation trends of the script. The input for this step is event data read from a database, and the output is the linguistic structure and evaluation trends as a result of the analysis.

[0594] Step 3:

[0595] The server generates new customer service scenarios using a generative AI model based on the analysis results. It generates multiple script variations, each aiming to maximize the audience's response. The input for this step is language structure and evaluation tendencies, and the output is the generated customer service scenario.

[0596] Step 4:

[0597] The user (store clerk) receives a customer service scenario generated through the terminal and practices according to it. The terminal records the practice session on video. The input for this step is the generated customer service scenario, and the output is the video data of the practice session.

[0598] Step 5:

[0599] The recorded practice video is transferred to a server. The server uses emotion analysis tools to analyze the employee's facial expressions and voice from the video data and determine their level of tension and emotional state. The input for this step is the video data, and the output is emotional data that determines the level of tension.

[0600] Step 6:

[0601] The server provides feedback to the employee based on the emotion analysis results. It sends specific advice to alleviate tension and performance adjustment suggestions to the terminal. The input for this step is emotion data and a generated customer service scenario, and the output is emotion-based feedback.

[0602] Step 7:

[0603] Users optimize their performance based on feedback from the server. Through this process, users can relax and provide more effective customer service. The input in this step is feedback, and the output is optimized performance.

[0604] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0605] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0606] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0607] [Fourth Embodiment]

[0608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0609] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0610] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0611] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0612] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0613] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0614] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0615] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0616] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0617] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0618] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0619] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0620] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0621] This invention relates to a system that utilizes generative AI to gain an advantage in performing arts contests. In this system, the process from data collection to final performance is carried out seamlessly through the collaboration of a server, terminals, and users (administrators and performers).

[0622] First, the server collects data from past talent contests from the internet and stores it in a database. This data includes unformatted scripts, video recordings, and evaluation metadata. Next, the server analyzes the collected data using natural language processing techniques and machine learning algorithms. Specifically, it identifies the characteristics of language structure, factors that induce laughter, and elements that influence performance evaluations. This analysis identifies useful patterns and trends.

[0623] Based on the analysis results, the server's generation AI model generates a new script. At this stage, multiple script variations are created based on different themes and contexts. This generated script is then provided to performers selected by the user. The selection process is conducted in an audition format, where performers are evaluated to determine which performer is best suited to deliver a performance using parts of the script provided by the generation AI.

[0624] Next, the terminal assists the selected performer in a practice session. During practice, the performer adjusts their performance based on the generated script and repeatedly tries and fails. The terminal records this process on video and sends the data to the server. Based on the transmitted data, the server's evaluation system generates detailed feedback and provides areas for improvement in the practice. This feedback covers a wide range of aspects, including timing of utterances, expression of emotion, and pacing.

[0625] The final performance is optimized through the aforementioned feedback loop. Users leverage the insights gained throughout the entire process to prepare for the actual production environment. A documentary recording this entire process is also created and used to widely publicize the capabilities of the generative AI.

[0626] Thus, this system can maximize the linguistic capabilities of generative AI and demonstrate an advantage in performing arts competitions. Specifically, it provides a series of processes for achieving a mature performance through practice and optimization based on AI-generated scripts.

[0627] The following describes the processing flow.

[0628] Step 1:

[0629] The server collects data related to past talent contests from the internet. This data includes script text, performance videos, and judges' evaluations. The server stores this data in a database.

[0630] Step 2:

[0631] The server preprocesses the collected data. Specifically, it tokenizes text data and transcribes audio from video data. It also removes unnecessary data and converts it into a format suitable for analysis.

[0632] Step 3:

[0633] The server analyzes pre-processed data using natural language processing techniques. This analysis aims to identify common patterns in successful scripts from the contest and elements that received particularly high ratings. Machine learning algorithms are used to extract useful trends.

[0634] Step 4:

[0635] The server generates a new script based on the analysis results. Using generation AI, it creates multiple script variations suitable for various themes and styles. The generated results are presented to the user, who selects the most suitable one.

[0636] Step 5:

[0637] The user holds auditions to select suitable performers to act out the chosen scripts. The selected performers then perform trial acting based on the server-generated scripts to check their fit.

[0638] Step 6:

[0639] The device records the performer's practice sessions and sends them to the server. During practice, the performance is fine-tuned based on the generated script. All practice sessions are recorded in detail using the device's recording function.

[0640] Step 7:

[0641] The server analyzes the practice data sent from the terminal and generates feedback. Specifically, it analyzes performance elements such as speech timing, emotional expression, and pacing in detail and provides suggestions for improvement.

[0642] Step 8:

[0643] Based on feedback from the server, users optimize the performer's performance and the script. By repeatedly practicing with the improvements incorporated, they prepare for the final performance in the best possible state.

[0644] Step 9:

[0645] After the user completes their final preparations, they will participate in the actual talent show competition, showcasing the results of their training. This process will be recorded and later used to create a documentary widely promoting the capabilities of the generative AI.

[0646] (Example 1)

[0647] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0648] In entertainment contests, high-quality performances require performers to prepare appropriate scripts and to practice them repeatedly to perform them effectively. However, traditional methods have challenges in terms of efficiency and accuracy in generating appropriate scripts and optimizing the practice process. In particular, the lack of objective, data-driven feedback makes improving performance time-consuming and labor-intensive.

[0649] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0650] In this invention, the server includes means for acquiring information on past performing arts competitions, means for analyzing the information to extract language structure and evaluation characteristics, and means for generating new documents based on the analyzed information. This enables performers to efficiently obtain high-quality scripts and prepare for optimal performances while receiving objective, data-driven feedback.

[0651] "Information" refers to a collection of various data related to past entertainment competitions, specifically including scripts, video recordings, and metadata related to evaluations.

[0652] "Analysis" is the act of processing collected information and extracting linguistic structures and evaluation characteristics to identify useful patterns and trends.

[0653] A "document" refers to a new script or content generated based on the analyzed data, which serves as a guideline for performers to carry out their performance.

[0654] "Performers" refer to individuals or groups who perform acts such as acting or speeches based on the generated documents.

[0655] "Improvement suggestions" include specific advice and feedback on performance, such as timing and pauses in speech, based on records and analysis of the practice process.

[0656] "Means" refers to the components or technical elements used to realize the specific functions or processing processes described within the patent claims.

[0657] This invention is designed as a system that improves the quality of performances in entertainment contests by utilizing a generative AI model. Specific embodiments are described below.

[0658] The server first retrieves information related to past entertainment competitions that is publicly available on the internet. This information includes various metadata related to scripts, video recordings, and evaluations. Web scraping techniques are used for retrieval, such as utilizing the Python BeautifulSoup library. This data is then formatted by the server and stored in a database.

[0659] Next, the server analyzes the collected information using natural language processing techniques and machine learning algorithms. This process involves using the Python spaCy library to analyze language structure and extract language patterns that evoke laughter. Additionally, TensorFlow is used to train a machine learning model and identify factors that influence performance evaluation.

[0660] Once the analysis is complete, the server generates a new document using a generative AI model. This AI model might use OpenAI's GPT, for example, and is given prompts such as, "Generate a script for a comedy performance. The theme is 'Everyday Humor'." This generated document is then used by the user to select the most suitable performer.

[0661] The terminal supports the practice session with the selected performer. The terminal records the performer's practice on video and sends the data to the server. The server analyzes the transmitted video data and generates feedback that provides the performer with multifaceted improvement suggestions. This feedback includes aspects such as speech timing and emotional expression.

[0662] Ultimately, users optimize performance based on feedback from the executor. Leveraging the insights gained throughout the entire process, they are prepared to deliver successful final performance. A documentary recording this entire process serves as crucial material demonstrating the capabilities of the generative AI model.

[0663] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0664] Step 1:

[0665] The server retrieves information about past performing arts competitions from the internet. It uses publicly available data related to these competitions as input. This data includes scripts, video recordings, and evaluation metadata. Specifically, the server uses web scraping tools, for example, the BeautifulSoup library in Python, to parse HTML pages, extract data, and store it in a database. The output is a formalized database record.

[0666] Step 2:

[0667] The server analyzes the acquired information using natural language processing techniques. The input consists of text data and metadata stored in a database. Specifically, the server uses the Python spaCy library to analyze language patterns and identify elements that induce laughter. It also trains a machine learning model using TensorFlow to extract factors that influence performance evaluation. The output is data on language structure and evaluation characteristics obtained through the analysis.

[0668] Step 3:

[0669] The server launches a generative AI model to generate documents based on the analyzed data. The inputs used are patterns and evaluation characteristics obtained in the analysis step. Specifically, the generative AI model is prompted with a sentence, for example, "Generate a script for a comedy performance. The theme is 'Everyday Humor'," which generates multiple document variations. The output is the generated script candidates.

[0670] Step 4:

[0671] The user selects performers based on the generated documents. The input includes multiple generated script variations. Specifically, the user holds auditions and has each performer perform a script-based routine. The user then uses a terminal to video record the performance and sends the data to the server. The output is the selected, best performer.

[0672] Step 5:

[0673] The terminal conducts practice sessions with a selected performer. The inputs used are a generated script and feedback data from the server. Specifically, the terminal videotapes the performer during practice and sends the data to the server. The server analyzes the data and provides detailed feedback on timing and emotional expression. The output is an improved performance based on the feedback.

[0674] (Application Example 1)

[0675] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0676] In the process of practicing and preparing for acting, performers are required to efficiently improve their skills and achieve better performances. However, with conventional methods, it is not easy to provide instruction and feedback tailored to the individual needs of each user, resulting in the challenge of not being able to provide an effective practice environment.

[0677] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0678] In this invention, the server includes means for collecting information on past performance events, means for analyzing the information to extract language structure and evaluation trends, and means for generating new scripts based on the analyzed information. This enables feedback and optimization of practice based on the individual user's performance.

[0679] "Information" refers to historical data and metadata related to performance events, which form the basis for analysis.

[0680] A "generative AI model" is an artificial intelligence system that generates new manuscripts and performance guidelines based on user input and conditions.

[0681] A "script" refers to a text script for acting or performance created by a generative AI model, which forms the basis of the performance.

[0682] "Performer" refers to an individual or group that performs or acts using a generated script.

[0683] "User" refers to any entity that uses this system to improve their acting or performance, and may include performers.

[0684] "Feedback" refers to specific areas for improvement and evaluations of a performer's performance, providing users with information to optimize their performance during practice and actual performances.

[0685] "Means of collection" refers to the processes and technologies used to obtain data from past performance events.

[0686] "Analysis methods" refer to techniques that analyze collected information using natural language processing and machine learning technologies to extract useful patterns and trends.

[0687] "Generation means" refers to the techniques and algorithms used to create a new manuscript based on the analysis results.

[0688] The system for implementing this invention consists of a server, a terminal, and a user. The server first collects relevant information from past performance events via the internet and stores this information in a dedicated database. The database contains raw scripts, video recordings, and metadata related to evaluations. The server analyzes the collected information using natural language processing and generative AI models such as Google's TensorFlow and OpenAI's GPT series to extract characteristics of language structure and evaluation trends.

[0689] The server's AI model generates new scripts based on these analysis results, creating several script variations tailored to different themes and contexts. Users can receive this information via their device and select the script best suited to their performance.

[0690] Based on the selected script, users practice acting using a device. The device uses its built-in camera and microphone to record the performance, and the data is sent to a server. The server uses evaluation tools to analyze the recorded audio and video, providing detailed feedback on timing, emotional expression, and pacing. This allows users to identify specific areas for improvement to optimize their acting.

[0691] For example, if a user aspires to be a stand-up comedian, they can use this system to generate their own stand-up comedy script and practice when and what kind of jokes and retorts they should deliver. The generating AI will advise on which style is most effective. A possible example of a specific prompt would be, "I want to come up with a new stand-up comedy routine, so could you create a funny script based on everyday life?"

[0692] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0693] Step 1:

[0694] The server collects information on past performance events from the internet and stores this data in a database. Its input is information about past events, and its output is the accumulation of this information in the database. This data includes raw scripts, video recordings, and metadata related to evaluations. The server retrieves these datasets using HTTP requests and stores them in a storage system.

[0695] Step 2:

[0696] The server analyzes the collected data using natural language processing and machine learning techniques. The input is raw information stored in a database, and the output is the extraction of language structure and evaluation trends. The server uses libraries such as TensorFlow to perform the process of analyzing and extracting important patterns from the information.

[0697] Step 3:

[0698] The server's generation AI model generates new manuscripts based on the analyzed data. The input is data on language structure and evaluation tendencies, and the output is the new manuscript and its variations. The server uses OpenAI's GPT series to generate multiple manuscripts that meet the user's needs and prepares them for the user.

[0699] Step 4:

[0700] The user selects a script suitable for their performance from those provided via the terminal. The input is a variation of the script sent from the server, and the output is the specific script selected by the user. The user considers multiple options through the terminal's UI and decides on the script that best suits their individual practice needs.

[0701] Step 5:

[0702] The user practices their performance using a device based on a selected script. The input is the selected script, and the output is recorded performance data from the practice. As the user performs, the device's camera and microphone record the performance and send the data to the server.

[0703] Step 6:

[0704] The server analyzes the received practice data and generates detailed feedback. The input is recorded practice data, and the output is feedback information. The server uses speech recognition algorithms and video analysis technology for analysis, generating feedback on speech timing and emotional expression, and providing it to the user.

[0705] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0706] This invention enhances performance in entertainment contests through a generative AI system that combines an emotion engine. The system is implemented through collaboration between a server, terminals, and users (administrators and performers), and provides consistent support from preparation to execution of performances through data collection, analysis, script generation, and emotion recognition.

[0707] First, the server collects data related to past talent contests from internet resources and stores it in a database. This data includes scripts, performance videos, judges' evaluations, and data on audience reactions and emotional expressions. The server uses this data and employs natural language processing techniques to analyze the language structure and evaluation trends in detail.

[0708] Based on the analyzed information, the server's AI model generates a new script. During this process, the emotion engine creates multiple script variations, taking into account the user's emotional history and estimated audience emotional responses. The generated results are presented to the user, and the script predicted to have the greatest emotional impact is selected.

[0709] Based on the selected script, the user holds auditions to choose the most suitable performer. The selected performer practices their performance based on the given script via a device. The device records this practice on video and sends it to a server. The server generates feedback on speaking timing and voice adjustments from the recorded practice.

[0710] Furthermore, the emotion engine analyzes emotional data from the voices and facial expressions of users and audience members, and provides suggestions for adjusting performance. For example, if the engine determines that a user is nervous during practice, it provides advice to help them relax by adjusting their vocalization and timing. With feedback from the server and advice from the emotion engine, users optimize their performance.

[0711] This entire process incorporates the analysis results of the emotion engine, shaping a real-time, adaptable performance based on a script created by the generative AI. Finally, the user participates in a live talent competition, utilizing all the data and feedback. The process is documented to produce a documentary, extensively demonstrating the advantages of the generative AI and emotion engine.

[0712] In this embodiment of the present invention, by integrating a generative AI with an emotion engine, it is possible to achieve more emotionally and technically sophisticated performances.

[0713] The following describes the processing flow.

[0714] Step 1:

[0715] The server collects data related to past talent contests from the internet. This data includes scripts, performance videos, judges' evaluations, and audience reaction data. All of this is stored in a database.

[0716] Step 2:

[0717] The server preprocesses the collected data. Specifically, it formats text data into a parseable format and extracts facial expressions and voices from video data and converts them into text.

[0718] Step 3:

[0719] The server analyzes pre-processed data using natural language processing algorithms. This analysis identifies factors contributing to the success of the performance and points emphasized in evaluation, and extracts characteristic features of the language structure.

[0720] Step 4:

[0721] The server utilizes a generation AI model to generate new scripts based on the analysis results. Furthermore, the emotion engine assists in generating multiple script variations while considering the user's emotional data.

[0722] Step 5:

[0723] The user reviews the generated script and selects the most appropriate variation. Based on the selected script, the user conducts auditions for performers and selects the best performers.

[0724] Step 6:

[0725] The terminal records the practice sessions of selected performers and sends the data to the server. The terminal records video and audio in high resolution, playing a role in comprehensively documenting the practice process.

[0726] Step 7:

[0727] The server analyzes the practice data sent from the terminal and generates feedback. The feedback provides specific suggestions for improvement regarding the timing of speech, intonation, and pauses.

[0728] Step 8:

[0729] The emotion engine analyzes the user's or performer's emotions during practice, recognizing emotional states such as tension and anxiety. Based on this, the emotion engine provides advice on adjusting performance.

[0730] Step 9:

[0731] Users incorporate feedback from the server and advice from the emotion engine to further improve performance. Rehearsals are repeated to prepare for the live broadcast in an optimized state.

[0732] Step 10:

[0733] The user completes their final preparations and participates in the actual talent show competition. The entire process is recorded and edited into a documentary to promote the achievements of the generative AI and emotion engine.

[0734] (Example 2)

[0735] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0736] In traditional performing arts competitions, achieving emotionally impactful performances is a challenging task. There is a need for a system that effectively utilizes past data to generate scripts that take into account predicted audience emotional responses, as well as to select and train performers.

[0737] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0738] In this invention, the server includes means for collecting data from past performing arts competitions, means for analyzing the data to extract linguistic structure and evaluation trends, means for generating a new script based on the analyzed data, and means for analyzing emotions to provide suggestions for adjusting the performance. This enables the generation of optimal scripts for emotionally impactful performances, as well as the selection and training of performers.

[0739] "Data" refers to facts, figures, and observational results collected for the purpose of storing, analyzing, and utilizing information.

[0740] "Analysis" refers to the process of thoroughly examining collected data to reveal its structure and trends.

[0741] "Generation means" refers to a mechanism that executes a technical process to create new deliverables or information based on analyzed data.

[0742] A "script" refers to a document that describes the lines, instructions, and elements used to construct an act or performance.

[0743] "Performers" refers to individuals or groups who actually act or perform based on a script or screenplay.

[0744] "Training" refers to a systematic process of practice and learning aimed at improving specific skills or abilities.

[0745] "Emotion" refers to the psychological and emotional reactions and states of individuals and audiences, encompassing a wide range of sensations and expressions.

[0746] A "proposal for adjustment" refers to specific suggestions for improving or modifying existing plans or activities in order to achieve better results.

[0747] To implement this invention, a server, terminal, and user cooperate to perform a series of processes. The server collects data on past performing arts competitions via the internet, including scripts, performance videos, judges' evaluations, and audience reactions and emotional expressions. This data is stored in a database and used in the next analysis step. The server uses natural language processing techniques to analyze the language structure and evaluation trends from the collected data. In this process, commonly used natural language processing libraries (e.g., NLTK, spaCy) are often utilized.

[0748] The server's generation AI model generates a new script based on the analysis results. The generation AI model uses a large-scale language model (e.g., GPT-3) and integrates sentiment analysis algorithms to create scripts that take into account the emotional responses of the audience.

[0749] Users conduct auditions based on the generated script and select the most suitable performers. The selected performers train using the device. Performances during training are recorded by the device's camera and microphone and uploaded to a server. The server analyzes the recordings and provides feedback on timing and voice adjustments. During this process, voice analysis software is used to measure voice tone and pitch.

[0750] Furthermore, the emotion engine analyzes the voices and facial expressions of the user and audience, and provides suggestions for adjusting the performance. For example, if nervousness is detected during practice, the server will give the user specific advice such as "Speak more slowly" or "Speaking more brightly will give a more positive impression."

[0751] As a concrete example, the server analyzes patterns that generate laughter using data from past comedy shows, and a generative AI model generates a new humorous script. Based on this script, the user can hold auditions, and selected performers can undergo training before performing in the actual show. The following prompt can be used: "Based on data from past comedy shows, generate three new jokes that are likely to make the audience laugh. In the process, take the audience's emotional reactions into consideration."

[0752] In this way, the invention makes it possible to realize theatrical arts that have enhanced emotional impact and technical precision.

[0753] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0754] Step 1:

[0755] The server collects data on past performing arts competitions via the internet. It takes publicly available scripts, performance videos, judges' evaluations, and audience reaction data as input, and stores this data in a database as output. Specifically, it uses web scraping techniques to gather information from various online sources, converts it to JSON format, and saves it to storage.

[0756] Step 2:

[0757] The server analyzes the collected data. It receives script and performance video information from the database as input, processes the data to extract language structure and evaluation trends, and outputs the analysis results. Specifically, it performs text analysis using natural language processing libraries (e.g., NLTK and spaCy), and converts it into structured data through morphological analysis and sentiment classification.

[0758] Step 3:

[0759] The server's generation AI model generates a new script based on the analysis results. It takes a prompt as input and generates a new script as output. Specifically, the generation AI model (e.g., GPT-3) creates a template script based on the prompt, preparing multiple variations.

[0760] Step 4:

[0761] The user conducts auditions based on the generated script to select the most suitable performer. The input consists of multiple generated script variations, and the output determines the performer best suited to the selected script. Specifically, the user and performer collaborate to conduct auditions to select the most suitable candidate from among the candidates.

[0762] Step 5:

[0763] Selected performers use a device to practice the script. The device receives recorded practice videos as input and uploads the recorded data to a server as output. Specific operations include recording practice sessions using the device's camera and microphone.

[0764] Step 6:

[0765] The server analyzes recorded practice data and generates feedback. It analyzes uploaded practice videos as input and provides feedback on speech timing and voice adjustments as output. Specifically, it uses voice analysis software to suggest areas for improvement in performance through voice tone, pitch, and facial expression recognition.

[0766] Step 7:

[0767] Using an emotion engine, the system analyzes emotional responses from the voices and facial expressions of users and audience members, and provides suggestions for performance adjustments. Audio and video data recorded during concerts and rehearsals are provided as input, and emotion-based adjustment suggestions are generated as output. Specific actions include providing concrete advice to the user, such as "it would be good to pause slowly" or "use a different tone of voice."

[0768] (Application Example 2)

[0769] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0770] In traditional in-store customer service events, the individual performance quality of staff members significantly impacts the customer experience, making it difficult to maintain high-quality service. Furthermore, staff members may be unable to deliver appropriate performance due to nervousness or stress, potentially compromising the consistency of the customer service experience.

[0771] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0772] In this invention, the server includes means for collecting past event data, means for analyzing the data to extract language structure and evaluation trends, and means for generating a new script based on the analyzed data. This makes it possible to generate effective and emotionally sensitive customer service scenarios in physical stores.

[0773] "Event data" refers to a collection of information about past events, including participant reactions, scripts, performance details, and evaluations.

[0774] "Linguistic structure" refers to the constituent elements of a text or script, such as the arrangement of words and phrases and grammar, and is extracted by analyzing the formal characteristics of language.

[0775] "Evaluation trends" refer to patterns and tendencies in evaluations derived from past data, and represent tendencies in value judgments based on specific criteria.

[0776] "Generative means" refers to methods and processes for creating new information or structures using data based on a specific purpose.

[0777] A "physical store" refers to a real place of sale or provision where consumers can physically visit and receive goods or services.

[0778] A "customer service scenario" refers to a series of actions and response methods used when dealing with customers in a store, and is a plan that defines how store employees should interact with customers.

[0779] "Emotional analysis means" refers to techniques or methods for determining and analyzing a person's emotional state based on their facial expressions and voice.

[0780] "A state of tension" refers to a state of anxiety or stress that a person experiences psychologically or physiologically in a particular situation, and it is often a factor that affects performance.

[0781] To realize this invention, the server first collects past event data and analyzes it. The collected data includes scripts, evaluation comments, and audience reactions. The server uses natural language processing technology to extract language structure and evaluation trends from this data. Then, based on the analysis results, it generates new customer service scenarios using a generative AI model.

[0782] The generated customer service scenarios are referenced by store employees via smartphones or head-mounted displays. Users practice based on these scenarios, and the device records their practice and transmits the footage to a server. The server analyzes the employee's tension level from the practice video using emotion analysis tools and provides suggestions for adjusting their performance. This allows users to achieve more optimal performance.

[0783] A concrete example is a new product promotion event where, based on data obtained through emotion analysis, advice is given on how to alleviate tension, and a script generated by AI is used to ensure that store staff interact with customers in a fun and relaxed manner.

[0784] An example of a prompt message is: "Please generate a script for the next product sales event, taking customer feedback into consideration. This should include methods to help staff members relax if they appear nervous, so that they can provide more effective customer service."

[0785] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0786] Step 1:

[0787] The server collects historical event data from resources on the internet. The collected data includes scripts, audience reactions, and evaluation comments. This data is stored in a database for analysis. The input for this step is internet resources, and the output is the event data stored in the database.

[0788] Step 2:

[0789] The server analyzes the collected event data using natural language processing techniques. It uses language analysis algorithms to extract the linguistic structure and evaluation trends of the script. The input for this step is event data read from a database, and the output is the linguistic structure and evaluation trends as a result of the analysis.

[0790] Step 3:

[0791] The server generates new customer service scenarios using a generative AI model based on the analysis results. It generates multiple script variations, each aiming to maximize the audience's response. The input for this step is language structure and evaluation tendencies, and the output is the generated customer service scenario.

[0792] Step 4:

[0793] The user (store clerk) receives a customer service scenario generated through the terminal and practices according to it. The terminal records the practice session on video. The input for this step is the generated customer service scenario, and the output is the video data of the practice session.

[0794] Step 5:

[0795] The recorded practice video is transferred to a server. The server uses emotion analysis tools to analyze the employee's facial expressions and voice from the video data and determine their level of tension and emotional state. The input for this step is the video data, and the output is emotional data that determines the level of tension.

[0796] Step 6:

[0797] The server provides feedback to the employee based on the emotion analysis results. It sends specific advice to alleviate tension and performance adjustment suggestions to the terminal. The input for this step is emotion data and a generated customer service scenario, and the output is emotion-based feedback.

[0798] Step 7:

[0799] Users optimize their performance based on feedback from the server. Through this process, users can relax and provide more effective customer service. The input in this step is feedback, and the output is optimized performance.

[0800] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0801] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0802] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0803] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0804] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0805] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0806] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0807] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0808] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0809] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0810] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0811] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0812] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0813] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0814] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0815] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0816] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0817] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0818] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0819] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0820] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0821] The following is further disclosed regarding the embodiments described above.

[0822] (Claim 1)

[0823] Methods for collecting data from past talent contests,

[0824] A means for analyzing the aforementioned data to extract language structure and evaluation trends,

[0825] A generation means for generating a new script based on the analyzed data,

[0826] A method for selecting performers to use the generated script and for them to practice together,

[0827] An evaluation means that records and analyzes the aforementioned practice process and provides feedback,

[0828] A system that includes this.

[0829] (Claim 2)

[0830] The system according to claim 1, wherein the generation means includes an algorithm for creating multiple script variations.

[0831] (Claim 3)

[0832] The system according to claim 1, wherein the evaluation means includes means for analyzing and optimizing the speaker's speaking timing, vocalization, and pauses.

[0833] "Example 1"

[0834] (Claim 1)

[0835] Means of obtaining information on past entertainment competitions,

[0836] A means for analyzing the aforementioned information and extracting language structure and evaluation characteristics,

[0837] A means for generating a new document based on the analyzed information,

[0838] A means of selecting executors to use the generated documents and practicing collaboratively,

[0839] An evaluation means that records and analyzes the aforementioned practice process and provides improvement suggestions,

[0840] A system that includes this.

[0841] (Claim 2)

[0842] The system according to claim 1, wherein the creation means includes a calculation method for generating multiple document variations.

[0843] (Claim 3)

[0844] The system according to claim 1, wherein the evaluation means includes means for analyzing and optimizing the timing, utterance, and pauses of the executor's speech.

[0845] "Application Example 1"

[0846] (Claim 1)

[0847] Means of collecting information on past performance events,

[0848] A means for analyzing the aforementioned information to extract language structure and evaluation tendencies,

[0849] A generation means for generating a new manuscript based on the analyzed information,

[0850] A method for selecting performers to use the generated script and for them to practice together,

[0851] An evaluation means that records and analyzes the aforementioned practice process and provides feedback,

[0852] A means of generating a script using a generative AI model based on user input, and providing feedback on the timing of speech and emotional expression,

[0853] A system that includes this.

[0854] (Claim 2)

[0855] The system according to claim 1, wherein the generation means includes an algorithm for creating multiple manuscript variations.

[0856] (Claim 3)

[0857] The system according to claim 1, wherein the evaluation means includes means for analyzing and optimizing the timing, voice, and pauses of the performer's speech, and means for generating feedback based on the recorded voice.

[0858] "Example 2 of combining an emotion engine"

[0859] (Claim 1)

[0860] A means of collecting data from past performing arts competitions,

[0861] A means for analyzing the aforementioned data to extract language structure and evaluation trends,

[0862] A generation means for generating a new script based on analyzed data,

[0863] A means of selecting and jointly training performers who will use the generated script,

[0864] An evaluation means that records and analyzes the aforementioned training process and provides feedback,

[0865] A means of analyzing emotions and providing suggestions for adjusting acting,

[0866] A system that includes this.

[0867] (Claim 2)

[0868] The system according to claim 1, wherein the generation means includes an algorithm for creating multiple script variations.

[0869] (Claim 3)

[0870] The system according to claim 1, wherein the evaluation means includes means for analyzing and optimizing the performer's speaking timing, vocalization, and pauses.

[0871] "Application example 2 when combining with an emotional engine"

[0872] (Claim 1)

[0873] Means for collecting past event data,

[0874] A means for analyzing the aforementioned data to extract language structure and evaluation trends,

[0875] A generation means for generating a new script based on the analyzed data,

[0876] A method for selecting individuals to use the generated script and practicing together,

[0877] An evaluation means that records and analyzes the aforementioned practice process and provides feedback,

[0878] An emotion analysis method that analyzes the user's tension level from their facial expressions and voice to adjust performance,

[0879] A means of generating customer service scenarios in physical stores and providing applications for store staff to use,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, comprising an algorithm for creating multiple script variations.

[0883] (Claim 3)

[0884] The system according to claim 1, comprising means for analyzing and optimizing the timing, vocalization, and pauses of a performer's speech. [Explanation of Symbols]

[0885] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Methods for collecting data from past talent contests, A means for analyzing the aforementioned data to extract language structure and evaluation trends, A generation means for generating a new script based on the analyzed data, A method for selecting performers to use the generated script and for them to practice together, An evaluation means that records and analyzes the aforementioned practice process and provides feedback, A system that includes this.

2. The system according to claim 1, wherein the generation means includes an algorithm for creating a plurality of script variations.

3. The system according to claim 1, wherein the evaluation means includes means for analyzing and optimizing the timing, vocalization, and pauses of the performer's speech.

Images