system

Abstract

We provide the system. [Solution] A means of automatically generating scripts and other materials using a generation algorithm based on the distribution theme entered by the user, A means to scan the broadcaster's device environment and automatically suggest and configure the optimal broadcast settings, A means to monitor viewer comments in real time during the broadcast and filter out inappropriate content, A means of collecting and analyzing viewing data after the broadcast and providing viewer feedback as a report, A means to select and configure content monetization models, and to track and manage revenue data. 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 as a 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] For beginners aiming for a distribution debut and users who are insecure about technology, setting up the distribution environment, creating high-quality content, and building means for following viewers and monetization after distribution require a lot of time and effort and are a heavy burden. Therefore, in order to carry out distribution activities effectively and safely, a system that enables even users without technical knowledge to easily experience advanced distribution is necessary.

Means for Solving the Problems

[0005] This invention includes a generation algorithm that automatically generates scripts and reports based on a distribution theme entered by the user, and means for scanning the distributor's terminal environment to automatically suggest and configure optimal distribution settings. Furthermore, it can monitor viewer comments in real time during distribution and filter out inappropriate content. In addition, it aggregates and analyzes viewing data after distribution and provides viewer feedback as a report. It also includes means for selecting and configuring content monetization models and tracking and managing revenue data, thus enabling users to easily manage everything from distribution preparation to post-distribution follow-up and monetization.

[0006] A "user" is an individual or legal entity that creates and distributes content using a distribution platform.

[0007] A "generative algorithm" is a computational method for automatically generating content such as scripts and screenplays based on input data from the user.

[0008] "Terminal environment" refers to the hardware and software configuration necessary for streaming, including camera, microphone, and network connectivity.

[0009] "Streaming settings" refer to a set of parameters necessary to ensure the quality and stability of the stream, including bitrate, resolution, and frame rate.

[0010] "Filtering" is the process of monitoring viewer input and comments and removing or hiding inappropriate or unnecessary information.

[0011] "Viewing data" refers to viewer behavior data collected during a live stream, including viewing time, number of comments, and engagement rate.

[0012] A "monetization model" is a methodology for generating financial profit from content, and includes advertising, paid viewing models, and the sale of related merchandise.

[0013] "Revenue data" refers to information about profits earned through streaming activities, and is a set of information used to track things like advertising revenue and product sales performance. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This 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 the 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 the emotion engine is combined.

Modes for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0017] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of a plurality of 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 signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[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] The present invention is a system for enabling users to easily deliver high-quality content, and its embodiments are described below.

[0036] Users access the platform and register by first entering their personal information and the purpose of their distribution. This registration information forms the basis for generating content based on the distribution theme.

[0037] The server scans the user's terminal environment. During this process, it detects the camera, microphone, and network status, and generates optimal streaming settings based on this information. For example, the bitrate and frame rate are adjusted according to the resolution of the camera being used and the speed of the internet connection.

[0038] Next, when the user enters the theme for their broadcast, the server automatically generates a script or screenplay using a generation algorithm. This screenplay includes the topics to be covered and the flow of the scenario during the broadcast, which the user can then use as a basis for their broadcast.

[0039] During the live stream, the server monitors viewer comments in real time and immediately filters out inappropriate remarks and spam. This allows users to prevent problems and ensure a smooth live stream. Important comments are notified on the user's device, enabling them to respond quickly.

[0040] After the broadcast ends, the server analyzes the collected viewing data and provides users with a report. This report includes viewing statistics and viewer feedback, which can be used as a reference for future broadcasts.

[0041] Furthermore, users can select and configure monetization models through their devices. The server tracks and manages revenue data based on these settings and reports it to the user. For example, data on revenue from ad impressions and product purchases by viewers are updated in real time.

[0042] This provides users with a consistently supported environment, from pre-broadcast preparation and in-broadcast interaction to post-broadcast follow-up and monetization.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] Users access the distribution platform and register their personal information and distribution purpose. This information is sent to the server and used in subsequent steps.

[0046] Step 2:

[0047] The server scans the user's device environment to detect the resolution of the camera being used, the model number of the microphone, and the internet connection speed. Based on this information, it generates settings that suggest the optimal bitrate and frame rate for streaming.

[0048] Step 3:

[0049] Users enter the theme and related keywords they want to distribute and send them to the server.

[0050] Step 4:

[0051] The server automatically generates scripts and screenplays using a generation algorithm based on the input theme. This includes the flow of each scene, key points of the dialogue, and suggestions for visual materials.

[0052] Step 5:

[0053] Once the broadcast begins, the server monitors viewer comments in real time, and AI filtering immediately detects and removes inappropriate comments. Other comments are promptly forwarded to the user, allowing for uninterrupted responses.

[0054] Step 6:

[0055] After the broadcast ends, the server compiles the accumulated viewing data and analyzes viewing time, number of comments, engagement rate, etc. The analysis results are then fed back to the user in the form of a report.

[0056] Step 7:

[0057] Users select a monetization model and configure advertising and payment options through their device. The server tracks revenue data based on these settings and reports it to the user periodically, including, for example, ad views and sales performance.

[0058] This allows users to comprehensively manage all aspects of their streaming activities, promoting the delivery of high-quality content and monetization.

[0059] (Example 1)

[0060] 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."

[0061] In online streaming, there is a need for users to easily generate high-quality content, maintain smooth interaction with viewers, and maximize the effectiveness of the stream. However, with current technologies, optimizing the streaming environment and providing individual viewer feedback on content has been necessary, leading to increased user burden. Furthermore, limited monetization options have made sustainable streaming operations difficult.

[0062] 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.

[0063] In this invention, the server includes means for automatically generating content using a generation method based on information input by the user and the distribution theme; means for analyzing the user's device environment and automatically proposing and configuring appropriate distribution settings; and means for immediately monitoring responses from recipients during distribution and eliminating inappropriate information. As a result, the user is comprehensively supported from pre-distribution preparation to distribution management and post-distribution analysis, maximizing the effectiveness of distribution and enabling sustainable operation with expanded monetization options.

[0064] "User" refers to an entity that distributes content using a distribution platform, and can be an individual or an organization.

[0065] "Distribution theme" refers to information that describes the subject or purpose of the content a user distributes.

[0066] "Generation methods" refer to technologies that automatically construct and create content based on user input data.

[0067] "Device environment" refers to the environment including the hardware and software configuration used by the user.

[0068] "Streaming settings" refer to technical parameters such as bitrate, frame rate, and audio quality that are automatically adjusted to optimize streaming.

[0069] "Recipient" refers to the viewer who watches the content distributed by the user.

[0070] "Inappropriate information" refers to comments or reactions from viewers that may potentially hinder the purpose or quality of the broadcast.

[0071] This invention is a system that utilizes a distribution platform to help users easily deliver high-quality online broadcasts. Users access the platform, enter their personal information and broadcast theme, and register. This registration information forms the basis for content generation, and the server uses a generation method to automatically generate scripts and screenplays according to the broadcast content.

[0072] The server analyzes the user's device environment. Specifically, it collects data such as the resolution of the camera being used, the quality of the microphone, and the network speed, and automatically configures streaming settings that optimize the bitrate and frame rate based on this data. In addition, to ensure smooth interaction during streaming, it monitors viewer comments in real time and immediately filters out inappropriate information.

[0073] After the broadcast ends, the server collects viewing data and provides users with a visualized report. This report includes the number of viewers, time spent on the screen, engagement levels, and feedback from recipients. This makes it easy for users to identify areas for improvement for future broadcasts.

[0074] Regarding monetization, users select and configure suitable monetization strategies via their devices. Based on these settings, the server tracks and manages revenue information, such as ad placement, and reports regularly updated data to the user.

[0075] As a concrete example, when a user broadcasts an online cooking class, they enter "vegetarian recipes" as the broadcast theme. The server then optimizes the broadcast settings based on the user's camera resolution and internet speed, and creates a script using a generative AI model. It uses prompts such as "Generate a script for an online cooking class. The theme is 'vegetarian recipes'" to specify the content. This allows the user to deliver a broadcast that will interest viewers based on the script.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] Users access the platform, enter their personal information and distribution themes, and register. This involves entering information into an online form and clicking a submit button. The input data includes personal information (e.g., name, email address) and distribution themes. The server receives this input and registers it in its database. The distribution themes entered by the user form the basis for content generation.

[0079] Step 2:

[0080] The server scans the user's device environment. During this process, it collects device data such as camera resolution, microphone audio quality, and network speed. Based on this data, calculations are performed to set the optimal bitrate and frame rate. Specifically, if the network speed is slow, the frame rate is lowered; if a high-resolution camera is being used, the bitrate is increased. As a result, the adjusted streaming settings are sent to the device.

[0081] Step 3:

[0082] After the user enters a broadcast theme, the server automatically generates a script or screenplay using a generative AI model. The input for this process is the broadcast theme that the user has set in advance. Based on this theme, the generative AI model aggregates relevant information and creates a script that includes the flow of the topic and specific content. The output is a script that can be used for broadcasting, which is sent to the user's terminal and displayed.

[0083] Step 4:

[0084] During the broadcast, the server monitors and filters viewer comments in real time. The input is the viewer comment stream. Natural language processing technology is used to analyze the comments, identifying and immediately removing inappropriate remarks and spam. Important comments are also notified to the user's device. This allows users to quickly interact with viewers.

[0085] Step 5:

[0086] After the broadcast ends, the server collects viewing data and generates a visualized report. This input includes broadcast data such as the number of viewers, viewing time, and engagement level. The server performs aggregation and analysis, generating a report that visualizes the results as graphs and statistics. The output is a report outlining areas for improvement for the next broadcast, which is sent to and provided to the user.

[0087] Step 6:

[0088] Users select and configure monetization models through their devices. Inputs include monetization-related choices (e.g., ad types, revenue sharing methods). Based on this, the server manages ad placement and product sales tracking, updating and tracking revenue data in real time. The final output is a regularly generated revenue report, which is provided to the user.

[0089] (Application Example 1)

[0090] 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."

[0091] In modern streaming services, users often need specialized knowledge and skills to provide high-quality and engaging content. Furthermore, there is a demand for mechanisms that efficiently monetize content while incorporating sophisticated real-time interaction with viewers. This challenge is particularly significant for novice streamers and small-scale content creators operating independently. Moreover, methods for accurately understanding viewer reactions and using that feedback to improve future streams are often insufficient. This invention is provided to address these issues.

[0092] 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.

[0093] In this invention, the server includes means for automatically generating content generation instructions using a generation algorithm based on information input from the user, means for scanning the distributor's information processing device environment and automatically setting optimal distribution conditions, and means for sequentially auditing responses from recipients during distribution and eliminating inappropriate content. As a result, distributors can perform high-quality distribution without relying on specialized technical skills, maintain smooth interaction with the audience, and efficiently monetize and improve future distributions.

[0094] A "generation algorithm" is a method for automatically generating content instructions from information entered by the user.

[0095] The term "information processing device environment" refers to the state of the terminal used by the broadcaster and its connection environment.

[0096] "Distribution conditions" is a term that refers to the technical settings and adjustments required when distributing content.

[0097] "Reactions from recipients" refers to reactions such as comments and ratings made by viewers of the broadcast.

[0098] "Inappropriate content" refers to offensive, discriminatory, or spam messages that should be removed during the broadcast.

[0099] A "content generation instruction sheet" refers to an automatically generated outline or script that follows a given theme and is used as a reference during distribution.

[0100] The system for realizing this invention primarily uses a server, a user terminal, and a generation AI model. The server automatically creates content generation instructions using a generation algorithm based on information input from the user. The generated instructions are sent to the user's terminal and provided to the distributor.

[0101] The user's device scans the delivery environment and feeds back the optimal delivery conditions to the server. Based on this information, the server sets conditions suitable for the sender, enabling efficient delivery. Furthermore, during delivery, responses from recipients are audited in real time. This audit is essential to help eliminate inappropriate content and achieve better interaction.

[0102] The specific hardware is a smartphone, and the software uses OpenAI's GPT series as a generative AI model and the NLTK library for natural language processing. This allows users to leverage the generative AI model and efficiently provide scripts for smooth distribution.

[0103] For example, a user could choose "Live Cooking Show" as their theme and enter a text prompt like this: "The theme for the next live cooking show is Italian cuisine. The automatically generated script will start by showing how to make an appetizer, then move on to the main course. Please suggest some topic ideas." Based on this prompt, the generating AI model will provide a predetermined scenario to support the user's broadcast.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The user enters the distribution theme and personal information into their device. This input data is sent to the server, where the distribution purpose and user information are recorded in the database. The important point here is that the entered data forms the basis of subsequent automated generation processes.

[0107] Step 2:

[0108] The server receives data sent from the user's terminal and passes prompt messages to the generative AI model to generate a script. Specifically, it uses the generative AI model to generate content generation instructions that match the theme entered by the user. These prompt messages include specific instructions such as, "The theme for the next cooking live stream will be Italian cuisine."

[0109] Step 3:

[0110] The terminal scans the current camera, microphone, and network status based on the content generation instructions received from the server to determine the optimal delivery conditions. The input includes the terminal's hardware status, and the output consists of specific parameters required for configuration.

[0111] Step 4:

[0112] Based on the scan results, the server proposes optimal delivery conditions to the user and automatically makes any necessary adjustments. The data processing performed here involves analyzing status information from the terminal and calculating the best bitrate and frame rate.

[0113] Step 5:

[0114] Once a user starts streaming, the server monitors viewer reactions in real time. It supports smooth streaming by filtering out inappropriate comments. The input includes viewer comments, and the output is a filtered set of comments.

[0115] Step 6:

[0116] After the broadcast ends, the server collects and analyzes viewing data. In this step, trends in viewer behavior are analyzed based on the collected data, and feedback is compiled for the next broadcast. The output is a report that includes suggestions for improvement for the next broadcast.

[0117] Step 7:

[0118] The user reviews feedback from the server and selects a monetization model. Based on the selected model, the server tracks revenue data and manages revenue status in real time. Inputs include information on the selected monetization model, and outputs are revenue and its report.

[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 enables users of a distribution platform to improve the quality of content by recognizing their emotional state. This facilitates smoother interaction with viewers and makes it possible to provide a more personalized experience. The following describes specific embodiments for carrying out this invention.

[0121] Users access the distribution platform and register. During this process, they enter personal information and distribution objectives, and, if necessary, select the option to enable the sentiment engine, thus preparing to use the sentiment recognition feature.

[0122] The server acquires the user's facial expressions and voice tone through the camera and microphone installed on the user's device. By analyzing this information in real time, the emotion engine can recognize the user's emotional state and use the results as feedback.

[0123] When a user inputs themes and related content to be delivered, the server uses a generation algorithm to automatically generate scripts and screenplays based on this information. During this process, feedback from an emotion engine can be incorporated, and suggestions can be included to help the user adjust the content based on their current emotions.

[0124] During the live stream, the server monitors viewer comments in real time, and inappropriate comments are filtered out using AI. Additionally, an emotion engine monitors the user's emotions and suggests actions based on their specific emotional state. For example, if tension is detected, it can suggest that the user take a break to relax.

[0125] After the broadcast, the server collects viewing and sentiment data and provides users with a detailed analysis report. This allows users to correlate changes in sentiment during the broadcast with viewer reactions and clearly identify areas for improvement for future broadcasts.

[0126] Furthermore, emotional data is applied to selected monetization models, used to optimize the timing and content of ad displays. This enables higher engagement and more effective monetization.

[0127] Thus, the present invention realizes multi-functional delivery support, including user emotion recognition, and supports the implementation of advanced delivery even if the user does not possess technical knowledge.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] Users access the distribution platform and create an account. They enter their personal information and distribution purpose, and enable the sentiment engine option as needed.

[0131] Step 2:

[0132] The server accesses the user's device and retrieves camera and microphone data. Based on this, it checks the performance of the peripherals being used and generates the optimal streaming settings.

[0133] Step 3:

[0134] The user enters the theme and keywords of the content to be distributed into their device. This information is sent to the server.

[0135] Step 4:

[0136] The server uses theme information received from the user to automatically generate scripts and screenplays through a generation algorithm. At this stage, the emotion engine analyzes the user's recent emotion data and fine-tunes the content based on that analysis.

[0137] Step 5:

[0138] As soon as streaming begins, the server monitors the user's facial expressions and tone of voice in real time. The emotion engine recognizes the emotional state from this data, and if, for example, tension or stress is detected, it notifies the user and offers suggestions for relaxation.

[0139] Step 6:

[0140] Simultaneously, the server monitors comments sent by viewers in real time and automatically filters out inappropriate content. This filtering is performed by AI, ensuring a safe viewing environment.

[0141] Step 7:

[0142] After the broadcast ends, the server aggregates the viewing and sentiment data accumulated during the broadcast and generates a detailed analysis report. This report takes into account the relationship between changes in sentiment and viewer reactions.

[0143] Step 8:

[0144] Users receive reports via their devices, allowing them to identify areas for improvement and effective strategies for future deliveries. This feedback includes analysis by an emotion engine, helping to develop more personalized delivery strategies.

[0145] Step 9:

[0146] Furthermore, from a monetization perspective, the emotion engine analyzes viewer emotion data to recommend optimal ad display timings and content. Based on this information, users can efficiently monetize their content.

[0147] (Example 2)

[0148] 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".

[0149] Providing an effective and personalized experience for viewers requires technical knowledge and a great deal of trial and error. Furthermore, traditional streaming systems lack concrete methods for understanding viewer emotions and reactions in real time and improving content quality. Additionally, data utilization to enhance monetization efficiency is insufficient.

[0150] 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.

[0151] In this invention, the server includes means for automatically generating components using a generation method based on information input from the user, means for detecting the sender's equipment environment and automatically proposing and setting the optimal transmission settings, and means for immediately monitoring the receiver's response during transmission and censoring inappropriate content. This allows the broadcaster to understand the audience's emotions in real time, thereby improving the quality of the content and achieving effective monetization.

[0152] A "user" is an entity that uses a system to input information and receive services and functions.

[0153] A "server" is a computer system that processes user input and provides various functions.

[0154] A "generation method" is an algorithm or process for automatically generating components based on information input by the user.

[0155] "Sender" refers to the individual or organization that distributes or sends information.

[0156] "Device environment" refers to the settings including the configuration and operating status of the devices and networks used by the sender.

[0157] "Inappropriate content" refers to information or comments that are undesirable or offensive to viewers or recipients.

[0158] "Censorship" is the process of excluding or hiding content that is deemed inappropriate based on specific criteria.

[0159] "Recipient" refers to an individual or group that receives information that has been distributed or transmitted.

[0160] "Emotional state" refers to the psychological state analyzed from the user's facial expressions, voice, and other factors.

[0161] "Monetization" refers to the methods and processes for generating financial profit through the provision of services or content.

[0162] This invention is a distribution support system using a server and terminals that can improve content quality and increase the efficiency of monetization through user emotion recognition. The following describes specific embodiments of the system.

[0163] Users first access the distribution platform using their own devices and enter the necessary personal information and distribution purpose. If they wish to enable the emotion recognition feature, they select a dedicated option. The device is equipped with a camera and microphone, which are used to capture the user's facial expressions and voice tone. This emotion data is then sent to the server and analyzed in real time.

[0164] The server uses an emotion engine to process data sent from the terminal and determine the user's emotional state. Based on this information, it utilizes a generative AI model to automatically generate scripts and screenplays that match the delivery theme entered by the user. The generated content reflects feedback based on the user's emotional state and includes suggestions for improving the quality of the content.

[0165] During the broadcast, the server monitors viewer comments in real time and uses AI filtering technology to censor inappropriate comments. Furthermore, the emotion engine continuously monitors the user's emotions and, if it detects a specific emotional state, suggests a concrete action, such as "suggesting a break to relax."

[0166] After the broadcast ends, the server collects viewing and sentiment data and generates a detailed analysis report. This allows users to analyze the relationship between changes in sentiment during the broadcast and viewer reactions, enabling them to identify areas for improvement for future broadcasts. Furthermore, sentiment data is used to optimize the monetization model, helping to adjust the timing and content of ad displays.

[0167] For example, if a user chooses "live cooking streaming" as their theme, the server can use a generative AI model to automatically generate a script using a chef template as source material. It can also analyze the user's emotional state and make adjustments, such as suggesting a calm tone of voice if the user is nervous.

[0168] Example of a prompt:

[0169] "Based on the user's current emotional state, please suggest a suitable way of speaking for a cooking commentary."

[0170] Thus, the present invention utilizes user emotion recognition to enable sophisticated delivery even without technical knowledge on the part of the user, and to provide personalized experiences to viewers.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] Users access the distribution platform using their devices and enter their personal information and distribution purpose. This data is sent to the server, which stores the user's profile in a database and confirms the option to enable sentiment recognition. This process prepares the user's basic information and distribution-ready data.

[0174] Step 2:

[0175] The device activates its camera and microphone to capture the user's facial expressions and voice tone. This data is transmitted to the server in real time. The server analyzes this data using an emotion engine to recognize the user's emotional state. This output is used as feedback to generate the next content via a generative AI model.

[0176] Step 3:

[0177] The user inputs the theme and related content they wish to deliver into their device. The server uses a generative AI model to automatically generate scripts and screenplays based on the input theme. Based on the user's theme information and sentiment data as input data, the server generates content and outputs a script that includes suggestions tailored to the user's sentiment.

[0178] Step 4:

[0179] During the broadcast, the server monitors viewer comments in real time. An AI filtering system analyzes the incoming comment data and removes inappropriate content. This process maintains the appropriateness of comments and ensures the quality of the broadcast.

[0180] Step 5:

[0181] The server continuously monitors the user's emotions through an emotion engine. When a specific emotional state is detected, the server suggests an action to the user, such as "suggesting a break to relax." In this step, emotional data is used as input to output suggestions that are appropriate to the user's state.

[0182] Step 6:

[0183] After the broadcast ends, the server collects viewing and sentiment data. Based on this data, it generates a detailed analysis report and provides it to the user. The user uses this report as input to help improve future broadcasts. The output provides a list of areas for improvement based on viewer reactions and changes in sentiment.

[0184] Step 7:

[0185] The server optimizes the monetization model using sentiment data. It analyzes revenue data as input and adjusts the optimal timing and content of ad displays. In this step, based on data analysis, it outputs a monetization strategy to increase engagement.

[0186] (Application Example 2)

[0187] 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 device 14 will be referred to as the "terminal."

[0188] Modern content delivery requires flexible adjustment of content based on the user's emotional state and real-time feedback. However, conventional systems lack the functionality to recognize emotional states and reflect them in the content, making it difficult to improve the user experience. This invention aims to provide a personalized experience by recognizing the user's emotional state in real time and improving interaction with viewers.

[0189] 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.

[0190] In this invention, the server includes means for automatically generating documents and scripts using a generation method based on a theme input by the user; means for recognizing the broadcaster's electronic device and automatically suggesting and setting the optimal settings; and means for analyzing the user's emotional state in real time using an emotion recognition function and providing feedback to adjust the content and speech during broadcast. This enables the user to dynamically adjust content according to their emotional state and communicate effectively with viewers.

[0191] A "user" refers to an individual or organization that uses a content distribution platform to disseminate information or content.

[0192] A "theme" refers to the subject or purpose of the content that the user sets when distributing it.

[0193] "Generation method" refers to algorithms and technologies that automatically generate content based on input information.

[0194] A "document" is a text-based data file that is automatically generated by a generation method and includes scripts and other data intended for use during broadcast.

[0195] "Electronic devices" refers to a broad range of hardware, including digital devices and terminals used by users for distribution.

[0196] "Emotion recognition functionality" refers to technology that uses cameras and microphones to analyze a user's emotional state from their facial expressions and voice, and acquires the results as data.

[0197] "Real-time analysis" refers to a process where data is analyzed immediately upon acquisition, and the results are provided in a usable format.

[0198] "Feedback" refers to information and advice provided to users based on the results of emotion recognition, and is used to adjust the content and progress of the broadcast.

[0199] "Content" refers to all forms of expression, including information and media formats, distributed by users.

[0200] The system for implementing this invention enables smooth content generation and distribution when users utilize a distribution platform. The server and the user's terminal play key roles.

[0201] The server automatically generates documents and scripts based on themes entered by the user, using generation methods. It also provides emotion recognition capabilities, recognizing the user's emotions in real time through the user's electronic devices, such as smart glasses or smartphones, using their cameras and microphones. This emotion data is analyzed to provide feedback necessary for adjusting the content of the broadcast and spoken utterances. The server can utilize the aforementioned generation AI model.

[0202] The user's device automatically suggests and implements optimal delivery settings based on instructions from the server. Furthermore, it has the ability to monitor real-time information from viewers and filter out inappropriate content. It can also combine viewing data with sentiment analysis results and provide this information to the user in the form of a report.

[0203] As a concrete example, when a user is using smart glasses to stream, the device instantly analyzes their emotional state and provides feedback such as "Try taking a deep breath" if the result indicates they are feeling nervous. An example of a prompt accompanying this process would be, "The user is feeling nervous. Please suggest ways for her to relax."

[0204] Overall, this system enables users to adjust content appropriately based on their emotional state and engage in effective interaction with their audience.

[0205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0206] Step 1:

[0207] The user logs into the distribution platform and enters the distribution theme and related information. The input data is sent to the server. The server receives this information and uses it to initialize the generation method. This enables the generation of documents and scripts tailored to the user.

[0208] Step 2:

[0209] The server captures the user's facial expressions and voice in real time through the camera and microphone accessed from the user's electronic device. This serves as the input for emotional data. The server analyzes this data to identify the user's emotional state. Emotion recognition and generative AI models are used for the analysis. The output is data indicating the emotional state.

[0210] Step 3:

[0211] The server adjusts the generated script based on the emotion data obtained in step 2. During this process, it uses a generative AI model to generate feedback and suggestions tailored to the emotional state. This feedback is then presented to the user as a prompt. For example, if the user is feeling anxious, the server might generate a message such as "Try taking a deep breath" and send it to the user's device.

[0212] Step 4:

[0213] During the broadcast, the server monitors viewer comments and feedback in real time. Comments are sent to the server as input data and filtered to remove inappropriate content. The output is clean comment data. Prompts are adjusted as needed to facilitate smooth interaction with viewers.

[0214] Step 5:

[0215] After the broadcast ends, the server integrates and analyzes viewing data and sentiment data. This data processing allows for detailed analysis, including viewer reactions and changes in user sentiment. As output, a report is generated that includes suggestions for improvement for the next broadcast and is provided to the user. This process allows users to gain concrete insights for their next broadcast.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] [Second Embodiment]

[0220] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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).

[0226] 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.

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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".

[0232] The present invention is a system for enabling users to easily deliver high-quality content, and its embodiments are described below.

[0233] Users access the platform and register by first entering their personal information and the purpose of their distribution. This registration information forms the basis for generating content based on the distribution theme.

[0234] The server scans the user's terminal environment. During this process, it detects the camera, microphone, and network status, and generates optimal streaming settings based on this information. For example, the bitrate and frame rate are adjusted according to the resolution of the camera being used and the speed of the internet connection.

[0235] Next, when the user enters the theme for their broadcast, the server automatically generates a script or screenplay using a generation algorithm. This screenplay includes the topics to be covered and the flow of the scenario during the broadcast, which the user can then use as a basis for their broadcast.

[0236] During the live stream, the server monitors viewer comments in real time and immediately filters out inappropriate remarks and spam. This allows users to prevent problems and ensure a smooth live stream. Important comments are notified on the user's device, enabling them to respond quickly.

[0237] After the broadcast ends, the server analyzes the collected viewing data and provides users with a report. This report includes viewing statistics and viewer feedback, which can be used as a reference for future broadcasts.

[0238] Furthermore, users can select and configure monetization models through their devices. The server tracks and manages revenue data based on these settings and reports it to the user. For example, data on revenue from ad impressions and product purchases by viewers are updated in real time.

[0239] This provides users with a consistently supported environment, from pre-broadcast preparation and in-broadcast interaction to post-broadcast follow-up and monetization.

[0240] The following describes the processing flow.

[0241] Step 1:

[0242] Users access the distribution platform and register their personal information and distribution purpose. This information is sent to the server and used in subsequent steps.

[0243] Step 2:

[0244] The server scans the user's device environment to detect the resolution of the camera being used, the model number of the microphone, and the internet connection speed. Based on this information, it generates settings that suggest the optimal bitrate and frame rate for streaming.

[0245] Step 3:

[0246] Users enter the theme and related keywords they want to distribute and send them to the server.

[0247] Step 4:

[0248] The server automatically generates scripts and screenplays using a generation algorithm based on the input theme. This includes the flow of each scene, key points of the dialogue, and suggestions for visual materials.

[0249] Step 5:

[0250] Once the broadcast begins, the server monitors viewer comments in real time, and AI filtering immediately detects and removes inappropriate comments. Other comments are promptly forwarded to the user, allowing for uninterrupted responses.

[0251] Step 6:

[0252] After the broadcast ends, the server compiles the accumulated viewing data and analyzes viewing time, number of comments, engagement rate, etc. The analysis results are then fed back to the user in the form of a report.

[0253] Step 7:

[0254] Users select a monetization model and configure advertising and payment options through their device. The server tracks revenue data based on these settings and reports it to the user periodically, including, for example, ad views and sales performance.

[0255] This allows users to comprehensively manage all aspects of their streaming activities, promoting the delivery of high-quality content and monetization.

[0256] (Example 1)

[0257] 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."

[0258] In online streaming, there is a need for users to easily generate high-quality content, maintain smooth interaction with viewers, and maximize the effectiveness of the stream. However, with current technologies, optimizing the streaming environment and providing individual viewer feedback on content has been necessary, leading to increased user burden. Furthermore, limited monetization options have made sustainable streaming operations difficult.

[0259] 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.

[0260] In this invention, the server includes means for automatically generating content using a generation method based on information input by the user and the distribution theme; means for analyzing the user's device environment and automatically proposing and configuring appropriate distribution settings; and means for immediately monitoring responses from recipients during distribution and eliminating inappropriate information. As a result, the user is comprehensively supported from pre-distribution preparation to distribution management and post-distribution analysis, maximizing the effectiveness of distribution and enabling sustainable operation with expanded monetization options.

[0261] "User" refers to an entity that distributes content using a distribution platform, and can be an individual or an organization.

[0262] "Distribution theme" refers to information that describes the subject or purpose of the content a user distributes.

[0263] "Generation methods" refer to technologies that automatically construct and create content based on user input data.

[0264] "Device environment" refers to the environment including the hardware and software configuration used by the user.

[0265] "Streaming settings" refer to technical parameters such as bitrate, frame rate, and audio quality that are automatically adjusted to optimize streaming.

[0266] "Recipient" refers to the viewer who watches the content distributed by the user.

[0267] "Inappropriate information" refers to comments or reactions from viewers that may potentially hinder the purpose or quality of the broadcast.

[0268] This invention is a system that utilizes a distribution platform to help users easily deliver high-quality online broadcasts. Users access the platform, enter their personal information and broadcast theme, and register. This registration information forms the basis for content generation, and the server uses a generation method to automatically generate scripts and screenplays according to the broadcast content.

[0269] The server analyzes the user's device environment. Specifically, it collects data such as the resolution of the camera being used, the quality of the microphone, and the network speed, and automatically configures streaming settings that optimize the bitrate and frame rate based on this data. In addition, to ensure smooth interaction during streaming, it monitors viewer comments in real time and immediately filters out inappropriate information.

[0270] After the broadcast ends, the server collects viewing data and provides users with a visualized report. This report includes the number of viewers, time spent on the screen, engagement levels, and feedback from recipients. This makes it easy for users to identify areas for improvement for future broadcasts.

[0271] Regarding monetization, users select and configure suitable monetization strategies via their devices. Based on these settings, the server tracks and manages revenue information, such as ad placement, and reports regularly updated data to the user.

[0272] As a concrete example, when a user broadcasts an online cooking class, they enter "vegetarian recipes" as the broadcast theme. The server then optimizes the broadcast settings based on the user's camera resolution and internet speed, and creates a script using a generative AI model. It uses prompts such as "Generate a script for an online cooking class. The theme is 'vegetarian recipes'" to specify the content. This allows the user to deliver a broadcast that will interest viewers based on the script.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] Users access the platform, enter their personal information and distribution themes, and register. This involves entering information into an online form and clicking a submit button. The input data includes personal information (e.g., name, email address) and distribution themes. The server receives this input and registers it in its database. The distribution themes entered by the user form the basis for content generation.

[0276] Step 2:

[0277] The server scans the user's terminal environment. In this process, it collects device data such as the resolution of the camera, the audio quality of the microphone, and the network speed. Based on this data, calculations are performed to set the optimal bitrate and frame rate. Specifically, when the network speed is slow, the frame rate is decreased, and when a high-resolution camera is used, the bitrate is increased. As a result, the adjusted delivery settings are sent to the terminal.

[0278] Step 3:

[0279] After the user inputs a delivery theme, the server uses a generation AI model to automatically generate a script or scenario. The input for this process is the delivery theme previously set by the user. The generation AI model aggregates relevant information based on this theme and creates a script containing the flow of topics and specific content. The output is a script that can be used for delivery, which is sent to and displayed on the user terminal.

[0280] Step 4:

[0281] During the delivery, the server monitors and filters comments from viewers in real time. The input is the comment stream of the viewers. Using natural language processing technology, the comments are analyzed to identify inappropriate remarks and spam and immediately excluded. Also, important comments are notified to the user terminal. This enables the user to quickly interact with the viewers.

[0282] Step 5:

[0283] After the delivery ends, the server aggregates the viewing data and creates a visualized report. The input for this is delivery data such as the number of viewers, viewing time, and engagement level. Aggregation and analysis are performed to generate a report that visualizes the results as graphs and statistics. The output is a report indicating improvement points for the next delivery, which is sent to and provided to the user.

[0284] Step 6:

[0285] The user selects and sets a monetization model through the terminal. The input includes options related to monetization (e.g., types of advertisements, revenue distribution methods). Based on this, the server manages advertisement placement and product sales tracking, and updates and tracks revenue data in real time. The final output is a revenue report that is created periodically and provided to the user.

[0286] (Application Example 1)

[0287] 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".

[0288] In modern distribution services, in order for users to provide high-quality and attractive content, specialized knowledge and technology are often required. Also, a mechanism that efficiently monetizes while incorporating a high degree of interaction with viewers in real time is desired. This issue is a particularly large barrier for novice distributors and small-scale content producers operated by individuals. And often, the method of accurately grasping the reaction of viewers and applying it to subsequent distributions is not sufficient. To improve the above situation, the present invention is provided.

[0289] 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.

[0290] In this invention, the server includes means for automatically generating a content generation instruction using a generation algorithm based on information input from the user, means for scanning the information processing device environment of the distributor and automatically setting optimal distribution conditions, and means for sequentially auditing the reaction from the recipient during distribution and eliminating inappropriate content. Thereby, the distributor can perform high-quality distribution without relying on specialized technology, maintain smooth interaction with the audience, and achieve efficient monetization and improvement for subsequent distributions.

[0291] A "generation algorithm" is a method for automatically generating content instructions from information entered by the user.

[0292] The term "information processing device environment" refers to the state of the terminal used by the broadcaster and its connection environment.

[0293] "Distribution conditions" is a term that refers to the technical settings and adjustments required when distributing content.

[0294] "Reactions from recipients" refers to reactions such as comments and ratings made by viewers of the broadcast.

[0295] "Inappropriate content" refers to offensive, discriminatory, or spam messages that should be removed during the broadcast.

[0296] A "content generation instruction sheet" refers to an automatically generated outline or script that follows a given theme and is used as a reference during distribution.

[0297] The system for realizing this invention primarily uses a server, a user terminal, and a generation AI model. The server automatically creates content generation instructions using a generation algorithm based on information input from the user. The generated instructions are sent to the user's terminal and provided to the distributor.

[0298] The user's device scans the delivery environment and feeds back the optimal delivery conditions to the server. Based on this information, the server sets conditions suitable for the sender, enabling efficient delivery. Furthermore, during delivery, responses from recipients are audited in real time. This audit is essential to help eliminate inappropriate content and achieve better interaction.

[0299] The specific hardware is a smartphone, and the software uses OpenAI's GPT series as a generative AI model and the NLTK library for natural language processing. This allows users to leverage the generative AI model and efficiently provide scripts for smooth delivery.

[0300] For example, a user could choose "Live Cooking Show" as their theme and enter a text prompt like this: "The theme for the next live cooking show is Italian cuisine. The automatically generated script will start by showing how to make an appetizer, then move on to the main course. Please suggest some topic ideas." Based on this prompt, the generating AI model will provide a predetermined scenario to support the user's broadcast.

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

[0302] Step 1:

[0303] The user enters the distribution theme and personal information into their device. This input data is sent to the server, where the distribution purpose and user information are recorded in the database. The important point here is that the entered data forms the basis of subsequent automated generation processes.

[0304] Step 2:

[0305] The server receives data sent from the user's terminal and passes prompt messages to the generative AI model to generate a script. Specifically, it uses the generative AI model to generate content generation instructions that match the theme entered by the user. These prompt messages include specific instructions such as, "The theme for the next cooking live stream will be Italian cuisine."

[0306] Step 3:

[0307] Based on the content generation instruction received from the server, the terminal scans the current states of the camera, microphone, and network to determine the optimal delivery conditions. The input includes the hardware state of the terminal, and the output is the specific parameters required for the settings.

[0308] Step 4:

[0309] Based on the scan results, the server proposes the optimal delivery conditions to the user and automatically makes the necessary adjustments. The data processing performed here is to analyze the status information from the terminal and calculate the best bitrate and frame rate.

[0310] Step 5:

[0311] When the user starts the delivery, the server monitors the reactions from the viewers in real-time. By filtering inappropriate comments, it supports smooth delivery. The input includes the comments from the viewers, and the output is the filtered comment group.

[0312] Step 6:

[0313] After the delivery ends, the server collects and analyzes the viewing data. In this step, based on the collected data, it analyzes the trends of viewer behavior and summarizes the feedback for the next delivery. The output is a report including suggestions for improvement for the next delivery.

[0314] Step 7:

[0315] The user checks the feedback from the server and selects a monetization model. Based on the selected model, the server tracks the revenue data and manages the revenue situation in real-time. The input includes the selection information of the monetization model, and the output is the revenue and its report.

[0316] 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.

[0317] This invention enables users of a distribution platform to improve the quality of content by recognizing their emotional state. This facilitates smoother interaction with viewers and makes it possible to provide a more personalized experience. The following describes specific embodiments for carrying out this invention.

[0318] Users access the distribution platform and register. During this process, they enter personal information and distribution objectives, and, if necessary, select the option to enable the sentiment engine, thus preparing to use the sentiment recognition feature.

[0319] The server acquires the user's facial expressions and voice tone through the camera and microphone installed on the user's device. By analyzing this information in real time, the emotion engine can recognize the user's emotional state and use the results as feedback.

[0320] When a user inputs themes and related content to be delivered, the server uses a generation algorithm to automatically generate scripts and screenplays based on this information. During this process, feedback from an emotion engine can be incorporated, and suggestions can be included to help the user adjust the content based on their current emotions.

[0321] During the live stream, the server monitors viewer comments in real time, and inappropriate comments are filtered out using AI. Additionally, an emotion engine monitors the user's emotions and suggests actions based on their specific emotional state. For example, if tension is detected, it can suggest that the user take a break to relax.

[0322] After the broadcast, the server collects viewing and sentiment data and provides users with a detailed analysis report. This allows users to correlate changes in sentiment during the broadcast with viewer reactions and clearly identify areas for improvement for future broadcasts.

[0323] Furthermore, emotional data is applied to selected monetization models, used to optimize the timing and content of ad displays. This enables higher engagement and more effective monetization.

[0324] Thus, the present invention realizes multi-functional delivery support, including user emotion recognition, and supports the implementation of advanced delivery even if the user does not possess technical knowledge.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] Users access the distribution platform and create an account. They enter their personal information and distribution purpose, and enable the sentiment engine option as needed.

[0328] Step 2:

[0329] The server accesses the user's device and retrieves camera and microphone data. Based on this, it checks the performance of the peripherals being used and generates the optimal streaming settings.

[0330] Step 3:

[0331] The user enters the theme and keywords of the content to be distributed into their device. This information is sent to the server.

[0332] Step 4:

[0333] The server uses theme information received from the user to automatically generate scripts and screenplays through a generation algorithm. At this stage, the emotion engine analyzes the user's recent emotion data and fine-tunes the content based on that analysis.

[0334] Step 5:

[0335] As soon as streaming begins, the server monitors the user's facial expressions and tone of voice in real time. The emotion engine recognizes the emotional state from this data, and if, for example, tension or stress is detected, it notifies the user and offers suggestions for relaxation.

[0336] Step 6:

[0337] Simultaneously, the server monitors comments sent by viewers in real time and automatically filters out inappropriate content. This filtering is performed by AI, ensuring a safe viewing environment.

[0338] Step 7:

[0339] After the broadcast ends, the server aggregates the viewing and sentiment data accumulated during the broadcast and generates a detailed analysis report. This report takes into account the relationship between changes in sentiment and viewer reactions.

[0340] Step 8:

[0341] Users receive reports via their devices, allowing them to identify areas for improvement and effective strategies for future deliveries. This feedback includes analysis by an emotion engine, helping to develop more personalized delivery strategies.

[0342] Step 9:

[0343] Furthermore, from a monetization perspective, the emotion engine analyzes viewer emotion data to recommend optimal ad display timings and content. Based on this information, users can efficiently monetize their content.

[0344] (Example 2)

[0345] 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".

[0346] Providing an effective and personalized experience for viewers requires technical knowledge and a great deal of trial and error. Furthermore, traditional streaming systems lack concrete methods for understanding viewer emotions and reactions in real time and improving content quality. Additionally, data utilization to enhance monetization efficiency is insufficient.

[0347] 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.

[0348] In this invention, the server includes means for automatically generating components using a generation method based on information input from the user, means for detecting the sender's equipment environment and automatically proposing and setting the optimal transmission settings, and means for immediately monitoring the receiver's response during transmission and censoring inappropriate content. This allows the broadcaster to understand the audience's emotions in real time, thereby improving the quality of the content and achieving effective monetization.

[0349] A "user" is an entity that uses a system to input information and receive services and functions.

[0350] A "server" is a computer system that processes user input and provides various functions.

[0351] A "generation method" is an algorithm or process for automatically generating components based on information input by the user.

[0352] "Sender" refers to the individual or organization that distributes or sends information.

[0353] "Device environment" refers to the settings including the configuration and operating status of the devices and networks used by the sender.

[0354] "Inappropriate content" refers to information or comments that are undesirable or offensive to viewers or recipients.

[0355] "Censorship" is the process of excluding or hiding content that is deemed inappropriate based on specific criteria.

[0356] "Recipient" refers to an individual or group that receives information that has been distributed or transmitted.

[0357] "Emotional state" refers to the psychological state analyzed from the user's facial expressions, voice, and other factors.

[0358] "Monetization" refers to the methods and processes for generating financial profit through the provision of services or content.

[0359] This invention is a distribution support system using a server and terminals that can improve content quality and increase the efficiency of monetization through user emotion recognition. The following describes specific embodiments of the system.

[0360] Users first access the distribution platform using their own devices and enter the necessary personal information and distribution purpose. If they wish to enable the emotion recognition feature, they select a dedicated option. The device is equipped with a camera and microphone, which are used to capture the user's facial expressions and voice tone. This emotion data is then sent to the server and analyzed in real time.

[0361] The server uses an emotion engine to process data sent from the terminal and determine the user's emotional state. Based on this information, it utilizes a generative AI model to automatically generate scripts and screenplays that match the delivery theme entered by the user. The generated content reflects feedback based on the user's emotional state and includes suggestions for improving the quality of the content.

[0362] During the broadcast, the server monitors viewer comments in real time and uses AI filtering technology to censor inappropriate comments. Furthermore, the emotion engine continuously monitors the user's emotions and, if it detects a specific emotional state, suggests a concrete action, such as "suggesting a break to relax."

[0363] After the broadcast ends, the server collects viewing and sentiment data and generates a detailed analysis report. This allows users to analyze the relationship between changes in sentiment during the broadcast and viewer reactions, enabling them to identify areas for improvement for future broadcasts. Furthermore, sentiment data is used to optimize the monetization model, helping to adjust the timing and content of ad displays.

[0364] For example, if a user chooses "live cooking streaming" as their theme, the server can use a generative AI model to automatically generate a script using a chef template as source material. It can also analyze the user's emotional state and make adjustments, such as suggesting a calm tone of voice if the user is nervous.

[0365] Example of a prompt:

[0366] "Based on the user's current emotional state, please suggest a suitable way of speaking for a cooking commentary."

[0367] Thus, the present invention utilizes user emotion recognition to enable sophisticated delivery even without technical knowledge on the part of the user, and to provide personalized experiences to viewers.

[0368] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0369] Step 1:

[0370] Users access the distribution platform using their devices and enter their personal information and distribution purpose. This data is sent to the server, which stores the user's profile in a database and confirms the option to enable sentiment recognition. This process prepares the user's basic information and distribution-ready data.

[0371] Step 2:

[0372] The device activates its camera and microphone to capture the user's facial expressions and voice tone. This data is transmitted to the server in real time. The server analyzes this data using an emotion engine to recognize the user's emotional state. This output is used as feedback to generate the next content via a generative AI model.

[0373] Step 3:

[0374] The user inputs the theme and related content they wish to deliver into their device. The server uses a generative AI model to automatically generate scripts and screenplays based on the input theme. Based on the user's theme information and sentiment data as input data, the server generates content and outputs a script that includes suggestions tailored to the user's sentiment.

[0375] Step 4:

[0376] During the broadcast, the server monitors viewer comments in real time. An AI filtering system analyzes the incoming comment data and removes inappropriate content. This process maintains the appropriateness of comments and ensures the quality of the broadcast.

[0377] Step 5:

[0378] The server continuously monitors the user's emotions through an emotion engine. When a specific emotional state is detected, the server suggests an action to the user, such as "suggesting a break to relax." In this step, emotional data is used as input to output suggestions that are appropriate to the user's state.

[0379] Step 6:

[0380] After the broadcast ends, the server collects viewing and sentiment data. Based on this data, it generates a detailed analysis report and provides it to the user. The user uses this report as input to help improve future broadcasts. The output provides a list of areas for improvement based on viewer reactions and changes in sentiment.

[0381] Step 7:

[0382] The server optimizes the monetization model using sentiment data. It analyzes revenue data as input and adjusts the optimal timing and content of ad displays. In this step, based on data analysis, it outputs a monetization strategy to increase engagement.

[0383] (Application Example 2)

[0384] 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."

[0385] Modern content delivery requires flexible adjustment of content based on the user's emotional state and real-time feedback. However, conventional systems lack the functionality to recognize emotional states and reflect them in the content, making it difficult to improve the user experience. This invention aims to provide a personalized experience by recognizing the user's emotional state in real time and improving interaction with viewers.

[0386] 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.

[0387] In this invention, the server includes means for automatically generating documents and scripts using a generation method based on a theme input by the user; means for recognizing the broadcaster's electronic device and automatically suggesting and setting the optimal settings; and means for analyzing the user's emotional state in real time using an emotion recognition function and providing feedback to adjust the content and speech during broadcast. This enables the user to dynamically adjust content according to their emotional state and communicate effectively with viewers.

[0388] A "user" refers to an individual or organization that uses a content distribution platform to disseminate information or content.

[0389] A "theme" refers to the subject or purpose of the content that the user sets when distributing it.

[0390] "Generation method" refers to algorithms and technologies that automatically generate content based on input information.

[0391] A "document" is a text-based data file that is automatically generated by a generation method and includes scripts and other data intended for use during broadcast.

[0392] "Electronic devices" refers to a broad range of hardware, including digital devices and terminals used by users for distribution.

[0393] "Emotion recognition functionality" refers to technology that uses cameras and microphones to analyze a user's emotional state from their facial expressions and voice, and acquires the results as data.

[0394] "Real-time analysis" refers to a process where data is analyzed immediately upon acquisition, and the results are provided in a usable format.

[0395] "Feedback" refers to information and advice provided to users based on the results of emotion recognition, and is used to adjust the content and progress of the broadcast.

[0396] "Content" refers to all forms of expression, including information and media formats, distributed by users.

[0397] The system for implementing this invention enables smooth content generation and distribution when users utilize a distribution platform. The server and the user's terminal play key roles.

[0398] The server automatically generates documents and scripts based on themes entered by the user, using generation methods. It also provides emotion recognition capabilities, recognizing the user's emotions in real time through the user's electronic devices, such as smart glasses or smartphones, using their cameras and microphones. This emotion data is analyzed to provide feedback necessary for adjusting the content of the broadcast and spoken utterances. The server can utilize the aforementioned generation AI model.

[0399] The user's device automatically suggests and implements optimal delivery settings based on instructions from the server. Furthermore, it has the ability to monitor real-time information from viewers and filter out inappropriate content. It can also combine viewing data with sentiment analysis results and provide this information to the user in the form of a report.

[0400] As a concrete example, when a user is using smart glasses to stream, the device instantly analyzes their emotional state and provides feedback such as "Try taking a deep breath" if the result indicates they are feeling nervous. An example of a prompt accompanying this process would be, "The user is feeling nervous. Please suggest ways for her to relax."

[0401] Overall, this system enables users to adjust content appropriately based on their emotional state and engage in effective interaction with their audience.

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The user logs into the distribution platform and enters the distribution theme and related information. The input data is sent to the server. The server receives this information and uses it to initialize the generation method. This enables the generation of documents and scripts tailored to the user.

[0405] Step 2:

[0406] The server captures the user's facial expressions and voice in real time through the camera and microphone accessed from the user's electronic device. This serves as the input for emotional data. The server analyzes this data to identify the user's emotional state. Emotion recognition and generative AI models are used for the analysis. The output is data indicating the emotional state.

[0407] Step 3:

[0408] The server adjusts the generated script based on the emotion data obtained in step 2. During this process, it uses a generative AI model to generate feedback and suggestions tailored to the emotional state. This feedback is then presented to the user as a prompt. For example, if the user is feeling anxious, the server might generate a message such as "Try taking a deep breath" and send it to the user's device.

[0409] Step 4:

[0410] During the broadcast, the server monitors viewer comments and feedback in real time. Comments are sent to the server as input data and filtered to remove inappropriate content. The output is clean comment data. Prompts are adjusted as needed to facilitate smooth interaction with viewers.

[0411] Step 5:

[0412] After the broadcast ends, the server integrates and analyzes viewing data and sentiment data. This data processing allows for detailed analysis, including viewer reactions and changes in user sentiment. As output, a report is generated that includes suggestions for improvement for the next broadcast and is provided to the user. This process allows users to gain concrete insights for their next broadcast.

[0413] 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.

[0414] 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.

[0415] 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.

[0416] [Third Embodiment]

[0417] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0418] 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.

[0419] 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).

[0420] 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.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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.

[0426] 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.

[0427] 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.

[0428] 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".

[0429] The present invention is a system for enabling users to easily deliver high-quality content, and its embodiments are described below.

[0430] Users access the platform and register by first entering their personal information and the purpose of their distribution. This registration information forms the basis for generating content based on the distribution theme.

[0431] The server scans the user's terminal environment. During this process, it detects the camera, microphone, and network status, and generates optimal streaming settings based on this information. For example, the bitrate and frame rate are adjusted according to the resolution of the camera being used and the speed of the internet connection.

[0432] Next, when the user enters the theme for their broadcast, the server automatically generates a script or screenplay using a generation algorithm. This screenplay includes the topics to be covered and the flow of the scenario during the broadcast, which the user can then use as a basis for their broadcast.

[0433] During the live stream, the server monitors viewer comments in real time and immediately filters out inappropriate remarks and spam. This allows users to prevent problems and ensure a smooth live stream. Important comments are notified on the user's device, enabling them to respond quickly.

[0434] After the broadcast ends, the server analyzes the collected viewing data and provides users with a report. This report includes viewing statistics and viewer feedback, which can be used as a reference for future broadcasts.

[0435] Furthermore, users can select and configure monetization models through their devices. The server tracks and manages revenue data based on these settings and reports it to the user. For example, data on revenue from ad impressions and product purchases by viewers are updated in real time.

[0436] This provides users with a consistently supported environment, from pre-broadcast preparation and in-broadcast interaction to post-broadcast follow-up and monetization.

[0437] The following describes the processing flow.

[0438] Step 1:

[0439] Users access the distribution platform and register their personal information and distribution purpose. This information is sent to the server and used in subsequent steps.

[0440] Step 2:

[0441] The server scans the user's device environment to detect the resolution of the camera being used, the model number of the microphone, and the internet connection speed. Based on this information, it generates settings that suggest the optimal bitrate and frame rate for streaming.

[0442] Step 3:

[0443] Users enter the theme and related keywords they want to distribute and send them to the server.

[0444] Step 4:

[0445] The server automatically generates scripts and screenplays using a generation algorithm based on the input theme. This includes the flow of each scene, key points of the dialogue, and suggestions for visual materials.

[0446] Step 5:

[0447] Once the broadcast begins, the server monitors viewer comments in real time, and AI filtering immediately detects and removes inappropriate comments. Other comments are promptly forwarded to the user, allowing for uninterrupted responses.

[0448] Step 6:

[0449] After the broadcast ends, the server compiles the accumulated viewing data and analyzes viewing time, number of comments, engagement rate, etc. The analysis results are then fed back to the user in the form of a report.

[0450] Step 7:

[0451] Users select a monetization model and configure advertising and payment options through their device. The server tracks revenue data based on these settings and reports it to the user periodically, including, for example, ad views and sales performance.

[0452] This allows users to comprehensively manage all aspects of their streaming activities, promoting the delivery of high-quality content and monetization.

[0453] (Example 1)

[0454] 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."

[0455] In online streaming, there is a need for users to easily generate high-quality content, maintain smooth interaction with viewers, and maximize the effectiveness of the stream. However, with current technologies, optimizing the streaming environment and providing individual viewer feedback on content has been necessary, leading to increased user burden. Furthermore, limited monetization options have made sustainable streaming operations difficult.

[0456] 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.

[0457] In this invention, the server includes means for automatically generating content using a generation method based on information input by the user and the distribution theme; means for analyzing the user's device environment and automatically proposing and configuring appropriate distribution settings; and means for immediately monitoring responses from recipients during distribution and eliminating inappropriate information. As a result, the user is comprehensively supported from pre-distribution preparation to distribution management and post-distribution analysis, maximizing the effectiveness of distribution and enabling sustainable operation with expanded monetization options.

[0458] "User" refers to an entity that distributes content using a distribution platform, and can be an individual or an organization.

[0459] "Distribution theme" refers to information that describes the subject or purpose of the content a user distributes.

[0460] "Generation methods" refer to technologies that automatically construct and create content based on user input data.

[0461] "Device environment" refers to the environment including the hardware and software configuration used by the user.

[0462] "Streaming settings" refer to technical parameters such as bitrate, frame rate, and audio quality that are automatically adjusted to optimize streaming.

[0463] "Recipient" refers to the viewer who watches the content distributed by the user.

[0464] "Inappropriate information" refers to comments or reactions from viewers that may potentially hinder the purpose or quality of the broadcast.

[0465] This invention is a system that utilizes a distribution platform to help users easily deliver high-quality online broadcasts. Users access the platform, enter their personal information and broadcast theme, and register. This registration information forms the basis for content generation, and the server uses a generation method to automatically generate scripts and screenplays according to the broadcast content.

[0466] The server analyzes the user's device environment. Specifically, it collects data such as the resolution of the camera being used, the quality of the microphone, and the network speed, and automatically configures streaming settings that optimize the bitrate and frame rate based on this data. In addition, to ensure smooth interaction during streaming, it monitors viewer comments in real time and immediately filters out inappropriate information.

[0467] After the broadcast ends, the server collects viewing data and provides users with a visualized report. This report includes the number of viewers, time spent on the screen, engagement levels, and feedback from recipients. This makes it easy for users to identify areas for improvement for future broadcasts.

[0468] Regarding monetization, users select and configure suitable monetization strategies via their devices. Based on these settings, the server tracks and manages revenue information, such as ad placement, and reports regularly updated data to the user.

[0469] As a concrete example, when a user broadcasts an online cooking class, they enter "vegetarian recipes" as the broadcast theme. The server then optimizes the broadcast settings based on the user's camera resolution and internet speed, and creates a script using a generative AI model. It uses prompts such as "Generate a script for an online cooking class. The theme is 'vegetarian recipes'" to specify the content. This allows the user to deliver a broadcast that will interest viewers based on the script.

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Step 1:

[0472] Users access the platform, enter their personal information and distribution themes, and register. This involves entering information into an online form and clicking a submit button. The input data includes personal information (e.g., name, email address) and distribution themes. The server receives this input and registers it in its database. The distribution themes entered by the user form the basis for content generation.

[0473] Step 2:

[0474] The server scans the user's device environment. During this process, it collects device data such as camera resolution, microphone audio quality, and network speed. Based on this data, calculations are performed to set the optimal bitrate and frame rate. Specifically, if the network speed is slow, the frame rate is lowered; if a high-resolution camera is being used, the bitrate is increased. As a result, the adjusted streaming settings are sent to the device.

[0475] Step 3:

[0476] After the user enters a broadcast theme, the server automatically generates a script or screenplay using a generative AI model. The input for this process is the broadcast theme that the user has set in advance. Based on this theme, the generative AI model aggregates relevant information and creates a script that includes the flow of the topic and specific content. The output is a script that can be used for broadcasting, which is sent to the user's terminal and displayed.

[0477] Step 4:

[0478] During the broadcast, the server monitors and filters viewer comments in real time. The input is the viewer comment stream. Natural language processing technology is used to analyze the comments, identifying and immediately removing inappropriate remarks and spam. Important comments are also notified to the user's device. This allows users to quickly interact with viewers.

[0479] Step 5:

[0480] After the broadcast ends, the server collects viewing data and generates a visualized report. This input includes broadcast data such as the number of viewers, viewing time, and engagement level. The server performs aggregation and analysis, generating a report that visualizes the results as graphs and statistics. The output is a report outlining areas for improvement for the next broadcast, which is sent to and provided to the user.

[0481] Step 6:

[0482] Users select and configure monetization models through their devices. Inputs include monetization-related choices (e.g., ad types, revenue sharing methods). Based on this, the server manages ad placement and product sales tracking, updating and tracking revenue data in real time. The final output is a regularly generated revenue report, which is provided to the user.

[0483] (Application Example 1)

[0484] 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."

[0485] In modern streaming services, users often need specialized knowledge and skills to provide high-quality and engaging content. Furthermore, there is a demand for mechanisms that efficiently monetize content while incorporating sophisticated real-time interaction with viewers. This challenge is particularly significant for novice streamers and small-scale content creators operating independently. Moreover, methods for accurately understanding viewer reactions and using that feedback to improve future streams are often insufficient. This invention is provided to address these issues.

[0486] 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.

[0487] In this invention, the server includes means for automatically generating content generation instructions using a generation algorithm based on information input from the user, means for scanning the distributor's information processing device environment and automatically setting optimal distribution conditions, and means for sequentially auditing responses from recipients during distribution and eliminating inappropriate content. As a result, distributors can perform high-quality distribution without relying on specialized technical skills, maintain smooth interaction with the audience, and efficiently monetize and improve future distributions.

[0488] A "generation algorithm" is a method for automatically generating content instructions from information entered by the user.

[0489] The term "information processing device environment" refers to the state of the terminal used by the broadcaster and its connection environment.

[0490] "Distribution conditions" is a term that refers to the technical settings and adjustments required when distributing content.

[0491] "Reactions from recipients" refers to reactions such as comments and ratings made by viewers of the broadcast.

[0492] "Inappropriate content" refers to offensive, discriminatory, or spam messages that should be removed during the broadcast.

[0493] A "content generation instruction sheet" refers to an automatically generated outline or script that follows a given theme and is used as a reference during distribution.

[0494] The system for realizing this invention primarily uses a server, a user terminal, and a generation AI model. The server automatically creates content generation instructions using a generation algorithm based on information input from the user. The generated instructions are sent to the user's terminal and provided to the distributor.

[0495] The user's device scans the delivery environment and feeds back the optimal delivery conditions to the server. Based on this information, the server sets conditions suitable for the sender, enabling efficient delivery. Furthermore, during delivery, responses from recipients are audited in real time. This audit is essential to help eliminate inappropriate content and achieve better interaction.

[0496] The specific hardware is a smartphone, and the software uses OpenAI's GPT series as a generative AI model and the NLTK library for natural language processing. This allows users to leverage the generative AI model and efficiently provide scripts for smooth delivery.

[0497] For example, a user could choose "Live Cooking Show" as their theme and enter a text prompt like this: "The theme for the next live cooking show is Italian cuisine. The automatically generated script will start by showing how to make an appetizer, then move on to the main course. Please suggest some topic ideas." Based on this prompt, the generating AI model will provide a predetermined scenario to support the user's broadcast.

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] The user enters the distribution theme and personal information into their device. This input data is sent to the server, where the distribution purpose and user information are recorded in the database. The important point here is that the entered data forms the basis of subsequent automated generation processes.

[0501] Step 2:

[0502] The server receives data sent from the user's terminal and passes prompt messages to the generative AI model to generate a script. Specifically, it uses the generative AI model to generate content generation instructions that match the theme entered by the user. These prompt messages include specific instructions such as, "The theme for the next cooking live stream will be Italian cuisine."

[0503] Step 3:

[0504] The terminal scans the current camera, microphone, and network status based on the content generation instructions received from the server to determine the optimal delivery conditions. The input includes the terminal's hardware status, and the output consists of specific parameters required for configuration.

[0505] Step 4:

[0506] Based on the scan results, the server proposes optimal delivery conditions to the user and automatically makes any necessary adjustments. The data processing performed here involves analyzing status information from the terminal and calculating the best bitrate and frame rate.

[0507] Step 5:

[0508] Once a user starts streaming, the server monitors viewer reactions in real time. It supports smooth streaming by filtering out inappropriate comments. The input includes viewer comments, and the output is a filtered set of comments.

[0509] Step 6:

[0510] After the broadcast ends, the server collects and analyzes viewing data. In this step, trends in viewer behavior are analyzed based on the collected data, and feedback is compiled for the next broadcast. The output is a report that includes suggestions for improvement for the next broadcast.

[0511] Step 7:

[0512] The user reviews feedback from the server and selects a monetization model. Based on the selected model, the server tracks revenue data and manages revenue status in real time. Inputs include information on the selected monetization model, and outputs are revenue and its report.

[0513] 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.

[0514] This invention enables users of a distribution platform to improve the quality of content by recognizing their emotional state. This facilitates smoother interaction with viewers and makes it possible to provide a more personalized experience. The following describes specific embodiments for carrying out this invention.

[0515] Users access the distribution platform and register. During this process, they enter personal information and distribution objectives, and, if necessary, select the option to enable the sentiment engine, thus preparing to use the sentiment recognition feature.

[0516] The server acquires the user's facial expressions and voice tone through the camera and microphone installed on the user's device. By analyzing this information in real time, the emotion engine can recognize the user's emotional state and use the results as feedback.

[0517] When a user inputs themes and related content to be delivered, the server uses a generation algorithm to automatically generate scripts and screenplays based on this information. During this process, feedback from an emotion engine can be incorporated, and suggestions can be included to help the user adjust the content based on their current emotions.

[0518] During the live stream, the server monitors viewer comments in real time, and inappropriate comments are filtered out using AI. Additionally, an emotion engine monitors the user's emotions and suggests actions based on their specific emotional state. For example, if tension is detected, it can suggest that the user take a break to relax.

[0519] After the broadcast, the server collects viewing and sentiment data and provides users with a detailed analysis report. This allows users to correlate changes in sentiment during the broadcast with viewer reactions and clearly identify areas for improvement for future broadcasts.

[0520] Furthermore, emotional data is applied to selected monetization models, used to optimize the timing and content of ad displays. This enables higher engagement and more effective monetization.

[0521] Thus, the present invention realizes multi-functional delivery support, including user emotion recognition, and supports the implementation of advanced delivery even if the user does not possess technical knowledge.

[0522] The following describes the processing flow.

[0523] Step 1:

[0524] Users access the distribution platform and create an account. They enter their personal information and distribution purpose, and enable the sentiment engine option as needed.

[0525] Step 2:

[0526] The server accesses the user's device and retrieves camera and microphone data. Based on this, it checks the performance of the peripherals being used and generates the optimal streaming settings.

[0527] Step 3:

[0528] The user enters the theme and keywords of the content to be distributed into their device. This information is sent to the server.

[0529] Step 4:

[0530] The server uses theme information received from the user to automatically generate scripts and screenplays through a generation algorithm. At this stage, the emotion engine analyzes the user's recent emotion data and fine-tunes the content based on that analysis.

[0531] Step 5:

[0532] As soon as streaming begins, the server monitors the user's facial expressions and tone of voice in real time. The emotion engine recognizes the emotional state from this data, and if, for example, tension or stress is detected, it notifies the user and offers suggestions for relaxation.

[0533] Step 6:

[0534] Simultaneously, the server monitors comments sent by viewers in real time and automatically filters out inappropriate content. This filtering is performed by AI, ensuring a safe viewing environment.

[0535] Step 7:

[0536] After the broadcast ends, the server aggregates the viewing and sentiment data accumulated during the broadcast and generates a detailed analysis report. This report takes into account the relationship between changes in sentiment and viewer reactions.

[0537] Step 8:

[0538] Users receive reports via their devices, allowing them to identify areas for improvement and effective strategies for future deliveries. This feedback includes analysis by an emotion engine, helping to develop more personalized delivery strategies.

[0539] Step 9:

[0540] Furthermore, from a monetization perspective, the emotion engine analyzes viewer emotion data to recommend optimal ad display timings and content. Based on this information, users can efficiently monetize their content.

[0541] (Example 2)

[0542] 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."

[0543] Providing an effective and personalized experience for viewers requires technical knowledge and a great deal of trial and error. Furthermore, traditional streaming systems lack concrete methods for understanding viewer emotions and reactions in real time and improving content quality. Additionally, data utilization to enhance monetization efficiency is insufficient.

[0544] 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.

[0545] In this invention, the server includes means for automatically generating components using a generation method based on information input from the user, means for detecting the sender's equipment environment and automatically proposing and setting the optimal transmission settings, and means for immediately monitoring the receiver's response during transmission and censoring inappropriate content. This allows the broadcaster to understand the audience's emotions in real time, thereby improving the quality of the content and achieving effective monetization.

[0546] A "user" is an entity that uses a system to input information and receive services and functions.

[0547] A "server" is a computer system that processes user input and provides various functions.

[0548] A "generation method" is an algorithm or process for automatically generating components based on information input by the user.

[0549] "Sender" refers to the individual or organization that distributes or sends information.

[0550] "Device environment" refers to the settings including the configuration and operating status of the devices and networks used by the sender.

[0551] "Inappropriate content" refers to information or comments that are undesirable or offensive to viewers or recipients.

[0552] "Censorship" is the process of excluding or hiding content that is deemed inappropriate based on specific criteria.

[0553] "Recipient" refers to an individual or group that receives information that has been distributed or transmitted.

[0554] "Emotional state" refers to the psychological state analyzed from the user's facial expressions, voice, and other factors.

[0555] "Monetization" refers to the methods and processes for generating financial profit through the provision of services or content.

[0556] This invention is a distribution support system using a server and terminals that can improve content quality and increase the efficiency of monetization through user emotion recognition. The following describes specific embodiments of the system.

[0557] Users first access the distribution platform using their own devices and enter the necessary personal information and distribution purpose. If they wish to enable the emotion recognition feature, they select a dedicated option. The device is equipped with a camera and microphone, which are used to capture the user's facial expressions and voice tone. This emotion data is then sent to the server and analyzed in real time.

[0558] The server uses an emotion engine to process data sent from the terminal and determine the user's emotional state. Based on this information, it utilizes a generative AI model to automatically generate scripts and screenplays that match the delivery theme entered by the user. The generated content reflects feedback based on the user's emotional state and includes suggestions for improving the quality of the content.

[0559] During the broadcast, the server monitors viewer comments in real time and uses AI filtering technology to censor inappropriate comments. Furthermore, the emotion engine continuously monitors the user's emotions and, if it detects a specific emotional state, suggests a concrete action, such as "suggesting a break to relax."

[0560] After the broadcast ends, the server collects viewing and sentiment data and generates a detailed analysis report. This allows users to analyze the relationship between changes in sentiment during the broadcast and viewer reactions, enabling them to identify areas for improvement for future broadcasts. Furthermore, sentiment data is used to optimize the monetization model, helping to adjust the timing and content of ad displays.

[0561] For example, if a user chooses "live cooking streaming" as their theme, the server can use a generative AI model to automatically generate a script using a chef template as source material. It can also analyze the user's emotional state and make adjustments, such as suggesting a calm tone of voice if the user is nervous.

[0562] Example of a prompt:

[0563] "Based on the user's current emotional state, please suggest a suitable way of speaking for a cooking commentary."

[0564] Thus, the present invention utilizes user emotion recognition to enable sophisticated delivery even without technical knowledge on the part of the user, and to provide personalized experiences to viewers.

[0565] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0566] Step 1:

[0567] Users access the distribution platform using their devices and enter their personal information and distribution purpose. This data is sent to the server, which stores the user's profile in a database and confirms the option to enable sentiment recognition. This process prepares the user's basic information and distribution-ready data.

[0568] Step 2:

[0569] The device activates its camera and microphone to capture the user's facial expressions and voice tone. This data is transmitted to the server in real time. The server analyzes this data using an emotion engine to recognize the user's emotional state. This output is used as feedback to generate the next content via a generative AI model.

[0570] Step 3:

[0571] The user inputs the theme and related content they wish to deliver into their device. The server uses a generative AI model to automatically generate scripts and screenplays based on the input theme. Based on the user's theme information and sentiment data as input data, the server generates content and outputs a script that includes suggestions tailored to the user's sentiment.

[0572] Step 4:

[0573] During the broadcast, the server monitors viewer comments in real time. An AI filtering system analyzes the incoming comment data and removes inappropriate content. This process maintains the appropriateness of comments and ensures the quality of the broadcast.

[0574] Step 5:

[0575] The server continuously monitors the user's emotions through an emotion engine. When a specific emotional state is detected, the server suggests an action to the user, such as "suggesting a break to relax." In this step, emotional data is used as input to output suggestions that are appropriate to the user's state.

[0576] Step 6:

[0577] After the broadcast ends, the server collects viewing and sentiment data. Based on this data, it generates a detailed analysis report and provides it to the user. The user uses this report as input to help improve future broadcasts. The output provides a list of areas for improvement based on viewer reactions and changes in sentiment.

[0578] Step 7:

[0579] The server optimizes the monetization model using sentiment data. It analyzes revenue data as input and adjusts the optimal timing and content of ad displays. In this step, based on data analysis, it outputs a monetization strategy to increase engagement.

[0580] (Application Example 2)

[0581] 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."

[0582] Modern content delivery requires flexible adjustment of content based on the user's emotional state and real-time feedback. However, conventional systems lack the functionality to recognize emotional states and reflect them in the content, making it difficult to improve the user experience. This invention aims to provide a personalized experience by recognizing the user's emotional state in real time and improving interaction with viewers.

[0583] 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.

[0584] In this invention, the server includes means for automatically generating documents and scripts using a generation method based on a theme input by the user; means for recognizing the broadcaster's electronic device and automatically suggesting and setting the optimal settings; and means for analyzing the user's emotional state in real time using an emotion recognition function and providing feedback to adjust the content and speech during broadcast. This enables the user to dynamically adjust content according to their emotional state and communicate effectively with viewers.

[0585] A "user" refers to an individual or organization that uses a content distribution platform to disseminate information or content.

[0586] A "theme" refers to the subject or purpose of the content that the user sets when distributing it.

[0587] "Generation method" refers to algorithms and technologies that automatically generate content based on input information.

[0588] A "document" is a text-based data file that is automatically generated by a generation method and includes scripts and other data intended for use during broadcast.

[0589] "Electronic devices" refers to a broad range of hardware, including digital devices and terminals used by users for distribution.

[0590] "Emotion recognition functionality" refers to technology that uses cameras and microphones to analyze a user's emotional state from their facial expressions and voice, and acquires the results as data.

[0591] "Real-time analysis" refers to a process where data is analyzed immediately upon acquisition, and the results are provided in a usable format.

[0592] "Feedback" refers to information and advice provided to users based on the results of emotion recognition, and is used to adjust the content and progress of the broadcast.

[0593] "Content" refers to all forms of expression, including information and media formats, distributed by users.

[0594] The system for implementing this invention enables smooth content generation and distribution when users utilize a distribution platform. The server and the user's terminal play key roles.

[0595] The server automatically generates documents and scripts based on themes entered by the user, using generation methods. It also provides emotion recognition capabilities, recognizing the user's emotions in real time through the user's electronic devices, such as smart glasses or smartphones, using their cameras and microphones. This emotion data is analyzed to provide feedback necessary for adjusting the content of the broadcast and spoken utterances. The server can utilize the aforementioned generation AI model.

[0596] The user's device automatically suggests and implements optimal delivery settings based on instructions from the server. Furthermore, it has the ability to monitor real-time information from viewers and filter out inappropriate content. It can also combine viewing data with sentiment analysis results and provide this information to the user in the form of a report.

[0597] As a concrete example, when a user is using smart glasses to stream, the device instantly analyzes their emotional state and provides feedback such as "Try taking a deep breath" if the result indicates they are feeling nervous. An example of a prompt accompanying this process would be, "The user is feeling nervous. Please suggest ways for her to relax."

[0598] Overall, this system enables users to adjust content appropriately based on their emotional state and engage in effective interaction with their audience.

[0599] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0600] Step 1:

[0601] The user logs into the distribution platform and enters the distribution theme and related information. The input data is sent to the server. The server receives this information and uses it to initialize the generation method. This enables the generation of documents and scripts tailored to the user.

[0602] Step 2:

[0603] The server captures the user's facial expressions and voice in real time through the camera and microphone accessed from the user's electronic device. This serves as the input for emotional data. The server analyzes this data to identify the user's emotional state. Emotion recognition and generative AI models are used for the analysis. The output is data indicating the emotional state.

[0604] Step 3:

[0605] The server adjusts the generated script based on the emotion data obtained in step 2. During this process, it uses a generative AI model to generate feedback and suggestions tailored to the emotional state. This feedback is then presented to the user as a prompt. For example, if the user is feeling anxious, the server might generate a message such as "Try taking a deep breath" and send it to the user's device.

[0606] Step 4:

[0607] During the broadcast, the server monitors viewer comments and feedback in real time. Comments are sent to the server as input data and filtered to remove inappropriate content. The output is clean comment data. Prompts are adjusted as needed to facilitate smooth interaction with viewers.

[0608] Step 5:

[0609] After the broadcast ends, the server integrates and analyzes viewing data and sentiment data. This data processing allows for detailed analysis, including viewer reactions and changes in user sentiment. As output, a report is generated that includes suggestions for improvement for the next broadcast and is provided to the user. This process allows users to gain concrete insights for their next broadcast.

[0610] 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.

[0611] 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.

[0612] 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.

[0613] [Fourth Embodiment]

[0614] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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).

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] 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.

[0625] 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.

[0626] 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".

[0627] The present invention is a system for enabling users to easily deliver high-quality content, and its embodiments are described below.

[0628] Users access the platform and register by first entering their personal information and the purpose of their distribution. This registration information forms the basis for generating content based on the distribution theme.

[0629] The server scans the user's terminal environment. During this process, it detects the camera, microphone, and network status, and generates optimal streaming settings based on this information. For example, the bitrate and frame rate are adjusted according to the resolution of the camera being used and the speed of the internet connection.

[0630] Next, when the user enters the theme for their broadcast, the server automatically generates a script or screenplay using a generation algorithm. This screenplay includes the topics to be covered and the flow of the scenario during the broadcast, which the user can then use as a basis for their broadcast.

[0631] During the live stream, the server monitors viewer comments in real time and immediately filters out inappropriate remarks and spam. This allows users to prevent problems and ensure a smooth live stream. Important comments are notified on the user's device, enabling them to respond quickly.

[0632] After the broadcast ends, the server analyzes the collected viewing data and provides users with a report. This report includes viewing statistics and viewer feedback, which can be used as a reference for future broadcasts.

[0633] Furthermore, users can select and configure monetization models through their devices. The server tracks and manages revenue data based on these settings and reports it to the user. For example, data on revenue from ad impressions and product purchases by viewers are updated in real time.

[0634] This provides users with a consistently supported environment, from pre-broadcast preparation and in-broadcast interaction to post-broadcast follow-up and monetization.

[0635] The following describes the processing flow.

[0636] Step 1:

[0637] Users access the distribution platform and register their personal information and distribution purpose. This information is sent to the server and used in subsequent steps.

[0638] Step 2:

[0639] The server scans the user's device environment to detect the resolution of the camera being used, the model number of the microphone, and the internet connection speed. Based on this information, it generates settings that suggest the optimal bitrate and frame rate for streaming.

[0640] Step 3:

[0641] Users enter the theme and related keywords they want to distribute and send them to the server.

[0642] Step 4:

[0643] The server automatically generates scripts and screenplays using a generation algorithm based on the input theme. This includes the flow of each scene, key points of the dialogue, and suggestions for visual materials.

[0644] Step 5:

[0645] Once the broadcast begins, the server monitors viewer comments in real time, and AI filtering immediately detects and removes inappropriate comments. Other comments are promptly forwarded to the user, allowing for uninterrupted responses.

[0646] Step 6:

[0647] After the broadcast ends, the server compiles the accumulated viewing data and analyzes viewing time, number of comments, engagement rate, etc. The analysis results are then fed back to the user in the form of a report.

[0648] Step 7:

[0649] Users select a monetization model and configure advertising and payment options through their device. The server tracks revenue data based on these settings and reports it to the user periodically, including, for example, ad views and sales performance.

[0650] This allows users to comprehensively manage all aspects of their streaming activities, promoting the delivery of high-quality content and monetization.

[0651] (Example 1)

[0652] 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".

[0653] In online streaming, there is a need for users to easily generate high-quality content, maintain smooth interaction with viewers, and maximize the effectiveness of the stream. However, with current technologies, optimizing the streaming environment and providing individual viewer feedback on content has been necessary, leading to increased user burden. Furthermore, limited monetization options have made sustainable streaming operations difficult.

[0654] 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.

[0655] In this invention, the server includes means for automatically generating content using a generation method based on information input by the user and the distribution theme; means for analyzing the user's device environment and automatically proposing and configuring appropriate distribution settings; and means for immediately monitoring responses from recipients during distribution and eliminating inappropriate information. As a result, the user is comprehensively supported from pre-distribution preparation to distribution management and post-distribution analysis, maximizing the effectiveness of distribution and enabling sustainable operation with expanded monetization options.

[0656] "User" refers to an entity that distributes content using a distribution platform, and can be an individual or an organization.

[0657] "Distribution theme" refers to information that describes the subject or purpose of the content a user distributes.

[0658] "Generation methods" refer to technologies that automatically construct and create content based on user input data.

[0659] "Device environment" refers to the environment including the hardware and software configuration used by the user.

[0660] "Streaming settings" refer to technical parameters such as bitrate, frame rate, and audio quality that are automatically adjusted to optimize streaming.

[0661] "Recipient" refers to the viewer who watches the content distributed by the user.

[0662] "Inappropriate information" refers to comments or reactions from viewers that may potentially hinder the purpose or quality of the broadcast.

[0663] This invention is a system that utilizes a distribution platform to help users easily deliver high-quality online broadcasts. Users access the platform, enter their personal information and broadcast theme, and register. This registration information forms the basis for content generation, and the server uses a generation method to automatically generate scripts and screenplays according to the broadcast content.

[0664] The server analyzes the user's device environment. Specifically, it collects data such as the resolution of the camera being used, the quality of the microphone, and the network speed, and automatically configures streaming settings that optimize the bitrate and frame rate based on this data. In addition, to ensure smooth interaction during streaming, it monitors viewer comments in real time and immediately filters out inappropriate information.

[0665] After the broadcast ends, the server collects viewing data and provides users with a visualized report. This report includes the number of viewers, time spent on the screen, engagement levels, and feedback from recipients. This makes it easy for users to identify areas for improvement for future broadcasts.

[0666] Regarding monetization, users select and configure suitable monetization strategies via their devices. Based on these settings, the server tracks and manages revenue information, such as ad placement, and reports regularly updated data to the user.

[0667] As a concrete example, when a user broadcasts an online cooking class, they enter "vegetarian recipes" as the broadcast theme. The server then optimizes the broadcast settings based on the user's camera resolution and internet speed, and creates a script using a generative AI model. It uses prompts such as "Generate a script for an online cooking class. The theme is 'vegetarian recipes'" to specify the content. This allows the user to deliver a broadcast that will interest viewers based on the script.

[0668] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0669] Step 1:

[0670] Users access the platform, enter their personal information and distribution themes, and register. This involves entering information into an online form and clicking a submit button. The input data includes personal information (e.g., name, email address) and distribution themes. The server receives this input and registers it in its database. The distribution themes entered by the user form the basis for content generation.

[0671] Step 2:

[0672] The server scans the user's device environment. During this process, it collects device data such as camera resolution, microphone audio quality, and network speed. Based on this data, calculations are performed to set the optimal bitrate and frame rate. Specifically, if the network speed is slow, the frame rate is lowered; if a high-resolution camera is being used, the bitrate is increased. As a result, the adjusted streaming settings are sent to the device.

[0673] Step 3:

[0674] After the user enters a broadcast theme, the server automatically generates a script or screenplay using a generative AI model. The input for this process is the broadcast theme that the user has set in advance. Based on this theme, the generative AI model aggregates relevant information and creates a script that includes the flow of the topic and specific content. The output is a script that can be used for broadcasting, which is sent to the user's terminal and displayed.

[0675] Step 4:

[0676] During the broadcast, the server monitors and filters viewer comments in real time. The input is the viewer comment stream. Natural language processing technology is used to analyze the comments, identifying and immediately removing inappropriate remarks and spam. Important comments are also notified to the user's device. This allows users to quickly interact with viewers.

[0677] Step 5:

[0678] After the broadcast ends, the server collects viewing data and generates a visualized report. This input includes broadcast data such as the number of viewers, viewing time, and engagement level. The server performs aggregation and analysis, generating a report that visualizes the results as graphs and statistics. The output is a report outlining areas for improvement for the next broadcast, which is sent to and provided to the user.

[0679] Step 6:

[0680] Users select and configure monetization models through their devices. Inputs include monetization-related choices (e.g., ad types, revenue sharing methods). Based on this, the server manages ad placement and product sales tracking, updating and tracking revenue data in real time. The final output is a regularly generated revenue report, which is provided to the user.

[0681] (Application Example 1)

[0682] 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".

[0683] In modern streaming services, users often need specialized knowledge and skills to provide high-quality and engaging content. Furthermore, there is a demand for mechanisms that efficiently monetize content while incorporating sophisticated real-time interaction with viewers. This challenge is particularly significant for novice streamers and small-scale content creators operating independently. Moreover, methods for accurately understanding viewer reactions and using that feedback to improve future streams are often insufficient. This invention is provided to address these issues.

[0684] 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.

[0685] In this invention, the server includes means for automatically generating content generation instructions using a generation algorithm based on information input from the user, means for scanning the distributor's information processing device environment and automatically setting optimal distribution conditions, and means for sequentially auditing responses from recipients during distribution and eliminating inappropriate content. As a result, distributors can perform high-quality distribution without relying on specialized technical skills, maintain smooth interaction with the audience, and efficiently monetize and improve future distributions.

[0686] A "generation algorithm" is a method for automatically generating content instructions from information entered by the user.

[0687] The term "information processing device environment" refers to the state of the terminal used by the broadcaster and its connection environment.

[0688] "Distribution conditions" is a term that refers to the technical settings and adjustments required when distributing content.

[0689] "Reactions from recipients" refers to reactions such as comments and ratings made by viewers of the broadcast.

[0690] "Inappropriate content" refers to offensive, discriminatory, or spam messages that should be removed during the broadcast.

[0691] A "content generation instruction sheet" refers to an automatically generated outline or script that follows a given theme and is used as a reference during distribution.

[0692] The system for realizing this invention primarily uses a server, a user terminal, and a generation AI model. The server automatically creates content generation instructions using a generation algorithm based on information input from the user. The generated instructions are sent to the user's terminal and provided to the distributor.

[0693] The user's device scans the delivery environment and feeds back the optimal delivery conditions to the server. Based on this information, the server sets conditions suitable for the sender, enabling efficient delivery. Furthermore, during delivery, responses from recipients are audited in real time. This audit is essential to help eliminate inappropriate content and achieve better interaction.

[0694] The specific hardware is a smartphone, and the software uses OpenAI's GPT series as a generative AI model and the NLTK library for natural language processing. This allows users to leverage the generative AI model and efficiently provide scripts for smooth delivery.

[0695] For example, a user could choose "Live Cooking Show" as their theme and enter a text prompt like this: "The theme for the next live cooking show is Italian cuisine. The automatically generated script will start by showing how to make an appetizer, then move on to the main course. Please suggest some topic ideas." Based on this prompt, the generating AI model will provide a predetermined scenario to support the user's broadcast.

[0696] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0697] Step 1:

[0698] The user enters the distribution theme and personal information into their device. This input data is sent to the server, where the distribution purpose and user information are recorded in the database. The important point here is that the entered data forms the basis of subsequent automated generation processes.

[0699] Step 2:

[0700] The server receives data sent from the user's terminal and passes prompt messages to the generative AI model to generate a script. Specifically, it uses the generative AI model to generate content generation instructions that match the theme entered by the user. These prompt messages include specific instructions such as, "The theme for the next cooking live stream will be Italian cuisine."

[0701] Step 3:

[0702] The terminal scans the current camera, microphone, and network status based on the content generation instructions received from the server to determine the optimal delivery conditions. The input includes the terminal's hardware status, and the output consists of specific parameters required for configuration.

[0703] Step 4:

[0704] Based on the scan results, the server proposes optimal delivery conditions to the user and automatically makes any necessary adjustments. The data processing performed here involves analyzing status information from the terminal and calculating the best bitrate and frame rate.

[0705] Step 5:

[0706] Once a user starts streaming, the server monitors viewer reactions in real time. It supports smooth streaming by filtering out inappropriate comments. The input includes viewer comments, and the output is a filtered set of comments.

[0707] Step 6:

[0708] After the broadcast ends, the server collects and analyzes viewing data. In this step, trends in viewer behavior are analyzed based on the collected data, and feedback is compiled for the next broadcast. The output is a report that includes suggestions for improvement for the next broadcast.

[0709] Step 7:

[0710] The user reviews feedback from the server and selects a monetization model. Based on the selected model, the server tracks revenue data and manages revenue status in real time. Inputs include information on the selected monetization model, and outputs are revenue and its report.

[0711] 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.

[0712] This invention enables users of a distribution platform to improve the quality of content by recognizing their emotional state. This facilitates smoother interaction with viewers and makes it possible to provide a more personalized experience. The following describes specific embodiments for carrying out this invention.

[0713] Users access the distribution platform and register. During this process, they enter personal information and distribution objectives, and, if necessary, select the option to enable the sentiment engine, thus preparing to use the sentiment recognition feature.

[0714] The server acquires the user's facial expressions and voice tone through the camera and microphone installed on the user's device. By analyzing this information in real time, the emotion engine can recognize the user's emotional state and use the results as feedback.

[0715] When a user inputs themes and related content to be delivered, the server uses a generation algorithm to automatically generate scripts and screenplays based on this information. During this process, feedback from an emotion engine can be incorporated, and suggestions can be included to help the user adjust the content based on their current emotions.

[0716] During the live stream, the server monitors viewer comments in real time, and inappropriate comments are filtered out using AI. Additionally, an emotion engine monitors the user's emotions and suggests actions based on their specific emotional state. For example, if tension is detected, it can suggest that the user take a break to relax.

[0717] After the broadcast, the server collects viewing and sentiment data and provides users with a detailed analysis report. This allows users to correlate changes in sentiment during the broadcast with viewer reactions and clearly identify areas for improvement for future broadcasts.

[0718] Furthermore, emotional data is applied to selected monetization models, used to optimize the timing and content of ad displays. This enables higher engagement and more effective monetization.

[0719] Thus, the present invention realizes multi-functional delivery support, including user emotion recognition, and supports the implementation of advanced delivery even if the user does not possess technical knowledge.

[0720] The following describes the processing flow.

[0721] Step 1:

[0722] Users access the distribution platform and create an account. They enter their personal information and distribution purpose, and enable the sentiment engine option as needed.

[0723] Step 2:

[0724] The server accesses the user's device and retrieves camera and microphone data. Based on this, it checks the performance of the peripherals being used and generates the optimal streaming settings.

[0725] Step 3:

[0726] The user enters the theme and keywords of the content to be distributed into their device. This information is sent to the server.

[0727] Step 4:

[0728] The server uses theme information received from the user to automatically generate scripts and screenplays through a generation algorithm. At this stage, the emotion engine analyzes the user's recent emotion data and fine-tunes the content based on that analysis.

[0729] Step 5:

[0730] As soon as streaming begins, the server monitors the user's facial expressions and tone of voice in real time. The emotion engine recognizes the emotional state from this data, and if, for example, tension or stress is detected, it notifies the user and offers suggestions for relaxation.

[0731] Step 6:

[0732] Simultaneously, the server monitors comments sent by viewers in real time and automatically filters out inappropriate content. This filtering is performed by AI, ensuring a safe viewing environment.

[0733] Step 7:

[0734] After the broadcast ends, the server aggregates the viewing and sentiment data accumulated during the broadcast and generates a detailed analysis report. This report takes into account the relationship between changes in sentiment and viewer reactions.

[0735] Step 8:

[0736] Users receive reports via their devices, allowing them to identify areas for improvement and effective strategies for future deliveries. This feedback includes analysis by an emotion engine, helping to develop more personalized delivery strategies.

[0737] Step 9:

[0738] Furthermore, from a monetization perspective, the emotion engine analyzes viewer emotion data to recommend optimal ad display timings and content. Based on this information, users can efficiently monetize their content.

[0739] (Example 2)

[0740] 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".

[0741] Providing an effective and personalized experience for viewers requires technical knowledge and a great deal of trial and error. Furthermore, traditional streaming systems lack concrete methods for understanding viewer emotions and reactions in real time and improving content quality. Additionally, data utilization to enhance monetization efficiency is insufficient.

[0742] 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.

[0743] In this invention, the server includes means for automatically generating components using a generation method based on information input from the user, means for detecting the sender's equipment environment and automatically proposing and setting the optimal transmission settings, and means for immediately monitoring the receiver's response during transmission and censoring inappropriate content. This allows the broadcaster to understand the audience's emotions in real time, thereby improving the quality of the content and achieving effective monetization.

[0744] A "user" is an entity that uses a system to input information and receive services and functions.

[0745] A "server" is a computer system that processes user input and provides various functions.

[0746] A "generation method" is an algorithm or process for automatically generating components based on information input by the user.

[0747] "Sender" refers to the individual or organization that distributes or sends information.

[0748] "Device environment" refers to the settings including the configuration and operating status of the devices and networks used by the sender.

[0749] "Inappropriate content" refers to information or comments that are undesirable or offensive to viewers or recipients.

[0750] "Censorship" is the process of excluding or hiding content that is deemed inappropriate based on specific criteria.

[0751] "Recipient" refers to an individual or group that receives information that has been distributed or transmitted.

[0752] "Emotional state" refers to the psychological state analyzed from the user's facial expressions, voice, and other factors.

[0753] "Monetization" refers to the methods and processes for generating financial profit through the provision of services or content.

[0754] This invention is a distribution support system using a server and terminals that can improve content quality and increase the efficiency of monetization through user emotion recognition. The following describes specific embodiments of the system.

[0755] Users first access the distribution platform using their own devices and enter the necessary personal information and distribution purpose. If they wish to enable the emotion recognition feature, they select a dedicated option. The device is equipped with a camera and microphone, which are used to capture the user's facial expressions and voice tone. This emotion data is then sent to the server and analyzed in real time.

[0756] The server uses an emotion engine to process data sent from the terminal and determine the user's emotional state. Based on this information, it utilizes a generative AI model to automatically generate scripts and screenplays that match the delivery theme entered by the user. The generated content reflects feedback based on the user's emotional state and includes suggestions for improving the quality of the content.

[0757] During the broadcast, the server monitors viewer comments in real time and uses AI filtering technology to censor inappropriate comments. Furthermore, the emotion engine continuously monitors the user's emotions and, if it detects a specific emotional state, suggests a concrete action, such as "suggesting a break to relax."

[0758] After the broadcast ends, the server collects viewing and sentiment data and generates a detailed analysis report. This allows users to analyze the relationship between changes in sentiment during the broadcast and viewer reactions, enabling them to identify areas for improvement for future broadcasts. Furthermore, sentiment data is used to optimize the monetization model, helping to adjust the timing and content of ad displays.

[0759] For example, if a user chooses "live cooking streaming" as their theme, the server can use a generative AI model to automatically generate a script using a chef template as source material. It can also analyze the user's emotional state and make adjustments, such as suggesting a calm tone of voice if the user is nervous.

[0760] Example of a prompt:

[0761] "Based on the user's current emotional state, please suggest a suitable way of speaking for a cooking commentary."

[0762] Thus, the present invention utilizes user emotion recognition to enable sophisticated delivery even without technical knowledge on the part of the user, and to provide personalized experiences to viewers.

[0763] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0764] Step 1:

[0765] Users access the distribution platform using their devices and enter their personal information and distribution purpose. This data is sent to the server, which stores the user's profile in a database and confirms the option to enable sentiment recognition. This process prepares the user's basic information and distribution-ready data.

[0766] Step 2:

[0767] The device activates its camera and microphone to capture the user's facial expressions and voice tone. This data is transmitted to the server in real time. The server analyzes this data using an emotion engine to recognize the user's emotional state. This output is used as feedback to generate the next content via a generative AI model.

[0768] Step 3:

[0769] The user inputs the theme and related content they wish to deliver into their device. The server uses a generative AI model to automatically generate scripts and screenplays based on the input theme. Based on the user's theme information and sentiment data as input data, the server generates content and outputs a script that includes suggestions tailored to the user's sentiment.

[0770] Step 4:

[0771] During the broadcast, the server monitors viewer comments in real time. An AI filtering system analyzes the incoming comment data and removes inappropriate content. This process maintains the appropriateness of comments and ensures the quality of the broadcast.

[0772] Step 5:

[0773] The server continuously monitors the user's emotions through an emotion engine. When a specific emotional state is detected, the server suggests an action to the user, such as "suggesting a break to relax." In this step, emotional data is used as input to output suggestions that are appropriate to the user's state.

[0774] Step 6:

[0775] After the broadcast ends, the server collects viewing and sentiment data. Based on this data, it generates a detailed analysis report and provides it to the user. The user uses this report as input to help improve future broadcasts. The output provides a list of areas for improvement based on viewer reactions and changes in sentiment.

[0776] Step 7:

[0777] The server optimizes the monetization model using sentiment data. It analyzes revenue data as input and adjusts the optimal timing and content of ad displays. In this step, based on data analysis, it outputs a monetization strategy to increase engagement.

[0778] (Application Example 2)

[0779] 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".

[0780] Modern content delivery requires flexible adjustment of content based on the user's emotional state and real-time feedback. However, conventional systems lack the functionality to recognize emotional states and reflect them in the content, making it difficult to improve the user experience. This invention aims to provide a personalized experience by recognizing the user's emotional state in real time and improving interaction with viewers.

[0781] 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.

[0782] In this invention, the server includes means for automatically generating documents and scripts using a generation method based on a theme input by the user; means for recognizing the broadcaster's electronic device and automatically suggesting and setting the optimal settings; and means for analyzing the user's emotional state in real time using an emotion recognition function and providing feedback to adjust the content and speech during broadcast. This enables the user to dynamically adjust content according to their emotional state and communicate effectively with viewers.

[0783] A "user" refers to an individual or organization that uses a content distribution platform to disseminate information or content.

[0784] A "theme" refers to the subject or purpose of the content that the user sets when distributing it.

[0785] "Generation method" refers to algorithms and technologies that automatically generate content based on input information.

[0786] A "document" is a text-based data file that is automatically generated by a generation method and includes scripts and other data intended for use during broadcast.

[0787] "Electronic devices" refers to a broad range of hardware, including digital devices and terminals used by users for distribution.

[0788] "Emotion recognition functionality" refers to technology that uses cameras and microphones to analyze a user's emotional state from their facial expressions and voice, and acquires the results as data.

[0789] "Real-time analysis" refers to a process where data is analyzed immediately upon acquisition, and the results are provided in a usable format.

[0790] "Feedback" refers to information and advice provided to users based on the results of emotion recognition, and is used to adjust the content and progress of the broadcast.

[0791] "Content" refers to all forms of expression, including information and media formats, distributed by users.

[0792] The system for implementing this invention enables smooth content generation and distribution when users utilize a distribution platform. The server and the user's terminal play key roles.

[0793] The server automatically generates documents and scripts based on themes entered by the user, using generation methods. It also provides emotion recognition capabilities, recognizing the user's emotions in real time through the user's electronic devices, such as smart glasses or smartphones, using their cameras and microphones. This emotion data is analyzed to provide feedback necessary for adjusting the content of the broadcast and spoken utterances. The server can utilize the aforementioned generation AI model.

[0794] The user's device automatically suggests and implements optimal delivery settings based on instructions from the server. Furthermore, it has the ability to monitor real-time information from viewers and filter out inappropriate content. It can also combine viewing data with sentiment analysis results and provide this information to the user in the form of a report.

[0795] As a concrete example, when a user is using smart glasses to stream, the device instantly analyzes their emotional state and provides feedback such as "Try taking a deep breath" if the result indicates they are feeling nervous. An example of a prompt accompanying this process would be, "The user is feeling nervous. Please suggest ways for her to relax."

[0796] Overall, this system enables users to adjust content appropriately based on their emotional state and engage in effective interaction with their audience.

[0797] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0798] Step 1:

[0799] The user logs into the distribution platform and enters the distribution theme and related information. The input data is sent to the server. The server receives this information and uses it to initialize the generation method. This enables the generation of documents and scripts tailored to the user.

[0800] Step 2:

[0801] The server captures the user's facial expressions and voice in real time through the camera and microphone accessed from the user's electronic device. This serves as the input for emotional data. The server analyzes this data to identify the user's emotional state. Emotion recognition and generative AI models are used for the analysis. The output is data indicating the emotional state.

[0802] Step 3:

[0803] The server adjusts the generated script based on the emotion data obtained in step 2. During this process, it uses a generative AI model to generate feedback and suggestions tailored to the emotional state. This feedback is then presented to the user as a prompt. For example, if the user is feeling anxious, the server might generate a message such as "Try taking a deep breath" and send it to the user's device.

[0804] Step 4:

[0805] During the broadcast, the server monitors viewer comments and feedback in real time. Comments are sent to the server as input data and filtered to remove inappropriate content. The output is clean comment data. Prompts are adjusted as needed to facilitate smooth interaction with viewers.

[0806] Step 5:

[0807] After the broadcast ends, the server integrates and analyzes viewing data and sentiment data. This data processing allows for detailed analysis, including viewer reactions and changes in user sentiment. As output, a report is generated that includes suggestions for improvement for the next broadcast and is provided to the user. This process allows users to gain concrete insights for their next broadcast.

[0808] 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.

[0809] 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.

[0810] 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 robot 414.

[0811] 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.

[0812] 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.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] 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."

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] The following is further disclosed regarding the embodiments described above.

[0830] (Claim 1)

[0831] A means of automatically generating scripts and other materials using a generation algorithm based on the distribution theme entered by the user,

[0832] A means to scan the broadcaster's device environment and automatically suggest and configure the optimal broadcast settings,

[0833] A means to monitor viewer comments in real time during the broadcast and filter out inappropriate content,

[0834] A means of collecting and analyzing viewing data after the broadcast and providing viewer feedback as a report,

[0835] A means to select and configure content monetization models, and to track and manage revenue data.

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, characterized in that the distribution method optimizes the generation algorithm and distribution setting means by having the distribution method provider register personal information and distribution purpose.

[0839] (Claim 3)

[0840] The system according to claim 1, characterized in that it has a function to automatically suggest improvements for the next broadcast based on an analysis of viewer behavior.

[0841] "Example 1"

[0842] (Claim 1)

[0843] A means for automatically generating content using a generation method based on information entered by the user and the distribution theme,

[0844] A means for analyzing the user's device environment and automatically suggesting and configuring appropriate distribution settings,

[0845] A means to immediately monitor recipient reactions during broadcast and filter out inappropriate information,

[0846] A means of collecting and analyzing data after the distribution ends and providing feedback from recipients as a report,

[0847] A means to select and configure content monetization strategies, and to track and manage revenue information,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, characterized in that the generation method and distribution setting means are optimized by the user registering personal data and distribution goals.

[0851] (Claim 3)

[0852] The system according to claim 1, characterized in that it has a function to automatically suggest improvements for the next delivery based on the behavioral analysis of the recipient.

[0853] "Application Example 1"

[0854] (Claim 1)

[0855] A means for automatically generating content generation instructions using a generation algorithm based on information entered by the user,

[0856] A means for scanning the information processing environment of a broadcaster and automatically setting the optimal broadcasting conditions,

[0857] A means to continuously audit the reactions from recipients during distribution and eliminate inappropriate content,

[0858] A means of collecting and analyzing viewing results after distribution and providing recipient reactions as a report,

[0859] A means of selecting and configuring methods for monetizing information, and tracking and managing revenue information,

[0860] A system that includes this.

[0861] (Claim 2)

[0862] The system according to claim 1, characterized in that the distribution user registers personal information and distribution purpose, thereby optimizing the generation algorithm and distribution condition setting means.

[0863] (Claim 3)

[0864] The system according to claim 1, characterized in that it has a function to automatically suggest improvements for the next delivery based on the behavioral analysis of the recipient.

[0865] "Example 2 of combining an emotion engine"

[0866] (Claim 1)

[0867] A means for automatically generating constituent elements using a generation method based on information input by the user,

[0868] A means for detecting the sender's equipment environment and automatically proposing and setting the optimal transmission settings,

[0869] A means to immediately monitor the recipient's response during transmission and censor inappropriate content,

[0870] A means of aggregating and analyzing received data after transmission and providing feedback from recipients as a report,

[0871] A means to select and configure data monetization methods, and to track and manage revenue data.

[0872] A means of analyzing users' emotional states and making specific suggestions to improve content quality,

[0873] A means of adjusting the timing to optimize monetization opportunities using user sentiment information,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, characterized in that the sender registers personal information and the purpose of transmission, thereby optimizing the generation method and the transmission setting means.

[0877] (Claim 3)

[0878] The system according to claim 1, characterized in that it has a function to automatically suggest improvements for the next transmission based on an analysis of the recipient's behavior.

[0879] "Application example 2 when combining with an emotional engine"

[0880] (Claim 1)

[0881] A means for automatically generating documents and scripts using a generation method based on a theme entered by the user,

[0882] A means of recognizing the broadcaster's electronic device and automatically suggesting and setting the optimal settings,

[0883] A means to monitor viewer information in real time during the broadcast and eliminate inappropriate content,

[0884] A means of statistically analyzing and analyzing viewing data after distribution and providing viewer feedback as a report,

[0885] A means of analyzing the user's emotional state in real time using emotion recognition functionality and providing feedback to adjust the content and speech being delivered,

[0886] A means of acquiring emotional data through electronic devices and dynamically changing content based on that data,

[0887] A means to select and configure methods for monetizing content, and to track and manage revenue data.

[0888] A system that includes this.

[0889] (Claim 2)

[0890] The system according to claim 1, characterized in that the distributionr registers personal information and distribution purpose, thereby optimizing the generation method and setting means, and further enabling the emotion recognition function.

[0891] (Claim 3)

[0892] The system according to claim 1, characterized in that it has a function to automatically suggest improvements for the next broadcast based on an analysis of the viewer's behavior and emotional state. [Explanation of symbols]

[0893] 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. A means of automatically generating scripts and other materials using a generation algorithm based on the distribution theme entered by the user, A means to scan the broadcaster's device environment and automatically suggest and configure the optimal broadcast settings, A means to monitor viewer comments in real time during the broadcast and filter out inappropriate content, A means of collecting and analyzing viewing data after the broadcast and providing viewer feedback as a report, A means to select and configure content monetization models, and to track and manage revenue data, A system that includes this.

2. The system according to claim 1, characterized in that the distribution method optimizes the generation algorithm and distribution setting means by having the distribution method provider register personal information and distribution purpose.

3. The system according to claim 1, characterized in that it has a function to automatically suggest improvements for the next broadcast based on an analysis of viewer behavior.

Images