system

Abstract

We provide the system. [Solution] A means for collecting individual datasets and preprocessing said datasets, A means for training a generative model using preprocessed data and generating individual generative intelligences, A means of providing individually generated generative intelligences on a sales platform and distributing profits based on their sales performance, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Current general-purpose generative artificial intelligence has difficulty appropriately reflecting the thinking patterns and styles of specific individuals and can only provide general outputs. There is also no appropriate platform that can meet the needs of both those who want to spread their ideas and styles to others and those who want to use them. As a result, individuals lose the opportunity to efficiently utilize their intellectual assets and cannot obtain sufficient benefits.

Means for Solving the Problems

[0005] This invention is a system that collects individual datasets and provides individualized generative intelligences (AIs) generated based on them. This system creates AIs tailored to individual styles by training a generative model using individuals' copyrighted works and transcripts of their speech. Furthermore, by providing these AIs through a sales platform and returning the profits from sales to the creators, it provides a means to efficiently utilize individuals' intellectual assets. As a result, it becomes possible to share an individual's unique way of thinking with others and share the benefits together.

[0006] A "dataset" is a collection of information used to train a generative model, such as personal writings or transcripts of speeches.

[0007] "Preprocessing" refers to a series of processes that remove noise from raw data and prepare it into a format that AI can learn from.

[0008] A "generative model" is an artificial intelligence algorithm that generates new output based on input data, and in this case, it is used to teach an individual's style.

[0009] A "personalized generative intelligence" is a generative AI model that learns from a specific individual's dataset and can reflect that individual's unique style and way of thinking.

[0010] A "sales platform" is an online system that publishes and provides generative intelligence to buyers.

[0011] "Profit sharing" refers to the distribution of revenue earned from the sales performance of the generated intelligence to the creators and other parties involved. [Brief explanation of the drawing]

[0012] [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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] Shows an emotion map to which multiple emotions are mapped. [Figure 10] Shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] 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.

[0017] 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.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system that generates individual generative intelligences based on personal data and distributes profits through their sale. This system consists of the following stages: data collection, data preprocessing, model generation, model publication, sales, and profit distribution.

[0034] Users upload their own works and transcripts of statements to the system using their devices. This process includes a mechanism that allows for easy data provision through the user interface. The server collects necessary data from other data sources (e.g., publicly available online information) and aggregates the text information.

[0035] The collected data is preprocessed by the server and converted into a format suitable for AI training. This preprocessing includes noise reduction, grammar correction, and text normalization. The server then uses the preprocessed data to train a generative model, generating individual generative intelligences. This results in a model that reflects the style and thinking of a specific individual.

[0036] The individual generated AIs are uploaded by the server to an online sales platform. Users can visit this platform, purchase the AIs they are interested in, and download and use them on their devices. The purchase process is designed to be intuitive through the interface.

[0037] The profits from sold models are automatically calculated by the server and fed back to the creator of the generated AI according to a predetermined distribution ratio. The revenue distribution process is carried out accurately based on sales records, and payments are made quickly.

[0038] As a concrete example, let's assume a writer uploads their novel data. The server preprocesses this data and generates individual generative intelligences that mimic the writer's style. This model becomes available on a sales platform, where other users can purchase it and use it in their own creative activities. The profits generated in this process are returned to the writer through the system, providing an incentive for further writing.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] Users upload copyrighted works and transcripts of their statements to the system using their devices. The user interface guides the user and includes functions to verify the integrity of file formats and the type of data being processed.

[0042] Step 2:

[0043] The server collects uploaded data and, if necessary, gathers supplementary data from external sources. The server uses APIs to retrieve publicly available information from external databases.

[0044] Step 3:

[0045] The server performs preprocessing on the collected data. Preprocessing includes removing noise from the text data, correcting grammar and formatting, and preparing it in a format that is easy for generative models to learn from.

[0046] Step 4:

[0047] The server trains a generative model based on pre-processed data. During the training process, the existing generative model is fine-tuned to capture individual characteristic language patterns.

[0048] Step 5:

[0049] The server uploads the individually generated generative intelligences to the sales platform and configures them for user access. At this stage, model descriptions and introductory videos are also posted.

[0050] Step 6:

[0051] Users purchase generative intelligences of interest on the platform. An intuitive purchase flow is provided on the device, ensuring a secure payment process.

[0052] Step 7:

[0053] The server records sales performance and calculates profits based on sales. Profits are automatically calculated based on a set distribution ratio and distributed to the creator.

[0054] (Example 1)

[0055] 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."

[0056] Conventional systems for generating intelligent entities suffer from inefficient processes for collecting and pre-processing personal digital content, generating intelligent entities, and revenue sharing through sales. In particular, generating individual knowledge systems and effectively selling and utilizing them is difficult. Furthermore, there are issues with inadequate revenue sharing, preventing users from receiving fair compensation.

[0057] 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.

[0058] In this invention, the server includes means for collecting and pre-processing individual digital content, means for training a machine learning model using the pre-processed data to generate individual knowledge systems, and means for providing the generated individual knowledge systems on an online platform and distributing revenue based on their transaction performance. This enables the efficient and accurate generation of knowledge systems, and allows users who receive a fair share of the revenue to select and utilize the knowledge systems.

[0059] "Digital content" refers to electronic data such as text, images, audio, and video that can be created or accessed on a computer.

[0060] "Preprocessing" refers to the process of removing noise and correcting grammar in text data so that machine learning models can process the data efficiently.

[0061] A "machine learning model" refers to a computational model that has algorithms to automate a specific task based on input data and to predict or classify the results.

[0062] A "knowledge system" refers to a system that learns from collected data and can generate output with specific knowledge and style.

[0063] An "online platform" refers to a web-based marketplace provided over the internet where users can buy and sell digital goods.

[0064] "Revenue sharing" refers to the process of distributing profits earned from the sale of generated intelligences, etc., to the users and contributors involved.

[0065] This invention relates to a system that generates individual knowledge systems based on an individual's digital content and distributes profits by selling these systems. Specific embodiments are described below.

[0066] Users upload their digital content, such as documents and transcripts, to the system using their devices. To do this, users provide data through an intuitive user interface. These devices can be standard personal computers or smartphones.

[0067] The server collects relevant information not only from user input data but also from publicly available data sources on the internet. It uses online scraping techniques to aggregate data based on specified conditions. This process is necessary to collect a wide range of text information.

[0068] The collected data is preprocessed by the server and converted into a format that can be effectively trained by machine learning models. This preprocessing involves denoising, grammar correction, and normalization using Python's natural language processing libraries such as spacy and NLTK.

[0069] The server trains generative AI models using pre-processed data to generate individual knowledge systems. This process utilizes deep learning frameworks such as TENSORFLOW® and PyTorch to perform data-driven learning. This results in models that reflect the writing style and thought patterns of specific individuals.

[0070] The generated knowledge systems are uploaded to an online platform via a server. Users can visit this platform and select and purchase knowledge systems. The interface is designed to be user-friendly, and users can view text output samples and past evaluation reviews.

[0071] In revenue sharing, the server calculates sales based on the sales performance of the generated intelligent entities and distributes profits to users according to predetermined criteria. This process is automated, and the calculation results are notified to users via email or other means.

[0072] As a concrete example, an author uploads their novel data, and a knowledge system is generated based on that data. Then, by using a prompt message such as, "Please generate a short adventure story for children using this author's writing style," buyers can utilize the knowledge system. As a result, sales revenue is returned to the author, encouraging further creative activity.

[0073] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0074] Step 1:

[0075] Users upload digital content from their own devices. Specifically, they use the user interface to drag and drop or select their copyrighted works and transcripts to send them to the server. The system accepts data in text or PDF file format as input and saves it on the server as output.

[0076] Step 2:

[0077] The server collects data not only from data uploaded by users but also from publicly available information online. Specifically, it uses web scraping techniques to collect necessary text information. The input consists of URLs and online resources based on specified query conditions, and the output is the collected text data.

[0078] Step 3:

[0079] The server preprocesses the collected data. This involves using natural language processing libraries (e.g., spaCy or NLTK) to denoise, correct grammar, and normalize the text. The input is raw data, and the output is clear, preprocessed data.

[0080] Step 4:

[0081] The server trains a generative AI model using preprocessed data. It utilizes deep learning frameworks (e.g., TensorFlow or PyTorch) to generate individual knowledge systems. The input consists of preprocessed data and an AI algorithm, and the output is a model of a knowledge system that reflects the user's style.

[0082] Step 5:

[0083] The server uploads and publishes the generated knowledge system to an online platform. Here, the model overview and sample outputs are configured to be provided to users. The input is the knowledge system model file, and the output is published on the platform.

[0084] Step 6:

[0085] Users can visit the platform to purchase and utilize knowledge systems. Specifically, they can complete the purchase process and download the system using an intuitive interface. The input is the purchase procedure instructions, and the output is the downloaded model saved on the device.

[0086] Step 7:

[0087] The server calculates sales based on sales performance and distributes the profits to users. It automatically calculates based on sales records and makes payments according to pre-set criteria. The input is sales performance data, and the output is the calculated profits distributed to users.

[0088] (Application Example 1)

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

[0090] Traditional content generation systems struggled to create stories that adequately reflected individual user preferences, and lacked mechanisms for appropriately distributing revenue. As a result, personalized content experiences were not provided, and revenue sharing for creators was insufficient.

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

[0092] In this invention, the server includes means for collecting and pre-processing personal data collections; means for training a generative model using the pre-processed data and generating individual intelligent models; means for providing the generated individual intelligent models on an e-commerce platform and distributing profits based on their sales performance; and means for generating personalized stories based on the user's personal data and providing them on a visualization device. This enables the generation of unique stories that reflect the individual preferences of the user, as well as the rapid and accurate distribution of profits to creators.

[0093] A "personal data collection" is a collection of information related to an individual provided by a user, including the user's copyrighted works and records of their statements.

[0094] "Preprocessing" refers to the process of converting data into a format suitable for training an AI model, and includes techniques such as noise reduction and data normalization.

[0095] A "generative model" is an artificial intelligence system that creates an intelligent entity that reflects the user's unique knowledge based on collected data.

[0096] An "intelligent model" is a model generated by AI that reflects the characteristics and style of individual users, and is used in a variety of applications.

[0097] An "e-commerce platform" is a system for selling and trading digital goods online, enabling users to purchase and download products.

[0098] A "visualization device" is a device used to provide generated content to users visually, and includes smartphones and head-mounted displays.

[0099] A "personalized story" is a narrative or story that is generated based on a user's personal preferences and data, making it unique to each individual user.

[0100] "Profit sharing" is the process of appropriately distributing the profits earned to the creators and developers of the generative model based on sales performance.

[0101] Specific embodiments for carrying out this invention are shown below.

[0102] The system is designed to allow users to upload their personal data collections via devices such as smartphones and computers. Data sets include personal copyrighted works and records of speech. A login user interface ensures easy and secure data provision.

[0103] The server receives the collected data and performs preprocessing such as denoising and data normalization. The preprocessed data is then trained using the AI ​​library TensorFlow to generate individual intelligent models. These models reflect the characteristics and styles of each individual user.

[0104] The generated intelligent models are managed on Amazon DynamoDB and uploaded to an e-commerce platform, where they become available for purchase. This platform features a user-friendly interface built with React Native, allowing buyers to intuitively select and download models.

[0105] This allows users to experience personalized stories using visualization devices such as smartphones and head-mounted displays. These stories are generated based on the user's preferences, enriching their experience.

[0106] As a concrete example, a user who enjoys fantasy can create their own adventure story using a model generated to mimic their favorite story style. For instance, they could enter a prompt like this: "Create an epic adventure story about the brave knight Eric searching for his lost sword in a magical forest." This allows the user to have a new storytelling experience.

[0107] Profits from sales are distributed to creators quickly and accurately. This is expected to further boost their creative motivation.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] Users upload their personal data collections to the system using their smartphones or computers. This process involves the user logging in through the interface, selecting the files to upload, and pressing the submit button. Input data consists of text-based works and transcripts of speech, while output is raw data received on the server side.

[0111] Step 2:

[0112] The server preprocesses the received data collection. Specifically, it performs noise reduction, data normalization, and grammatical correction. The raw data acquired as input is converted into a noise-free format and shaped so that it can be easily trained by the AI ​​model. This results in clean, preprocessed data as output.

[0113] Step 3:

[0114] The server trains a generative model using pre-processed data. Here, TensorFlow is used to build a generative AI model based on the collected data. The input is formatted data, and the output is an intelligent model tailored to a specific user. This model reflects the user's style and characteristics.

[0115] Step 4:

[0116] The server saves the generated intelligent model to Amazon DynamoDB and uploads it to the e-commerce platform. At this time, sales information is registered on the platform and becomes viewable by users. The input is the newly generated intelligent model, and the output is in a state accessible on the online platform.

[0117] Step 5:

[0118] The user selects a generative model of interest on the platform and begins the download process. During the purchase process, the user selects a product via the interface, completes payment, and the model is downloaded to their device. The input is the user's selection information, and the output is the intelligent model stored on the user's device.

[0119] Step 6:

[0120] The device uses a downloaded intelligent model to generate stories based on the user's personal preferences. The user inputs prompts, and the model generates a story in response to those instructions. For example, if the prompt is "Create a story about the brave knight Eric's epic adventure to find his lost sword in a magical forest," the generation model will create a story based on the input prompt, resulting in a customized story.

[0121] 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.

[0122] This invention relates to a system equipped with an emotion engine that recognizes user emotions and optimizes the creation of individual generative intelligences and interactions accordingly. This system includes a series of processes from data collection to model generation, platform provision, and profit sharing, but by newly considering user emotions, it provides a more personalized experience.

[0123] When users upload their own works or transcripts using their devices, their emotional state at that time is analyzed by an emotion engine. This emotion analysis is performed, for example, by analyzing the intonation of their voice, their facial expressions, or the emotion of the input text. The server uses this emotion data to adjust the generative model to match the user's emotions and create an individualized generative intelligence.

[0124] The generated AIs possess a unique style that takes into account the user's emotions, and are provided to the platform in a format that other users can utilize based on that style. For example, a user who purchases an AI on the platform can have their emotions recognized in real time during interactions and receive responses accordingly. This makes interactions more natural and intimate.

[0125] The server recommends personalized generated intelligences by appropriately analyzing the emotions of users on the platform. If a user is feeling sad, it can recommend an intelligence that offers encouragement. This improvement in the user experience leads to increased sales of the selected intelligence.

[0126] As a concrete example, imagine a scenario where user A uploads data from writing a novel and has their motivation evaluated. The emotion engine measures user A's writing motivation and reflects it in the data, then generates a highly motivating generative intelligence based on that. This intelligence then generates positive and proactive responses to subsequent buyers, playing a role in increasing user A's brand value.

[0127] This system enables the creation and use of intelligent entities that respond to users' emotions, providing users with a more valuable experience, and also allows creators of intelligent entities to expand their market by offering diverse emotional settings.

[0128] The following describes the processing flow.

[0129] Step 1:

[0130] Users upload their own works and transcripts to the system using their devices. The user interface verifies the integrity of the file format and the type of data, while an emotion engine simultaneously analyzes the user's emotional state during the upload. This is done through voice input, text input, and webcam video.

[0131] Step 2:

[0132] The server collects uploaded data and stores it in a database along with the sentiment analysis results from the sentiment engine. The server also collects complementary information from other data sources, such as themes and styles of the user's past works.

[0133] Step 3:

[0134] The server performs preprocessing on the collected data and sentiment information. This preprocessing includes noise reduction, grammar correction, and adjustment of sentiment expression parameters, thereby preparing the data in a format suitable for training the generative model.

[0135] Step 4:

[0136] The server uses pre-processed data as input to train a generative model, generating individual generative intelligences that reflect the user's emotional information. During this learning process, the model's parameters are adjusted, enabling the generation of responses that prioritize specific emotional states.

[0137] Step 5:

[0138] The generated AIs are uploaded to the sales platform by the server and made publicly available for user access. Here, emotion-specific characteristics are introduced, allowing buyers to select an AI that suits their purpose.

[0139] Step 6:

[0140] The user, as the buyer, selects a generated intelligence on the platform and attempts to execute emotion-based scenarios. During the on-device interaction, the buyer's current emotional state is analyzed in real time to provide the most appropriate response.

[0141] Step 7:

[0142] The server records sales performance and calculates profits based on sales including added value derived from sentiment analysis. The profits are automatically returned to the creator of the generated intelligence according to a predetermined distribution ratio.

[0143] (Example 2)

[0144] 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".

[0145] In modern information technology, there is a growing demand in many fields to improve user experience through interaction with personalized artificial intelligence. However, conventional systems have not adequately considered the user's emotional state, limiting their ability to achieve natural and intimate communication with users. Furthermore, the lack of efficient methods for customizing and recommending generative intelligences has made it difficult to provide a more personalized experience.

[0146] 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.

[0147] In this invention, the server includes means for collecting and preprocessing a set of personal information; means for learning a generative model using the preprocessed information and generating individual generative intelligences; means for providing the generated individual generative intelligences on an e-commerce platform and distributing profits based on their transaction performance; means for analyzing the emotional state of a user obtained from a terminal and adjusting the generative model based on the analysis results; and means for analyzing the user's emotions in real time and optimizing the intelligence's response using the analysis results. This enables the customization of generative intelligences to match the user's emotions and real-time response optimization based on emotions.

[0148] An "information set" refers to a collection of data and information related to an individual, which includes text, audio, and image data.

[0149] "Preprocessing" refers to the process of converting collected raw data into a format suitable for analysis and model training.

[0150] A "generative model" refers to a data-driven computational model that uses machine learning algorithms to generate new data or responses.

[0151] A "generative intelligence" refers to an artificial intelligence program that is individually created using a generative model and interacts with the user.

[0152] An "e-commerce platform" refers to an online space for buying and selling digital products and services.

[0153] "Emotional state" refers to the user's psychological state and is analyzed through text, audio, and image data.

[0154] "Real-time analysis" refers to a process where data is processed and results are obtained immediately as soon as it is generated.

[0155] Users upload their personal information to the system using their devices. This information includes the user's copyrighted works, transcripts of their statements, audio data, and image data, and is used to analyze the user's emotional state.

[0156] The server receives the uploaded data set and performs initial preprocessing. This preprocessing includes removing unnecessary data and standardizing the data format. The server then analyzes the user's emotional state using emotion recognition technology. This analysis utilizes common speech recognition software for voice intonation analysis, video analysis software for facial expression analysis, and natural language processing software for text emotion analysis. Specifically, Google® Cloud Natural Language API and Microsoft® Azure® Emotion API may be used.

[0157] Next, the server adjusts the generative model based on the analyzed sentiment data to create individual generative intelligences. Machine learning models such as ChatGPT® and BERT are used for the generative model. These intelligences are then provided to users for use on the e-commerce platform. This allows the intelligences to generate responses tailored to the emotions of different users.

[0158] Furthermore, the server performs real-time analysis of the intelligent entities on the platform. The terminal sends user input to the server in real time, and emotions are analyzed on the spot. This immediacy makes it possible to make user interaction more natural and intimate.

[0159] For example, if a user inputs "I haven't felt like writing lately," the server analyzes the statement and adjusts its response to the AI. This provides an optimal response tailored to the user's emotions, resulting in a more personalized experience. An example of a prompt might be, "I recently started writing a novel, but how can I stay more motivated?" In response to this prompt, the AI ​​generates a positive response and provides valuable advice to the user.

[0160] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0161] Step 1:

[0162] Users upload their information to the system using a terminal. Input includes text data, audio data, and image data, which are sent to the server. The output is a structured dataset stored in the server-side database. This process involves specific actions such as file selection, form completion, and audio recording.

[0163] Step 2:

[0164] The server preprocesses the received data set. First, it removes unnecessary data and converts the format to a unified format. Data processing includes noise reduction, format conversion, and character encoding standardization. The output is a clean dataset suitable for analysis.

[0165] Step 3:

[0166] The server analyzes the user's emotional state using a clean dataset. The input is a pre-processed dataset, which is then analyzed by the emotion analysis engine. Data calculations include speech intonation analysis, facial expression recognition, and text sentiment analysis. The output is a result indicating the user's emotional state, which is stored in a dedicated table.

[0167] Step 4:

[0168] The server adjusts the generative AI model based on the sentiment analysis results. The input consists of the sentiment analysis results and the generative model; the model's parameters are customized to match the emotions. Data processing includes setting response style parameters and reorganizing the training data. The output is the adjusted generative intelligence.

[0169] Step 5:

[0170] The server publishes the generated intelligences on an e-commerce platform. The input is a pre-tuned generated intelligence, which is then deployed to the platform. Specific operations include sending data via APIs and creating profiles on the platform. The output is information about the published intelligences.

[0171] Step 6:

[0172] When a user interacts with an intelligent entity on the platform, the terminal sends input to the server in real time. The user's text or voice is sent as input in real time and analyzed by the server. The output is the analysis result, which is used for the intelligent entity's response.

[0173] Step 7:

[0174] The server generates an intelligent response based on the analysis results and returns it to the user. The input consists of real-time analysis results and a pre-tuned generative model, which then generates the response. Data processing includes natural language generation and sentiment filtering. The output is an optimized response presented to the user.

[0175] (Application Example 2)

[0176] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0177] Conventional generative intelligence systems have struggled to accurately reflect the emotional states of individual users, failing to provide personalized experiences. As a result, user interactions were often formal, making it difficult to achieve emotional satisfaction. Furthermore, the generated content did not always match the user's current emotional state, leading to a decline in the quality of the user experience.

[0178] 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.

[0179] In this invention, the server includes means for collecting and preprocessing individual datasets, means for training a generative model using the preprocessed data and generating individual generative intelligences, means for analyzing the user's emotions and selecting or adjusting content based on those emotions, and means for providing the adjusted generative intelligences on a platform for sale and distributing profits based on sales performance. This enables the delivery of personalized content that is tailored to the user's emotions.

[0180] A "personal dataset" is a collection of information related to a specific individual, and includes various data formats such as audio, text, and image data.

[0181] "Preprocessing" refers to the preparatory process of converting information within a dataset into a format suitable for analysis and training, and includes tasks such as noise reduction and normalization.

[0182] A "generative model" is a mathematical or algorithmic framework for generating new data or knowledge based on given input data.

[0183] A "generative intelligence" is an intelligent agent produced by a specific generative model, and its role is to support interaction with the user.

[0184] "Sentiment analysis" is a process that mechanically evaluates a user's emotional state from input voice, text, and image data.

[0185] "Content" refers to a portion of the information or media provided to users, and can be delivered in various forms such as music, video, and text.

[0186] A "sales platform" is an electronic market environment for trading generative intelligences as a value, providing a mechanism for users to select and purchase them.

[0187] "Profit sharing" refers to the process of appropriately distributing revenue earned based on sales performance among stakeholders.

[0188] This invention is a system that enables a more interactive content experience by providing a personalized generative intelligence that responds to the user's emotions. The server collects individual datasets and preprocesses them to prepare them for analysis. Specifically, it removes noise from audio, text, and image data and extracts the necessary information. This utilizes existing technologies such as OpenCV and the Google Cloud Speech-to-Text API.

[0189] Next, the server learns a generative model based on the pre-processed data. The generative model is typically implemented using machine learning algorithms to generate intelligent entities based on the user's individuality and emotional characteristics. These generated intelligent entities are then sold on a specific platform.

[0190] The device analyzes the user's emotions in real time from their voice, facial expressions, and text, and sends this information to the server. This allows the server to adjust and deliver optimal content to the user based on their current emotional state.

[0191] As a concrete example, in a content distribution service that users use daily, a system could be implemented that automatically recommends healing music or relaxing videos when an emotional state indicating fatigue is detected. This would allow users to have an experience that aligns with their emotions at that particular time.

[0192] The generative AI model requires a prompt, which is input as shown in the example below: "If the user is relaxed after work but showing signs of stress, list appropriate content. Recommend calming movies or music."

[0193] This makes it possible to create a user experience optimized for emotions.

[0194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0195] Step 1:

[0196] The device captures the user's voice, facial expressions, and text data in real time. This input data is acquired through the built-in microphone, camera, and text input interface. Because the acquired data is noisy, basic pre-processing is performed on the device.

[0197] Step 2:

[0198] Preprocessed data is sent from the terminal to the server. The server uses an emotion analysis system to analyze the user's emotional state based on the received data. This analysis uses a machine learning model to identify emotions from voice intonation, facial expressions, and text. The identified emotion information is obtained as output.

[0199] Step 3:

[0200] The server uses a generative AI model to generate or select content optimized for the user's emotions, based on the analyzed sentiment information. It uses prompts as input to instruct the generative AI model. The output is a list of content appropriate for the user's emotions.

[0201] Step 4:

[0202] The server sends a list of the retrieved content to the terminal. The terminal recommends content to the user's screen. The user can select and experience this recommended content. The server provides the user's selected content as output.

[0203] Step 5:

[0204] Users experience the provided content and send their feedback back to the server via their device. The server stores this feedback to use in training the next generational AI model. This feedback contributes to improving the accuracy of future sentiment analysis and content recommendation.

[0205] 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.

[0206] 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 (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.

[0207] 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.

[0208] [Second Embodiment]

[0209] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0210] 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.

[0211] 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).

[0212] 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.

[0213] 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.

[0214] 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).

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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".

[0221] This invention is a system that generates individual generative intelligences based on personal data and distributes profits through their sale. This system consists of the following stages: data collection, data preprocessing, model generation, model publication, sales, and profit distribution.

[0222] Users upload their own works and transcripts of statements to the system using their devices. This process includes a mechanism that allows for easy data provision through the user interface. The server collects necessary data from other data sources (e.g., publicly available online information) and aggregates the text information.

[0223] The collected data is preprocessed by the server and converted into a format suitable for AI training. This preprocessing includes noise reduction, grammar correction, and text normalization. The server then uses the preprocessed data to train a generative model, generating individual generative intelligences. This results in a model that reflects the style and thinking of a specific individual.

[0224] The individual generated AIs are uploaded by the server to an online sales platform. Users can visit this platform, purchase the AIs they are interested in, and download and use them on their devices. The purchase process is designed to be intuitive through the interface.

[0225] The profits from sold models are automatically calculated by the server and fed back to the creator of the generated AI according to a predetermined distribution ratio. The revenue distribution process is carried out accurately based on sales records, and payments are made quickly.

[0226] As a concrete example, let's assume a writer uploads their novel data. The server preprocesses this data and generates individual generative intelligences that mimic the writer's style. This model becomes available on a sales platform, where other users can purchase it and use it in their own creative activities. The profits generated in this process are returned to the writer through the system, providing an incentive for further writing.

[0227] The following describes the processing flow.

[0228] Step 1:

[0229] Users upload copyrighted works and transcripts of their statements to the system using their devices. The user interface guides the user and includes functions to verify the integrity of file formats and the type of data being processed.

[0230] Step 2:

[0231] The server collects uploaded data and, if necessary, gathers supplementary data from external sources. The server uses APIs to retrieve publicly available information from external databases.

[0232] Step 3:

[0233] The server performs preprocessing on the collected data. Preprocessing includes removing noise from the text data, correcting grammar and formatting, and preparing it in a format that is easy for generative models to learn from.

[0234] Step 4:

[0235] The server trains a generative model based on pre-processed data. During the training process, the existing generative model is fine-tuned to capture individual characteristic language patterns.

[0236] Step 5:

[0237] The server uploads the individually generated generative intelligences to the sales platform and configures them for user access. At this stage, model descriptions and introductory videos are also posted.

[0238] Step 6:

[0239] Users purchase generative intelligences of interest on the platform. An intuitive purchase flow is provided on the device, ensuring a secure payment process.

[0240] Step 7:

[0241] The server records sales performance and calculates profits based on sales. Profits are automatically calculated based on a set distribution ratio and distributed to the creator.

[0242] (Example 1)

[0243] 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".

[0244] Conventional systems for generating intelligent entities suffer from inefficient processes for collecting and pre-processing personal digital content, generating intelligent entities, and revenue sharing through sales. In particular, generating individual knowledge systems and effectively selling and utilizing them is difficult. Furthermore, there are issues with inadequate revenue sharing, preventing users from receiving fair compensation.

[0245] 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.

[0246] In this invention, the server includes means for collecting and pre-processing individual digital content, means for training a machine learning model using the pre-processed data to generate individual knowledge systems, and means for providing the generated individual knowledge systems on an online platform and distributing revenue based on their transaction performance. This enables the efficient and accurate generation of knowledge systems, and allows users who receive a fair share of the revenue to select and utilize the knowledge systems.

[0247] "Digital content" refers to electronic data such as text, images, audio, and video that can be created or accessed on a computer.

[0248] "Preprocessing" refers to the process of removing noise and correcting grammar in text data so that machine learning models can process the data efficiently.

[0249] A "machine learning model" refers to a computational model that has algorithms to automate a specific task based on input data and to predict or classify the results.

[0250] A "knowledge system" refers to a system that learns from collected data and can generate output with specific knowledge and style.

[0251] An "online platform" refers to a web-based marketplace provided over the internet where users can buy and sell digital goods.

[0252] "Revenue sharing" refers to the process of distributing profits earned from the sale of generated intelligences, etc., to the users and contributors involved.

[0253] This invention relates to a system that generates individual knowledge systems based on an individual's digital content and distributes profits by selling these systems. Specific embodiments are described below.

[0254] Users upload their digital content, such as documents and transcripts, to the system using their devices. To do this, users provide data through an intuitive user interface. These devices can be standard personal computers or smartphones.

[0255] The server collects relevant information not only from user input data but also from publicly available data sources on the internet. It uses online scraping techniques to aggregate data based on specified conditions. This process is necessary to collect a wide range of text information.

[0256] The collected data is preprocessed by the server and converted into a format that can be effectively trained by machine learning models. This preprocessing involves denoising, grammar correction, and normalization using Python's natural language processing libraries such as spacy and NLTK.

[0257] The server trains generative AI models using preprocessed data to generate individual knowledge systems. This process utilizes deep learning frameworks such as TensorFlow and PyTorch, performing data-driven learning. This results in models that reflect the writing style and thinking patterns of specific individuals.

[0258] The generated knowledge systems are uploaded to an online platform via a server. Users can visit this platform and select and purchase knowledge systems. The interface is designed to be user-friendly, and users can view text output samples and past evaluation reviews.

[0259] In revenue sharing, the server calculates sales based on the sales performance of the generated intelligent entities and distributes profits to users according to predetermined criteria. This process is automated, and the calculation results are notified to users via email or other means.

[0260] As a concrete example, an author uploads their novel data, and a knowledge system is generated based on that data. Then, by using a prompt message such as, "Please generate a short adventure story for children using this author's writing style," buyers can utilize the knowledge system. As a result, sales revenue is returned to the author, encouraging further creative activity.

[0261] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0262] Step 1:

[0263] Users upload digital content from their own devices. Specifically, they use the user interface to drag and drop or select their copyrighted works and transcripts to send them to the server. The system accepts data in text or PDF file format as input and saves it on the server as output.

[0264] Step 2:

[0265] The server collects data not only from data uploaded by users but also from publicly available information online. Specifically, it uses web scraping techniques to collect necessary text information. The input consists of URLs and online resources based on specified query conditions, and the output is the collected text data.

[0266] Step 3:

[0267] The server preprocesses the collected data. This involves using natural language processing libraries (e.g., spaCy or NLTK) to denoise, correct grammar, and normalize the text. The input is raw data, and the output is clear, preprocessed data.

[0268] Step 4:

[0269] The server trains a generative AI model using preprocessed data. It utilizes deep learning frameworks (e.g., TensorFlow or PyTorch) to generate individual knowledge systems. The input consists of preprocessed data and an AI algorithm, and the output is a model of a knowledge system that reflects the user's style.

[0270] Step 5:

[0271] The server uploads and publishes the generated knowledge system to an online platform. Here, the model overview and sample outputs are configured to be provided to users. The input is the knowledge system model file, and the output is published on the platform.

[0272] Step 6:

[0273] Users can visit the platform to purchase and utilize knowledge systems. Specifically, they can complete the purchase process and download the system using an intuitive interface. The input is the purchase procedure instructions, and the output is the downloaded model saved on the device.

[0274] Step 7:

[0275] The server calculates sales based on sales performance and distributes the profits to users. It automatically calculates based on sales records and makes payments according to pre-set criteria. The input is sales performance data, and the output is the calculated profits distributed to users.

[0276] (Application Example 1)

[0277] 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 glasses 214 will be referred to as the "terminal."

[0278] Traditional content generation systems struggled to create stories that adequately reflected individual user preferences, and lacked mechanisms for appropriately distributing revenue. As a result, personalized content experiences were not provided, and revenue sharing for creators was insufficient.

[0279] 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.

[0280] In this invention, the server includes means for collecting and pre-processing personal data collections; means for training a generative model using the pre-processed data and generating individual intelligent models; means for providing the generated individual intelligent models on an e-commerce platform and distributing profits based on their sales performance; and means for generating personalized stories based on the user's personal data and providing them on a visualization device. This enables the generation of unique stories that reflect the individual preferences of the user, as well as the rapid and accurate distribution of profits to creators.

[0281] A "personal data collection" is a collection of information related to an individual provided by a user, including the user's copyrighted works and records of their statements.

[0282] "Preprocessing" refers to the process performed to convert data into a format suitable for the learning of an AI model, and is a technique including noise removal and data normalization.

[0283] "Generative model" refers to an artificial intelligence system for creating an intelligent entity that reflects the user's unique knowledge based on the collected data.

[0284] "Intelligent model" refers to a model generated by AI that reflects the characteristics and styles of individual users, and is utilized for various applications.

[0285] "E-commerce platform" refers to a system for selling and trading digital goods online, enabling users to purchase and download products.

[0286] "Visualization device" refers to a device used to visually provide the generated content to users, including smartphones and head-mounted displays, etc.

[0287] "Personalized story" refers to a story or narrative specialized for individual users, generated based on the user's personal preferences and data.

[0288] "Profit distribution" refers to the process of appropriately distributing the obtained profits to the creators and authors of the generative model based on sales performance.

[0289] Specific embodiments for implementing this invention are shown below.

[0290] The system is designed to allow users to upload their personal data collections through terminals such as smartphones and computers. The dataset includes personal works and speech records. The login user interface enables easy and secure data provision.

[0291] The server receives the collected data and performs preprocessing such as denoising and data normalization. The preprocessed data is then trained using the AI ​​library TensorFlow to generate individual intelligent models. These models reflect the characteristics and styles of each individual user.

[0292] The generated intelligent models are managed on Amazon DynamoDB and uploaded to an e-commerce platform, where they become available for purchase. This platform features a user-friendly interface built with React Native, allowing buyers to intuitively select and download models.

[0293] This allows users to experience personalized stories using visualization devices such as smartphones and head-mounted displays. These stories are generated based on the user's preferences, enriching their experience.

[0294] As a concrete example, a user who enjoys fantasy can create their own adventure story using a model generated to mimic their favorite story style. For instance, they could enter a prompt like this: "Create an epic adventure story about the brave knight Eric searching for his lost sword in a magical forest." This allows the user to have a new storytelling experience.

[0295] Profits from sales are distributed to creators quickly and accurately. This is expected to further boost their creative motivation.

[0296] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0297] Step 1:

[0298] Users upload their personal data collections to the system using their smartphones or computers. This process involves the user logging in through the interface, selecting the files to upload, and pressing the submit button. Input data consists of text-based works and transcripts of speech, while output is raw data received on the server side.

[0299] Step 2:

[0300] The server preprocesses the received data collection. Specifically, it performs noise reduction, data normalization, and grammatical correction. The raw data acquired as input is converted into a noise-free format and shaped so that it can be easily trained by the AI ​​model. This results in clean, preprocessed data as output.

[0301] Step 3:

[0302] The server trains a generative model using pre-processed data. Here, TensorFlow is used to build a generative AI model based on the collected data. The input is formatted data, and the output is an intelligent model tailored to a specific user. This model reflects the user's style and characteristics.

[0303] Step 4:

[0304] The server saves the generated intelligent model to Amazon DynamoDB and uploads it to the e-commerce platform. At this time, sales information is registered on the platform and becomes viewable by users. The input is the newly generated intelligent model, and the output is in a state accessible on the online platform.

[0305] Step 5:

[0306] The user selects a generative model of interest on the platform and starts the process of downloading. In the purchase procedure, after selecting a product via the interface and completing the payment, the model is downloaded to the terminal. The input is the user's selection information, and the output is the intelligent model stored on the user terminal.

[0307] Step 6:

[0308] The terminal uses the downloaded intelligent model to generate a story based on the user's personal preferences. The user inputs a prompt, and the model generates a story according to that instruction. For example, if the prompt is "Please create an epic adventure story where the brave knight Eric searches for a lost sword in a magical forest.", the generative model performs creative activities based on the input prompt, and a customized story is obtained as the output.

[0309] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion recognition model 59 and perform specific processing using the user's emotions.

[0310] The present invention is a system provided with an emotion engine that recognizes the user's emotions and optimizes the creation and interaction of individual generative intelligent entities accordingly. This system includes a series of processes from data collection to model generation, provision on the platform, and profit distribution. By newly considering the user's emotions, a more personalized experience is provided.

[0311] When the user uploads their own works or speech records using the terminal, the emotion engine analyzes the emotional state at that time. This emotion analysis is performed, for example, by analyzing the intonation of voice, facial expressions, or the emotion of the input text. The server utilizes this emotion data to adjust the generative model to match the user's emotions and create an individual generative intelligent entity.

[0312] The generated AIs possess a unique style that takes into account the user's emotions, and are provided to the platform in a format that other users can utilize based on that style. For example, a user who purchases an AI on the platform can have their emotions recognized in real time during interactions and receive responses accordingly. This makes interactions more natural and intimate.

[0313] The server recommends personalized generated intelligences by appropriately analyzing the emotions of users on the platform. If a user is feeling sad, it can recommend an intelligence that offers encouragement. This improvement in the user experience leads to increased sales of the selected intelligence.

[0314] As a concrete example, imagine a scenario where user A uploads data from writing a novel and has their motivation evaluated. The emotion engine measures user A's writing motivation and reflects it in the data, then generates a highly motivating generative intelligence based on that. This intelligence then generates positive and proactive responses to subsequent buyers, playing a role in increasing user A's brand value.

[0315] This system enables the creation and use of intelligent entities that respond to users' emotions, providing users with a more valuable experience, and also allows creators of intelligent entities to expand their market by offering diverse emotional settings.

[0316] The following describes the processing flow.

[0317] Step 1:

[0318] Users upload their own works and transcripts to the system using their devices. The user interface verifies the integrity of the file format and the type of data, while an emotion engine simultaneously analyzes the user's emotional state during the upload. This is done through voice input, text input, and webcam video.

[0319] Step 2:

[0320] The server collects uploaded data and stores it in a database along with the sentiment analysis results from the sentiment engine. The server also collects complementary information from other data sources, such as themes and styles of the user's past works.

[0321] Step 3:

[0322] The server performs preprocessing on the collected data and sentiment information. This preprocessing includes noise reduction, grammar correction, and adjustment of sentiment expression parameters, thereby preparing the data in a format suitable for training the generative model.

[0323] Step 4:

[0324] The server uses pre-processed data as input to train a generative model, generating individual generative intelligences that reflect the user's emotional information. During this learning process, the model's parameters are adjusted, enabling the generation of responses that prioritize specific emotional states.

[0325] Step 5:

[0326] The generated AIs are uploaded to the sales platform by the server and made publicly available for user access. Here, emotion-specific characteristics are introduced, allowing buyers to select an AI that suits their purpose.

[0327] Step 6:

[0328] The user, as the buyer, selects a generated intelligence on the platform and attempts to execute emotion-based scenarios. During the on-device interaction, the buyer's current emotional state is analyzed in real time to provide the most appropriate response.

[0329] Step 7:

[0330] The server records sales performance and calculates profits based on sales including added value derived from sentiment analysis. The profits are automatically returned to the creator of the generated intelligence according to a predetermined distribution ratio.

[0331] (Example 2)

[0332] 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".

[0333] In modern information technology, there is a growing demand in many fields to improve user experience through interaction with personalized artificial intelligence. However, conventional systems have not adequately considered the user's emotional state, limiting their ability to achieve natural and intimate communication with users. Furthermore, the lack of efficient methods for customizing and recommending generative intelligences has made it difficult to provide a more personalized experience.

[0334] 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.

[0335] In this invention, the server includes means for collecting and preprocessing a set of personal information; means for learning a generative model using the preprocessed information and generating individual generative intelligences; means for providing the generated individual generative intelligences on an e-commerce platform and distributing profits based on their transaction performance; means for analyzing the emotional state of a user obtained from a terminal and adjusting the generative model based on the analysis results; and means for analyzing the user's emotions in real time and optimizing the intelligence's response using the analysis results. This enables the customization of generative intelligences to match the user's emotions and real-time response optimization based on emotions.

[0336] An "information set" refers to a collection of data and information related to an individual, which includes text, audio, and image data.

[0337] "Preprocessing" refers to the process of converting collected raw data into a format suitable for analysis and model training.

[0338] A "generative model" refers to a data-driven computational model that uses machine learning algorithms to generate new data or responses.

[0339] A "generative intelligence" refers to an artificial intelligence program that is individually created using a generative model and interacts with the user.

[0340] An "e-commerce platform" refers to an online space for buying and selling digital products and services.

[0341] "Emotional state" refers to the user's psychological state and is analyzed through text, audio, and image data.

[0342] "Real-time analysis" refers to a process where data is processed and results are obtained immediately as soon as it is generated.

[0343] Users upload their personal information to the system using their devices. This information includes the user's copyrighted works, transcripts of their statements, audio data, and image data, and is used to analyze the user's emotional state.

[0344] The server receives the uploaded data set and performs initial preprocessing. This preprocessing includes removing unnecessary data and standardizing the data format. The server then analyzes the user's emotional state using emotion recognition technology. This analysis utilizes common speech recognition software for voice intonation analysis, video analysis software for facial expression analysis, and natural language processing software for text emotion analysis. Specifically, Google Cloud Natural Language API and Microsoft Azure Emotion API may be used.

[0345] Next, the server adjusts the generative model based on the analyzed sentiment data to create individual generative intelligences. Machine learning models such as ChatGPT and BERT are used for the generative model. These intelligences are then provided to users for use on the e-commerce platform. This allows the intelligences to generate responses tailored to the emotions of different users.

[0346] Furthermore, the server performs real-time analysis of the intelligent entities on the platform. The terminal sends user input to the server in real time, and emotions are analyzed on the spot. This immediacy makes it possible to make user interaction more natural and intimate.

[0347] For example, if a user inputs "I haven't felt like writing lately," the server analyzes the statement and adjusts its response to the AI. This provides an optimal response tailored to the user's emotions, resulting in a more personalized experience. An example of a prompt might be, "I recently started writing a novel, but how can I stay more motivated?" In response to this prompt, the AI ​​generates a positive response and provides valuable advice to the user.

[0348] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0349] Step 1:

[0350] Users upload their information to the system using a terminal. Input includes text data, audio data, and image data, which are sent to the server. The output is a structured dataset stored in the server-side database. This process involves specific actions such as file selection, form completion, and audio recording.

[0351] Step 2:

[0352] The server preprocesses the received data set. First, it removes unnecessary data and converts the format to a unified format. Data processing includes noise reduction, format conversion, and character encoding standardization. The output is a clean dataset suitable for analysis.

[0353] Step 3:

[0354] The server analyzes the user's emotional state using a clean dataset. The input is a pre-processed dataset, which is then analyzed by the emotion analysis engine. Data calculations include speech intonation analysis, facial expression recognition, and text sentiment analysis. The output is a result indicating the user's emotional state, which is stored in a dedicated table.

[0355] Step 4:

[0356] The server adjusts the generative AI model based on the sentiment analysis results. The input consists of the sentiment analysis results and the generative model; the model's parameters are customized to match the emotions. Data processing includes setting response style parameters and reorganizing the training data. The output is the adjusted generative intelligence.

[0357] Step 5:

[0358] The server publishes the generated intelligences on an e-commerce platform. The input is a pre-tuned generated intelligence, which is then deployed to the platform. Specific operations include sending data via APIs and creating profiles on the platform. The output is information about the published intelligences.

[0359] Step 6:

[0360] When a user interacts with an intelligent entity on the platform, the terminal sends input to the server in real time. The user's text or voice is sent as input in real time and analyzed by the server. The output is the analysis result, which is used for the intelligent entity's response.

[0361] Step 7:

[0362] The server generates an intelligent response based on the analysis results and returns it to the user. The input consists of real-time analysis results and a pre-tuned generative model, which then generates the response. Data processing includes natural language generation and sentiment filtering. The output is an optimized response presented to the user.

[0363] (Application Example 2)

[0364] 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."

[0365] Conventional generative intelligence systems have struggled to accurately reflect the emotional states of individual users, failing to provide personalized experiences. As a result, user interactions were often formal, making it difficult to achieve emotional satisfaction. Furthermore, the generated content did not always match the user's current emotional state, leading to a decline in the quality of the user experience.

[0366] 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.

[0367] In this invention, the server includes means for collecting and preprocessing individual datasets, means for training a generative model using the preprocessed data and generating individual generative intelligences, means for analyzing the user's emotions and selecting or adjusting content based on those emotions, and means for providing the adjusted generative intelligences on a platform for sale and distributing profits based on sales performance. This enables the delivery of personalized content that is tailored to the user's emotions.

[0368] A "personal dataset" is a collection of information related to a specific individual, and includes various data formats such as audio, text, and image data.

[0369] "Preprocessing" refers to the preparatory process of converting information within a dataset into a format suitable for analysis and training, and includes tasks such as noise reduction and normalization.

[0370] A "generative model" is a mathematical or algorithmic framework for generating new data or knowledge based on given input data.

[0371] A "generative intelligence" is an intelligent agent produced by a specific generative model, and its role is to support interaction with the user.

[0372] "Sentiment analysis" is a process that mechanically evaluates a user's emotional state from input voice, text, and image data.

[0373] "Content" refers to a portion of the information or media provided to users, and can be delivered in various forms such as music, video, and text.

[0374] A "sales platform" is an electronic market environment for trading generative intelligences as a value, providing a mechanism for users to select and purchase them.

[0375] "Profit sharing" refers to the process of appropriately distributing revenue earned based on sales performance among stakeholders.

[0376] This invention is a system that enables a more interactive content experience by providing a personalized generative intelligence that responds to the user's emotions. The server collects individual datasets and preprocesses them to prepare them for analysis. Specifically, it removes noise from audio, text, and image data and extracts the necessary information. This utilizes existing technologies such as OpenCV and the Google Cloud Speech-to-Text API.

[0377] Next, the server learns a generative model based on the pre-processed data. The generative model is typically implemented using machine learning algorithms to generate intelligent entities based on the user's individuality and emotional characteristics. These generated intelligent entities are then sold on a specific platform.

[0378] The device analyzes the user's emotions in real time from their voice, facial expressions, and text, and sends this information to the server. This allows the server to adjust and deliver optimal content to the user based on their current emotional state.

[0379] As a concrete example, in a content distribution service that users use daily, a system could be implemented that automatically recommends healing music or relaxing videos when an emotional state indicating fatigue is detected. This would allow users to have an experience that aligns with their emotions at that particular time.

[0380] The generative AI model requires a prompt, which is input as shown in the example below: "If the user is relaxed after work but showing signs of stress, list appropriate content. Recommend calming movies or music."

[0381] This makes it possible to create a user experience optimized for emotions.

[0382] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0383] Step 1:

[0384] The device captures the user's voice, facial expressions, and text data in real time. This input data is acquired through the built-in microphone, camera, and text input interface. Because the acquired data is noisy, basic pre-processing is performed on the device.

[0385] Step 2:

[0386] Preprocessed data is sent from the terminal to the server. The server uses an emotion analysis system to analyze the user's emotional state based on the received data. This analysis uses a machine learning model to identify emotions from voice intonation, facial expressions, and text. The identified emotion information is obtained as output.

[0387] Step 3:

[0388] The server uses a generative AI model to generate or select content optimized for the user's emotions, based on the analyzed sentiment information. It uses prompts as input to instruct the generative AI model. The output is a list of content appropriate for the user's emotions.

[0389] Step 4:

[0390] The server sends a list of the retrieved content to the terminal. The terminal recommends content to the user's screen. The user can select and experience this recommended content. The server provides the user's selected content as output.

[0391] Step 5:

[0392] Users experience the provided content and send their feedback back to the server via their device. The server stores this feedback to use in training the next generational AI model. This feedback contributes to improving the accuracy of future sentiment analysis and content recommendation.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] [Third Embodiment]

[0397] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0398] 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.

[0399] 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).

[0400] 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.

[0401] 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.

[0402] 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).

[0403] 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.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] 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.

[0408] 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".

[0409] This invention is a system that generates individual generative intelligences based on personal data and distributes profits through their sale. This system consists of the following stages: data collection, data preprocessing, model generation, model publication, sales, and profit distribution.

[0410] Users upload their own works and transcripts of statements to the system using their devices. This process includes a mechanism that allows for easy data provision through the user interface. The server collects necessary data from other data sources (e.g., publicly available online information) and aggregates the text information.

[0411] The collected data is preprocessed by the server and converted into a format suitable for AI training. This preprocessing includes noise reduction, grammar correction, and text normalization. The server then uses the preprocessed data to train a generative model, generating individual generative intelligences. This results in a model that reflects the style and thinking of a specific individual.

[0412] The individual generated AIs are uploaded by the server to an online sales platform. Users can visit this platform, purchase the AIs they are interested in, and download and use them on their devices. The purchase process is designed to be intuitive through the interface.

[0413] The profits from sold models are automatically calculated by the server and fed back to the creator of the generated AI according to a predetermined distribution ratio. The revenue distribution process is carried out accurately based on sales records, and payments are made quickly.

[0414] As a concrete example, let's assume a writer uploads their novel data. The server preprocesses this data and generates individual generative intelligences that mimic the writer's style. This model becomes available on a sales platform, where other users can purchase it and use it in their own creative activities. The profits generated in this process are returned to the writer through the system, providing an incentive for further writing.

[0415] The following describes the processing flow.

[0416] Step 1:

[0417] Users upload copyrighted works and transcripts of their statements to the system using their devices. The user interface guides the user and includes functions to verify the integrity of file formats and the type of data being processed.

[0418] Step 2:

[0419] The server collects uploaded data and, if necessary, gathers supplementary data from external sources. The server uses APIs to retrieve publicly available information from external databases.

[0420] Step 3:

[0421] The server performs preprocessing on the collected data. Preprocessing includes removing noise from the text data, correcting grammar and formatting, and preparing it in a format that is easy for generative models to learn from.

[0422] Step 4:

[0423] The server trains a generative model based on pre-processed data. During the training process, the existing generative model is fine-tuned to capture individual characteristic language patterns.

[0424] Step 5:

[0425] The server uploads the individually generated generative intelligences to the sales platform and configures them for user access. At this stage, model descriptions and introductory videos are also posted.

[0426] Step 6:

[0427] Users purchase generative intelligences of interest on the platform. An intuitive purchase flow is provided on the device, ensuring a secure payment process.

[0428] Step 7:

[0429] The server records sales performance and calculates profits based on sales. Profits are automatically calculated based on a set distribution ratio and distributed to the creator.

[0430] (Example 1)

[0431] 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."

[0432] Conventional systems for generating intelligent entities suffer from inefficient processes for collecting and pre-processing personal digital content, generating intelligent entities, and revenue sharing through sales. In particular, generating individual knowledge systems and effectively selling and utilizing them is difficult. Furthermore, there are issues with inadequate revenue sharing, preventing users from receiving fair compensation.

[0433] 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.

[0434] In this invention, the server includes means for collecting and pre-processing individual digital content, means for training a machine learning model using the pre-processed data to generate individual knowledge systems, and means for providing the generated individual knowledge systems on an online platform and distributing revenue based on their transaction performance. This enables the efficient and accurate generation of knowledge systems, and allows users who receive a fair share of the revenue to select and utilize the knowledge systems.

[0435] "Digital content" refers to electronic data such as text, images, audio, and video that can be created or accessed on a computer.

[0436] "Preprocessing" refers to the process of removing noise and correcting grammar in text data so that machine learning models can process the data efficiently.

[0437] A "machine learning model" refers to a computational model that has algorithms to automate a specific task based on input data and to predict or classify the results.

[0438] A "knowledge system" refers to a system that learns from collected data and can generate output with specific knowledge and style.

[0439] An "online platform" refers to a web-based marketplace provided over the internet where users can buy and sell digital goods.

[0440] "Revenue sharing" refers to the process of distributing profits earned from the sale of generated intelligences, etc., to the users and contributors involved.

[0441] This invention relates to a system that generates individual knowledge systems based on an individual's digital content and distributes profits by selling these systems. Specific embodiments are described below.

[0442] Users upload their digital content, such as documents and transcripts, to the system using their devices. To do this, users provide data through an intuitive user interface. These devices can be standard personal computers or smartphones.

[0443] The server collects relevant information not only from user input data but also from publicly available data sources on the internet. It uses online scraping techniques to aggregate data based on specified conditions. This process is necessary to collect a wide range of text information.

[0444] The collected data is preprocessed by the server and converted into a format that can be effectively trained by machine learning models. This preprocessing involves denoising, grammar correction, and normalization using Python's natural language processing libraries such as spacy and NLTK.

[0445] The server trains generative AI models using preprocessed data to generate individual knowledge systems. This process utilizes deep learning frameworks such as TensorFlow and PyTorch, performing data-driven learning. This results in models that reflect the writing style and thinking patterns of specific individuals.

[0446] The generated knowledge systems are uploaded to an online platform via a server. Users can visit this platform and select and purchase knowledge systems. The interface is designed to be user-friendly, and users can view text output samples and past evaluation reviews.

[0447] In revenue sharing, the server calculates sales based on the sales performance of the generated intelligent entities and distributes profits to users according to predetermined criteria. This process is automated, and the calculation results are notified to users via email or other means.

[0448] As a concrete example, an author uploads their novel data, and a knowledge system is generated based on that data. Then, by using a prompt message such as, "Please generate a short adventure story for children using this author's writing style," buyers can utilize the knowledge system. As a result, sales revenue is returned to the author, encouraging further creative activity.

[0449] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0450] Step 1:

[0451] Users upload digital content from their own devices. Specifically, they use the user interface to drag and drop or select their copyrighted works and transcripts to send them to the server. The system accepts data in text or PDF file format as input and saves it on the server as output.

[0452] Step 2:

[0453] The server collects data not only from data uploaded by users but also from publicly available information online. Specifically, it uses web scraping techniques to collect necessary text information. The input consists of URLs and online resources based on specified query conditions, and the output is the collected text data.

[0454] Step 3:

[0455] The server preprocesses the collected data. This involves using natural language processing libraries (e.g., spaCy or NLTK) to denoise, correct grammar, and normalize the text. The input is raw data, and the output is clear, preprocessed data.

[0456] Step 4:

[0457] The server trains a generative AI model using preprocessed data. It utilizes deep learning frameworks (e.g., TensorFlow or PyTorch) to generate individual knowledge systems. The input consists of preprocessed data and an AI algorithm, and the output is a model of a knowledge system that reflects the user's style.

[0458] Step 5:

[0459] The server uploads and publishes the generated knowledge system to an online platform. Here, the model overview and sample outputs are configured to be provided to users. The input is the knowledge system model file, and the output is published on the platform.

[0460] Step 6:

[0461] Users can visit the platform to purchase and utilize knowledge systems. Specifically, they can complete the purchase process and download the system using an intuitive interface. The input is the purchase procedure instructions, and the output is the downloaded model saved on the device.

[0462] Step 7:

[0463] The server calculates sales based on sales performance and distributes the profits to users. It automatically calculates based on sales records and makes payments according to pre-set criteria. The input is sales performance data, and the output is the calculated profits distributed to users.

[0464] (Application Example 1)

[0465] 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."

[0466] Traditional content generation systems struggled to create stories that adequately reflected individual user preferences, and lacked mechanisms for appropriately distributing revenue. As a result, personalized content experiences were not provided, and revenue sharing for creators was insufficient.

[0467] 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.

[0468] In this invention, the server includes means for collecting and pre-processing personal data collections; means for training a generative model using the pre-processed data and generating individual intelligent models; means for providing the generated individual intelligent models on an e-commerce platform and distributing profits based on their sales performance; and means for generating personalized stories based on the user's personal data and providing them on a visualization device. This enables the generation of unique stories that reflect the individual preferences of the user, as well as the rapid and accurate distribution of profits to creators.

[0469] A "personal data collection" is a collection of information related to an individual provided by a user, including the user's copyrighted works and records of their statements.

[0470] "Preprocessing" refers to the process of transforming data into a format suitable for training an AI model, and includes techniques such as noise reduction and data normalization.

[0471] A "generative model" is an artificial intelligence system that creates an intelligent entity that reflects the user's unique knowledge based on collected data.

[0472] An "intelligent model" is a model generated by AI that reflects the characteristics and style of individual users, and is used in a variety of applications.

[0473] An "e-commerce platform" is a system for selling and trading digital goods online, enabling users to purchase and download products.

[0474] A "visualization device" is a device used to provide generated content to users visually, and includes smartphones and head-mounted displays.

[0475] A "personalized story" is a narrative or story that is generated based on a user's personal preferences and data, making it unique to each individual user.

[0476] "Profit sharing" is the process of appropriately distributing the profits earned to the creators and developers of the generative model based on sales performance.

[0477] Specific embodiments for carrying out this invention are shown below.

[0478] The system is designed to allow users to upload their personal data collections via devices such as smartphones and computers. Data sets include personal copyrighted works and records of speech. A login user interface ensures easy and secure data provision.

[0479] The server receives the collected data and performs preprocessing such as denoising and data normalization. The preprocessed data is then trained using the AI ​​library TensorFlow to generate individual intelligent models. These models reflect the characteristics and styles of each individual user.

[0480] The generated intelligent models are managed on Amazon DynamoDB and uploaded to an e-commerce platform, where they become available for purchase. This platform features a user-friendly interface built with React Native, allowing buyers to intuitively select and download models.

[0481] This allows users to experience personalized stories using visualization devices such as smartphones and head-mounted displays. These stories are generated based on the user's preferences, enriching their experience.

[0482] As a concrete example, a user who enjoys fantasy can create their own adventure story using a model generated to mimic their favorite story style. For instance, they could enter a prompt like this: "Create an epic adventure story about the brave knight Eric searching for his lost sword in a magical forest." This allows the user to have a new storytelling experience.

[0483] Profits from sales are distributed to creators quickly and accurately. This is expected to further boost their creative motivation.

[0484] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0485] Step 1:

[0486] Users upload their personal data collections to the system using their smartphones or computers. This process involves the user logging in through the interface, selecting the files to upload, and pressing the submit button. Input data consists of text-based works and transcripts of speech, while output is raw data received on the server side.

[0487] Step 2:

[0488] The server preprocesses the received data collection. Specifically, it performs noise reduction, data normalization, and grammatical correction. The raw data acquired as input is converted into a noise-free format and shaped so that it can be easily trained by the AI ​​model. This results in clean, preprocessed data as output.

[0489] Step 3:

[0490] The server trains a generative model using pre-processed data. Here, TensorFlow is used to build a generative AI model based on the collected data. The input is formatted data, and the output is an intelligent model tailored to a specific user. This model reflects the user's style and characteristics.

[0491] Step 4:

[0492] The server saves the generated intelligent model to Amazon DynamoDB and uploads it to the e-commerce platform. At this time, sales information is registered on the platform and becomes viewable by users. The input is the newly generated intelligent model, and the output is in a state accessible on the online platform.

[0493] Step 5:

[0494] The user selects a generative model of interest on the platform and begins the download process. During the purchase process, the user selects a product via the interface, completes payment, and the model is downloaded to their device. The input is the user's selection information, and the output is the intelligent model stored on the user's device.

[0495] Step 6:

[0496] The device uses a downloaded intelligent model to generate stories based on the user's personal preferences. The user inputs prompts, and the model generates a story in response to those instructions. For example, if the prompt is "Create a story about the brave knight Eric's epic adventure to find his lost sword in a magical forest," the generation model will create a story based on the input prompt, resulting in a customized story.

[0497] 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.

[0498] This invention relates to a system equipped with an emotion engine that recognizes user emotions and optimizes the creation of individual generative intelligences and interactions accordingly. This system includes a series of processes from data collection to model generation, platform provision, and profit sharing, but by newly considering user emotions, it provides a more personalized experience.

[0499] When users upload their own works or transcripts using their devices, their emotional state at that time is analyzed by an emotion engine. This emotion analysis is performed, for example, by analyzing the intonation of their voice, their facial expressions, or the emotion of the input text. The server uses this emotion data to adjust the generative model to match the user's emotions and create an individualized generative intelligence.

[0500] The generated AIs possess a unique style that takes into account the user's emotions, and are provided to the platform in a format that other users can utilize based on that style. For example, a user who purchases an AI on the platform can have their emotions recognized in real time during interactions and receive responses accordingly. This makes interactions more natural and intimate.

[0501] The server recommends personalized generated intelligences by appropriately analyzing the emotions of users on the platform. If a user is feeling sad, it can recommend an intelligence that offers encouragement. This improvement in the user experience leads to increased sales of the selected intelligence.

[0502] As a concrete example, imagine a scenario where user A uploads data from writing a novel and has their motivation evaluated. The emotion engine measures user A's writing motivation and reflects it in the data, then generates a highly motivating generative intelligence based on that. This intelligence then generates positive and proactive responses to subsequent buyers, playing a role in increasing user A's brand value.

[0503] This system enables the creation and use of intelligent entities that respond to users' emotions, providing users with a more valuable experience, and also allows creators of intelligent entities to expand their market by offering diverse emotional settings.

[0504] The following describes the processing flow.

[0505] Step 1:

[0506] Users upload their own works and transcripts to the system using their devices. The user interface verifies the integrity of the file format and the type of data, while an emotion engine simultaneously analyzes the user's emotional state during the upload. This is done through voice input, text input, and webcam video.

[0507] Step 2:

[0508] The server collects uploaded data and stores it in a database along with the sentiment analysis results from the sentiment engine. The server also collects complementary information from other data sources, such as themes and styles of the user's past works.

[0509] Step 3:

[0510] The server performs preprocessing on the collected data and sentiment information. This preprocessing includes noise reduction, grammar correction, and adjustment of sentiment expression parameters, thereby preparing the data in a format suitable for training the generative model.

[0511] Step 4:

[0512] The server uses pre-processed data as input to train a generative model, generating individual generative intelligences that reflect the user's emotional information. During this learning process, the model's parameters are adjusted, enabling the generation of responses that prioritize specific emotional states.

[0513] Step 5:

[0514] The generated AIs are uploaded to the sales platform by the server and made publicly available for user access. Here, emotion-specific characteristics are introduced, allowing buyers to select an AI that suits their purpose.

[0515] Step 6:

[0516] The user, as the buyer, selects a generated intelligence on the platform and attempts to execute emotion-based scenarios. During the on-device interaction, the buyer's current emotional state is analyzed in real time to provide the most appropriate response.

[0517] Step 7:

[0518] The server records sales performance and calculates profits based on sales including added value derived from sentiment analysis. The profits are automatically returned to the creator of the generated intelligence according to a predetermined distribution ratio.

[0519] (Example 2)

[0520] 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."

[0521] In modern information technology, there is a growing demand in many fields to improve user experience through interaction with personalized artificial intelligence. However, conventional systems have not adequately considered the user's emotional state, limiting their ability to achieve natural and intimate communication with users. Furthermore, the lack of efficient methods for customizing and recommending generative intelligences has made it difficult to provide a more personalized experience.

[0522] 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.

[0523] In this invention, the server includes means for collecting and preprocessing a set of personal information; means for learning a generative model using the preprocessed information and generating individual generative intelligences; means for providing the generated individual generative intelligences on an e-commerce platform and distributing profits based on their transaction performance; means for analyzing the emotional state of a user obtained from a terminal and adjusting the generative model based on the analysis results; and means for analyzing the user's emotions in real time and optimizing the intelligence's response using the analysis results. This enables the customization of generative intelligences to match the user's emotions and real-time response optimization based on emotions.

[0524] An "information set" refers to a collection of data and information related to an individual, which includes text, audio, and image data.

[0525] "Preprocessing" refers to the process of converting collected raw data into a format suitable for analysis and model training.

[0526] A "generative model" refers to a data-driven computational model that uses machine learning algorithms to generate new data or responses.

[0527] A "generative intelligence" refers to an artificial intelligence program that is individually created using a generative model and interacts with the user.

[0528] An "e-commerce platform" refers to an online space for buying and selling digital products and services.

[0529] "Emotional state" refers to the user's psychological state and is analyzed through text, audio, and image data.

[0530] "Real-time analysis" refers to a process where data is processed and results are obtained immediately as soon as it is generated.

[0531] Users upload their personal information to the system using their devices. This information includes the user's copyrighted works, transcripts of their statements, audio data, and image data, and is used to analyze the user's emotional state.

[0532] The server receives the uploaded data set and performs initial preprocessing. This preprocessing includes removing unnecessary data and standardizing the data format. The server then analyzes the user's emotional state using emotion recognition technology. This analysis utilizes common speech recognition software for voice intonation analysis, video analysis software for facial expression analysis, and natural language processing software for text emotion analysis. Specifically, Google Cloud Natural Language API and Microsoft Azure Emotion API may be used.

[0533] Next, the server adjusts the generative model based on the analyzed sentiment data to create individual generative intelligences. Machine learning models such as ChatGPT and BERT are used for the generative model. These intelligences are then provided to users for use on the e-commerce platform. This allows the intelligences to generate responses tailored to the emotions of different users.

[0534] Furthermore, the server performs real-time analysis of the intelligent entities on the platform. The terminal sends user input to the server in real time, and emotions are analyzed on the spot. This immediacy makes it possible to make user interaction more natural and intimate.

[0535] For example, if a user inputs "I haven't felt like writing lately," the server analyzes the statement and adjusts its response to the AI. This provides an optimal response tailored to the user's emotions, resulting in a more personalized experience. An example of a prompt might be, "I recently started writing a novel, but how can I stay more motivated?" In response to this prompt, the AI ​​generates a positive response and provides valuable advice to the user.

[0536] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0537] Step 1:

[0538] Users upload their information to the system using a terminal. Input includes text data, audio data, and image data, which are sent to the server. The output is a structured dataset stored in the server-side database. This process involves specific actions such as file selection, form completion, and audio recording.

[0539] Step 2:

[0540] The server preprocesses the received data set. First, it removes unnecessary data and converts the format to a unified format. Data processing includes noise reduction, format conversion, and character encoding standardization. The output is a clean dataset suitable for analysis.

[0541] Step 3:

[0542] The server analyzes the user's emotional state using a clean dataset. The input is a pre-processed dataset, which is then analyzed by the emotion analysis engine. Data calculations include speech intonation analysis, facial expression recognition, and text sentiment analysis. The output is a result indicating the user's emotional state, which is stored in a dedicated table.

[0543] Step 4:

[0544] The server adjusts the generative AI model based on the sentiment analysis results. The input consists of the sentiment analysis results and the generative model; the model's parameters are customized to match the emotions. Data processing includes setting response style parameters and reorganizing the training data. The output is the adjusted generative intelligence.

[0545] Step 5:

[0546] The server publishes the generated intelligences on an e-commerce platform. The input is a pre-tuned generated intelligence, which is then deployed to the platform. Specific operations include sending data via APIs and creating profiles on the platform. The output is information about the published intelligences.

[0547] Step 6:

[0548] When a user interacts with an intelligent entity on the platform, the terminal sends input to the server in real time. The user's text or voice is sent as input in real time and analyzed by the server. The output is the analysis result, which is used for the intelligent entity's response.

[0549] Step 7:

[0550] The server generates an intelligent response based on the analysis results and returns it to the user. The input consists of real-time analysis results and a pre-tuned generative model, which then generates the response. Data processing includes natural language generation and sentiment filtering. The output is an optimized response presented to the user.

[0551] (Application Example 2)

[0552] 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."

[0553] Conventional generative intelligence systems have struggled to accurately reflect the emotional states of individual users, failing to provide personalized experiences. As a result, user interactions were often formal, making it difficult to achieve emotional satisfaction. Furthermore, the generated content did not always match the user's current emotional state, leading to a decline in the quality of the user experience.

[0554] 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.

[0555] In this invention, the server includes means for collecting and preprocessing individual datasets, means for training a generative model using the preprocessed data and generating individual generative intelligences, means for analyzing the user's emotions and selecting or adjusting content based on those emotions, and means for providing the adjusted generative intelligences on a platform for sale and distributing profits based on sales performance. This enables the delivery of personalized content that is tailored to the user's emotions.

[0556] A "personal dataset" is a collection of information related to a specific individual, and includes various data formats such as audio, text, and image data.

[0557] "Preprocessing" refers to the preparatory process of converting information within a dataset into a format suitable for analysis and training, and includes tasks such as noise reduction and normalization.

[0558] A "generative model" is a mathematical or algorithmic framework for generating new data or knowledge based on given input data.

[0559] A "generative intelligence" is an intelligent agent produced by a specific generative model, and its role is to support interaction with the user.

[0560] "Sentiment analysis" is a process that mechanically evaluates a user's emotional state from input voice, text, and image data.

[0561] "Content" refers to a portion of the information or media provided to users, and can be delivered in various forms such as music, video, and text.

[0562] A "sales platform" is an electronic market environment for trading generative intelligences as a value, providing a mechanism for users to select and purchase them.

[0563] "Profit sharing" refers to the process of appropriately distributing revenue earned based on sales performance among stakeholders.

[0564] This invention is a system that enables a more interactive content experience by providing a personalized generative intelligence that responds to the user's emotions. The server collects individual datasets and preprocesses them to prepare them for analysis. Specifically, it removes noise from audio, text, and image data and extracts the necessary information. This utilizes existing technologies such as OpenCV and the Google Cloud Speech-to-Text API.

[0565] Next, the server learns a generative model based on the pre-processed data. The generative model is typically implemented using machine learning algorithms to generate intelligent entities based on the user's individuality and emotional characteristics. These generated intelligent entities are then sold on a specific platform.

[0566] The device analyzes the user's emotions in real time from their voice, facial expressions, and text, and sends this information to the server. This allows the server to adjust and deliver optimal content to the user based on their current emotional state.

[0567] As a concrete example, in a content distribution service that users use daily, a system could be implemented that automatically recommends healing music or relaxing videos when an emotional state indicating fatigue is detected. This would allow users to have an experience that aligns with their emotions at that particular time.

[0568] The generative AI model requires a prompt, which is input as shown in the example below: "If the user is relaxed after work but showing signs of stress, list suitable content. Recommend calming movies or music."

[0569] This makes it possible to create a user experience optimized for emotions.

[0570] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0571] Step 1:

[0572] The device captures the user's voice, facial expressions, and text data in real time. This input data is acquired through the built-in microphone, camera, and text input interface. Because the acquired data is noisy, basic pre-processing is performed on the device.

[0573] Step 2:

[0574] Preprocessed data is sent from the terminal to the server. The server uses an emotion analysis system to analyze the user's emotional state based on the received data. This analysis uses a machine learning model to identify emotions from voice intonation, facial expressions, and text. The identified emotion information is obtained as output.

[0575] Step 3:

[0576] The server uses a generative AI model to generate or select content optimized for the user's emotions, based on the analyzed sentiment information. It uses prompts as input to instruct the generative AI model. The output is a list of content appropriate for the user's emotions.

[0577] Step 4:

[0578] The server sends a list of the retrieved content to the terminal. The terminal recommends content to the user's screen. The user can select and experience this recommended content. The server provides the user's selected content as output.

[0579] Step 5:

[0580] Users experience the provided content and send their feedback back to the server via their device. The server stores this feedback to use in training the next generational AI model. This feedback contributes to improving the accuracy of future sentiment analysis and content recommendation.

[0581] 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.

[0582] 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.

[0583] 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.

[0584] [Fourth Embodiment]

[0585] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0586] 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.

[0587] 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).

[0588] 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.

[0589] 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.

[0590] 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).

[0591] 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.

[0592] 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.

[0593] 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.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] 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".

[0598] This invention is a system that generates individual generative intelligences based on personal data and distributes profits through their sale. This system consists of the following stages: data collection, data preprocessing, model generation, model publication, sales, and profit distribution.

[0599] Users upload their own works and transcripts of statements to the system using their devices. This process includes a mechanism that allows for easy data provision through the user interface. The server collects necessary data from other data sources (e.g., publicly available online information) and aggregates the text information.

[0600] The collected data is preprocessed by the server and converted into a format suitable for AI training. This preprocessing includes noise reduction, grammar correction, and text normalization. The server then uses the preprocessed data to train a generative model, generating individual generative intelligences. This results in a model that reflects the style and thinking of a specific individual.

[0601] The individual generated AIs are uploaded by the server to an online sales platform. Users can visit this platform, purchase the AIs they are interested in, and download and use them on their devices. The purchase process is designed to be intuitive through the interface.

[0602] The profits from sold models are automatically calculated by the server and fed back to the creator of the generated AI according to a predetermined distribution ratio. The revenue distribution process is carried out accurately based on sales records, and payments are made quickly.

[0603] As a concrete example, let's assume a writer uploads their novel data. The server preprocesses this data and generates individual generative intelligences that mimic the writer's style. This model becomes available on a sales platform, where other users can purchase it and use it in their own creative activities. The profits generated in this process are returned to the writer through the system, providing an incentive for further writing.

[0604] The following describes the processing flow.

[0605] Step 1:

[0606] Users upload copyrighted works and transcripts of their statements to the system using their devices. The user interface guides the user and includes functions to verify the integrity of file formats and the type of data being processed.

[0607] Step 2:

[0608] The server collects uploaded data and, if necessary, gathers supplementary data from external sources. The server uses APIs to retrieve publicly available information from external databases.

[0609] Step 3:

[0610] The server performs preprocessing on the collected data. Preprocessing includes removing noise from the text data, correcting grammar and formatting, and preparing it in a format that is easy for generative models to learn from.

[0611] Step 4:

[0612] The server trains a generative model based on pre-processed data. During the training process, the existing generative model is fine-tuned to capture individual characteristic language patterns.

[0613] Step 5:

[0614] The server uploads the individually generated generative intelligences to the sales platform and configures them for user access. At this stage, model descriptions and introductory videos are also posted.

[0615] Step 6:

[0616] Users purchase generative intelligences of interest on the platform. An intuitive purchase flow is provided on the device, ensuring a secure payment process.

[0617] Step 7:

[0618] The server records sales performance and calculates profits based on sales. Profits are automatically calculated based on a set distribution ratio and distributed to the creator.

[0619] (Example 1)

[0620] 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".

[0621] Conventional systems for generating intelligent entities suffer from inefficient processes for collecting and pre-processing personal digital content, generating intelligent entities, and revenue sharing through sales. In particular, generating individual knowledge systems and effectively selling and utilizing them is difficult. Furthermore, there are issues with inadequate revenue sharing, preventing users from receiving fair compensation.

[0622] 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.

[0623] In this invention, the server includes means for collecting and pre-processing individual digital content, means for training a machine learning model using the pre-processed data to generate individual knowledge systems, and means for providing the generated individual knowledge systems on an online platform and distributing revenue based on their transaction performance. This enables the efficient and accurate generation of knowledge systems, and allows users who receive a fair share of the revenue to select and utilize the knowledge systems.

[0624] "Digital content" refers to electronic data such as text, images, audio, and video that can be created or accessed on a computer.

[0625] "Preprocessing" refers to the process of removing noise and correcting grammar in text data so that machine learning models can process the data efficiently.

[0626] A "machine learning model" refers to a computational model that has algorithms to automate a specific task based on input data and to predict or classify the results.

[0627] A "knowledge system" refers to a system that learns from collected data and can generate output with specific knowledge and style.

[0628] An "online platform" refers to a web-based marketplace provided over the internet where users can buy and sell digital goods.

[0629] "Revenue sharing" refers to the process of distributing profits earned from the sale of generated intelligences, etc., to the users and contributors involved.

[0630] This invention relates to a system that generates individual knowledge systems based on an individual's digital content and distributes profits by selling these systems. Specific embodiments are described below.

[0631] Users upload their digital content, such as documents and transcripts, to the system using their devices. To do this, users provide data through an intuitive user interface. These devices can be standard personal computers or smartphones.

[0632] The server collects relevant information not only from user input data but also from publicly available data sources on the internet. It uses online scraping techniques to aggregate data based on specified conditions. This process is necessary to collect a wide range of text information.

[0633] The collected data is preprocessed by the server and converted into a format that can be effectively trained by machine learning models. This preprocessing involves denoising, grammar correction, and normalization using Python's natural language processing libraries such as spacy and NLTK.

[0634] The server trains generative AI models using preprocessed data to generate individual knowledge systems. This process utilizes deep learning frameworks such as TensorFlow and PyTorch, performing data-driven learning. This results in models that reflect the writing style and thinking patterns of specific individuals.

[0635] The generated knowledge systems are uploaded to an online platform via a server. Users can visit this platform and select and purchase knowledge systems. The interface is designed to be user-friendly, and users can view text output samples and past evaluation reviews.

[0636] In revenue sharing, the server calculates sales based on the sales performance of the generated intelligent entities and distributes profits to users according to predetermined criteria. This process is automated, and the calculation results are notified to users via email or other means.

[0637] As a concrete example, an author uploads their novel data, and a knowledge system is generated based on that data. Then, by using a prompt message such as, "Please generate a short adventure story for children using this author's writing style," buyers can utilize the knowledge system. As a result, sales revenue is returned to the author, encouraging further creative activity.

[0638] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0639] Step 1:

[0640] Users upload digital content from their own devices. Specifically, they use the user interface to drag and drop or select their copyrighted works and transcripts to send them to the server. The system accepts data in text or PDF file format as input and saves it on the server as output.

[0641] Step 2:

[0642] The server collects data not only from data uploaded by users but also from publicly available information online. Specifically, it uses web scraping techniques to collect necessary text information. The input consists of URLs and online resources based on specified query conditions, and the output is the collected text data.

[0643] Step 3:

[0644] The server preprocesses the collected data. This involves using natural language processing libraries (e.g., spaCy or NLTK) to denoise, correct grammar, and normalize the text. The input is raw data, and the output is clear, preprocessed data.

[0645] Step 4:

[0646] The server trains a generative AI model using preprocessed data. It utilizes deep learning frameworks (e.g., TensorFlow or PyTorch) to generate individual knowledge systems. The input consists of preprocessed data and an AI algorithm, and the output is a model of a knowledge system that reflects the user's style.

[0647] Step 5:

[0648] The server uploads and publishes the generated knowledge system to an online platform. Here, the model overview and sample outputs are configured to be provided to users. The input is the knowledge system model file, and the output is published on the platform.

[0649] Step 6:

[0650] Users can visit the platform to purchase and utilize knowledge systems. Specifically, they can complete the purchase process and download the system using an intuitive interface. The input is the purchase procedure instructions, and the output is the downloaded model saved on the device.

[0651] Step 7:

[0652] The server calculates sales based on sales performance and distributes the profits to users. It automatically calculates based on sales records and makes payments according to pre-set criteria. The input is sales performance data, and the output is the calculated profits distributed to users.

[0653] (Application Example 1)

[0654] 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".

[0655] Traditional content generation systems struggled to create stories that adequately reflected individual user preferences, and lacked mechanisms for appropriately distributing revenue. As a result, personalized content experiences were not provided, and revenue sharing for creators was insufficient.

[0656] 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.

[0657] In this invention, the server includes means for collecting and pre-processing personal data collections; means for training a generative model using the pre-processed data and generating individual intelligent models; means for providing the generated individual intelligent models on an e-commerce platform and distributing profits based on their sales performance; and means for generating personalized stories based on the user's personal data and providing them on a visualization device. This enables the generation of unique stories that reflect the individual preferences of the user, as well as the rapid and accurate distribution of profits to creators.

[0658] A "personal data collection" is a collection of information related to an individual provided by a user, including the user's copyrighted works and records of their statements.

[0659] "Preprocessing" refers to the process of transforming data into a format suitable for training an AI model, and includes techniques such as noise reduction and data normalization.

[0660] A "generative model" is an artificial intelligence system that creates an intelligent entity that reflects the user's unique knowledge based on collected data.

[0661] An "intelligent model" is a model generated by AI that reflects the characteristics and style of individual users, and is used in a variety of applications.

[0662] An "e-commerce platform" is a system for selling and trading digital goods online, enabling users to purchase and download products.

[0663] A "visualization device" is a device used to provide generated content to users visually, and includes smartphones and head-mounted displays.

[0664] A "personalized story" is a narrative or story that is generated based on a user's personal preferences and data, making it unique to each individual user.

[0665] "Profit sharing" is the process of appropriately distributing the profits earned to the creators and developers of the generative model based on sales performance.

[0666] Specific embodiments for carrying out this invention are shown below.

[0667] The system is designed to allow users to upload their personal data collections via devices such as smartphones and computers. Data sets include personal copyrighted works and records of speech. A login user interface ensures easy and secure data provision.

[0668] The server receives the collected data and performs preprocessing such as denoising and data normalization. The preprocessed data is then trained using the AI ​​library TensorFlow to generate individual intelligent models. These models reflect the characteristics and styles of each individual user.

[0669] The generated intelligent models are managed on Amazon DynamoDB and uploaded to an e-commerce platform, where they become available for purchase. This platform features a user-friendly interface built with React Native, allowing buyers to intuitively select and download models.

[0670] This allows users to experience personalized stories using visualization devices such as smartphones and head-mounted displays. These stories are generated based on the user's preferences, enriching their experience.

[0671] As a concrete example, a user who enjoys fantasy can create their own adventure story using a model generated to mimic their favorite story style. For instance, they could enter a prompt like this: "Create an epic adventure story about the brave knight Eric searching for his lost sword in a magical forest." This allows the user to have a new storytelling experience.

[0672] Profits from sales are distributed to creators quickly and accurately. This is expected to further boost their creative motivation.

[0673] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0674] Step 1:

[0675] Users upload their personal data collections to the system using their smartphones or computers. This process involves the user logging in through the interface, selecting the files to upload, and pressing the submit button. Input data consists of text-based works and transcripts of speech, while output is raw data received on the server side.

[0676] Step 2:

[0677] The server preprocesses the received data collection. Specifically, it performs noise reduction, data normalization, and grammatical correction. The raw data acquired as input is converted into a noise-free format and shaped so that it can be easily trained by the AI ​​model. This results in clean, preprocessed data as output.

[0678] Step 3:

[0679] The server trains a generative model using pre-processed data. Here, TensorFlow is used to build a generative AI model based on the collected data. The input is formatted data, and the output is an intelligent model tailored to a specific user. This model reflects the user's style and characteristics.

[0680] Step 4:

[0681] The server saves the generated intelligent model to Amazon DynamoDB and uploads it to the e-commerce platform. At this time, sales information is registered on the platform and becomes viewable by users. The input is the newly generated intelligent model, and the output is in a state accessible on the online platform.

[0682] Step 5:

[0683] The user selects a generative model of interest on the platform and begins the download process. During the purchase process, the user selects a product via the interface, completes payment, and the model is downloaded to their device. The input is the user's selection information, and the output is the intelligent model stored on the user's device.

[0684] Step 6:

[0685] The device uses a downloaded intelligent model to generate stories based on the user's personal preferences. The user inputs prompts, and the model generates a story in response to those instructions. For example, if the prompt is "Create a story about the brave knight Eric's epic adventure to find his lost sword in a magical forest," the generation model will create a story based on the input prompt, resulting in a customized story.

[0686] 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.

[0687] This invention relates to a system equipped with an emotion engine that recognizes user emotions and optimizes the creation of individual generative intelligences and interactions accordingly. This system includes a series of processes from data collection to model generation, platform provision, and profit sharing, but by newly considering user emotions, it provides a more personalized experience.

[0688] When users upload their own works or transcripts using their devices, their emotional state at that time is analyzed by an emotion engine. This emotion analysis is performed, for example, by analyzing the intonation of their voice, their facial expressions, or the emotion of the input text. The server uses this emotion data to adjust the generative model to match the user's emotions and create an individualized generative intelligence.

[0689] The generated AIs possess a unique style that takes into account the user's emotions, and are provided to the platform in a format that other users can utilize based on that style. For example, a user who purchases an AI on the platform can have their emotions recognized in real time during interactions and receive responses accordingly. This makes interactions more natural and intimate.

[0690] The server recommends personalized generated intelligences by appropriately analyzing the emotions of users on the platform. If a user is feeling sad, it can recommend an intelligence that offers encouragement. This improvement in the user experience leads to increased sales of the selected intelligence.

[0691] As a concrete example, imagine a scenario where user A uploads data from writing a novel and has their motivation evaluated. The emotion engine measures user A's writing motivation and reflects it in the data, then generates a highly motivating generative intelligence based on that. This intelligence then generates positive and proactive responses to subsequent buyers, playing a role in increasing user A's brand value.

[0692] This system enables the creation and use of intelligent entities that respond to users' emotions, providing users with a more valuable experience, and also allows creators of intelligent entities to expand their market by offering diverse emotional settings.

[0693] The following describes the processing flow.

[0694] Step 1:

[0695] Users upload their own works and transcripts to the system using their devices. The user interface verifies the integrity of the file format and the type of data, while an emotion engine simultaneously analyzes the user's emotional state during the upload. This is done through voice input, text input, and webcam video.

[0696] Step 2:

[0697] The server collects uploaded data and stores it in a database along with the sentiment analysis results from the sentiment engine. The server also collects complementary information from other data sources, such as themes and styles of the user's past works.

[0698] Step 3:

[0699] The server performs preprocessing on the collected data and sentiment information. This preprocessing includes noise reduction, grammar correction, and adjustment of sentiment expression parameters, thereby preparing the data in a format suitable for training the generative model.

[0700] Step 4:

[0701] The server uses pre-processed data as input to train a generative model, generating individual generative intelligences that reflect the user's emotional information. During this learning process, the model's parameters are adjusted, enabling the generation of responses that prioritize specific emotional states.

[0702] Step 5:

[0703] The generated AIs are uploaded to the sales platform by the server and made publicly available for user access. Here, emotion-specific characteristics are introduced, allowing buyers to select an AI that suits their purpose.

[0704] Step 6:

[0705] The user, as the buyer, selects a generated intelligence on the platform and attempts to execute emotion-based scenarios. During the on-device interaction, the buyer's current emotional state is analyzed in real time to provide the most appropriate response.

[0706] Step 7:

[0707] The server records sales performance and calculates profits based on sales including added value derived from sentiment analysis. The profits are automatically returned to the creator of the generated intelligence according to a predetermined distribution ratio.

[0708] (Example 2)

[0709] 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".

[0710] In modern information technology, there is a growing demand in many fields to improve user experience through interaction with personalized artificial intelligence. However, conventional systems have not adequately considered the user's emotional state, limiting their ability to achieve natural and intimate communication with users. Furthermore, the lack of efficient methods for customizing and recommending generative intelligences has made it difficult to provide a more personalized experience.

[0711] 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.

[0712] In this invention, the server includes means for collecting and preprocessing a set of personal information; means for learning a generative model using the preprocessed information and generating individual generative intelligences; means for providing the generated individual generative intelligences on an e-commerce platform and distributing profits based on their transaction performance; means for analyzing the emotional state of a user obtained from a terminal and adjusting the generative model based on the analysis results; and means for analyzing the user's emotions in real time and optimizing the intelligence's response using the analysis results. This enables the customization of generative intelligences to match the user's emotions and real-time response optimization based on emotions.

[0713] An "information set" refers to a collection of data and information related to an individual, which includes text, audio, and image data.

[0714] "Preprocessing" refers to the process of converting collected raw data into a format suitable for analysis and model training.

[0715] A "generative model" refers to a data-driven computational model that uses machine learning algorithms to generate new data or responses.

[0716] A "generative intelligence" refers to an artificial intelligence program that is individually created using a generative model and interacts with the user.

[0717] An "e-commerce platform" refers to an online space for buying and selling digital products and services.

[0718] "Emotional state" refers to the user's psychological state and is analyzed through text, audio, and image data.

[0719] "Real-time analysis" refers to a process where data is processed and results are obtained immediately as soon as it is generated.

[0720] Users upload their personal information to the system using their devices. This information includes the user's copyrighted works, transcripts of their statements, audio data, and image data, and is used to analyze the user's emotional state.

[0721] The server receives the uploaded data set and performs initial preprocessing. This preprocessing includes removing unnecessary data and standardizing the data format. The server then analyzes the user's emotional state using emotion recognition technology. This analysis utilizes common speech recognition software for voice intonation analysis, video analysis software for facial expression analysis, and natural language processing software for text emotion analysis. Specifically, Google Cloud Natural Language API and Microsoft Azure Emotion API may be used.

[0722] Next, the server adjusts the generative model based on the analyzed sentiment data to create individual generative intelligences. Machine learning models such as ChatGPT and BERT are used for the generative model. These intelligences are then provided to users for use on the e-commerce platform. This allows the intelligences to generate responses tailored to the emotions of different users.

[0723] Furthermore, the server performs real-time analysis of the intelligent entities on the platform. The terminal sends user input to the server in real time, and emotions are analyzed on the spot. This immediacy makes it possible to make user interaction more natural and intimate.

[0724] For example, if a user inputs "I haven't felt like writing lately," the server analyzes the statement and adjusts its response to the AI. This provides an optimal response tailored to the user's emotions, resulting in a more personalized experience. An example of a prompt might be, "I recently started writing a novel, but how can I stay more motivated?" In response to this prompt, the AI ​​generates a positive response and provides valuable advice to the user.

[0725] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0726] Step 1:

[0727] Users upload their information to the system using a terminal. Input includes text data, audio data, and image data, which are sent to the server. The output is a structured dataset stored in the server-side database. This process involves specific actions such as file selection, form completion, and audio recording.

[0728] Step 2:

[0729] The server preprocesses the received data set. First, it removes unnecessary data and converts the format to a unified format. Data processing includes noise reduction, format conversion, and character encoding standardization. The output is a clean dataset suitable for analysis.

[0730] Step 3:

[0731] The server analyzes the user's emotional state using a clean dataset. The input is a pre-processed dataset, which is then analyzed by the emotion analysis engine. Data calculations include speech intonation analysis, facial expression recognition, and text sentiment analysis. The output is a result indicating the user's emotional state, which is stored in a dedicated table.

[0732] Step 4:

[0733] The server adjusts the generative AI model based on the sentiment analysis results. The input consists of the sentiment analysis results and the generative model; the model's parameters are customized to match the emotions. Data processing includes setting response style parameters and reorganizing the training data. The output is the adjusted generative intelligence.

[0734] Step 5:

[0735] The server publishes the generated intelligences on an e-commerce platform. The input is a pre-tuned generated intelligence, which is then deployed to the platform. Specific operations include sending data via APIs and creating profiles on the platform. The output is information about the published intelligences.

[0736] Step 6:

[0737] When a user interacts with an intelligent entity on the platform, the terminal sends input to the server in real time. The user's text or voice is sent as input in real time and analyzed by the server. The output is the analysis result, which is used for the intelligent entity's response.

[0738] Step 7:

[0739] The server generates an intelligent response based on the analysis results and returns it to the user. The input consists of real-time analysis results and a pre-tuned generative model, which then generates the response. Data processing includes natural language generation and sentiment filtering. The output is an optimized response presented to the user.

[0740] (Application Example 2)

[0741] 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".

[0742] Conventional generative intelligence systems have struggled to accurately reflect the emotional states of individual users, failing to provide personalized experiences. As a result, user interactions were often formal, making it difficult to achieve emotional satisfaction. Furthermore, the generated content did not always match the user's current emotional state, leading to a decline in the quality of the user experience.

[0743] 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.

[0744] In this invention, the server includes means for collecting and preprocessing individual datasets, means for training a generative model using the preprocessed data and generating individual generative intelligences, means for analyzing the user's emotions and selecting or adjusting content based on those emotions, and means for providing the adjusted generative intelligences on a platform for sale and distributing profits based on sales performance. This enables the delivery of personalized content that is tailored to the user's emotions.

[0745] A "personal dataset" is a collection of information related to a specific individual, and includes various data formats such as audio, text, and image data.

[0746] "Preprocessing" refers to the preparatory process of converting information within a dataset into a format suitable for analysis and training, and includes tasks such as noise reduction and normalization.

[0747] A "generative model" is a mathematical or algorithmic framework for generating new data or knowledge based on given input data.

[0748] A "generative intelligence" is an intelligent agent produced by a specific generative model, and its role is to support interaction with the user.

[0749] "Sentiment analysis" is a process that mechanically evaluates a user's emotional state from input voice, text, and image data.

[0750] "Content" refers to a portion of the information or media provided to users, and can be delivered in various forms such as music, video, and text.

[0751] A "sales platform" is an electronic market environment for trading generative intelligences as a value, providing a mechanism for users to select and purchase them.

[0752] "Profit sharing" refers to the process of appropriately distributing revenue earned based on sales performance among stakeholders.

[0753] This invention is a system that enables a more interactive content experience by providing a personalized generative intelligence that responds to the user's emotions. The server collects individual datasets and preprocesses them to prepare them for analysis. Specifically, it removes noise from audio, text, and image data and extracts the necessary information. This utilizes existing technologies such as OpenCV and the Google Cloud Speech-to-Text API.

[0754] Next, the server learns a generative model based on the pre-processed data. The generative model is typically implemented using machine learning algorithms to generate intelligent entities based on the user's individuality and emotional characteristics. These generated intelligent entities are then sold on a specific platform.

[0755] The device analyzes the user's emotions in real time from their voice, facial expressions, and text, and sends this information to the server. This allows the server to adjust and deliver optimal content to the user based on their current emotional state.

[0756] As a concrete example, in a content distribution service that users use daily, a system could be implemented that automatically recommends healing music or relaxing videos when an emotional state indicating fatigue is detected. This would allow users to have an experience that aligns with their emotions at that particular time.

[0757] The generative AI model requires a prompt, which is input as shown in the example below: "If the user is relaxed after work but showing signs of stress, list suitable content. Recommend calming movies or music."

[0758] This makes it possible to create a user experience optimized for emotions.

[0759] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0760] Step 1:

[0761] The device captures the user's voice, facial expressions, and text data in real time. This input data is acquired through the built-in microphone, camera, and text input interface. Because the acquired data is noisy, basic pre-processing is performed on the device.

[0762] Step 2:

[0763] Preprocessed data is sent from the terminal to the server. The server uses an emotion analysis system to analyze the user's emotional state based on the received data. This analysis uses a machine learning model to identify emotions from voice intonation, facial expressions, and text. The identified emotion information is obtained as output.

[0764] Step 3:

[0765] The server uses a generative AI model to generate or select content optimized for the user's emotions, based on the analyzed sentiment information. It uses prompts as input to instruct the generative AI model. The output is a list of content appropriate for the user's emotions.

[0766] Step 4:

[0767] The server sends a list of the retrieved content to the terminal. The terminal recommends content to the user's screen. The user can select and experience this recommended content. The server provides the user's selected content as output.

[0768] Step 5:

[0769] Users experience the provided content and send their feedback back to the server via their device. The server stores this feedback to use in training the next generational AI model. This feedback contributes to improving the accuracy of future sentiment analysis and content recommendation.

[0770] 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.

[0771] 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.

[0772] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0773] 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.

[0774] 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.

[0775] 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.

[0776] 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.

[0777] 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.

[0778] 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."

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] 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.

[0788] 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.

[0789] 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.

[0790] 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 as being incorporated by reference.

[0791] The following is further disclosed regarding the embodiments described above.

[0792] (Claim 1)

[0793] A means for collecting individual datasets and preprocessing said datasets,

[0794] A means for training a generative model using preprocessed data and generating individual generative intelligences,

[0795] A means of providing individually generated generative intelligences on a sales platform and distributing profits based on their sales performance,

[0796] A system that includes this.

[0797] (Claim 2)

[0798] The system according to claim 1, which trains the generative model using personal copyrighted works and transcripts of statements.

[0799] (Claim 3)

[0800] The system according to claim 1, which enables a purchaser to select and use a generated intelligent entity on the sales platform.

[0801] "Example 1"

[0802] (Claim 1)

[0803] means for collecting personal digital content and pre-processing said digital content,

[0804] A means for training a machine learning model using preprocessed data and generating individual knowledge systems,

[0805] A means of providing the generated individual knowledge systems on an online platform and distributing revenue based on their transaction performance,

[0806] A means of providing and purchasing digital content via a user interface,

[0807] A means for calculating revenue through an automated process and allocating it to users based on predetermined criteria,

[0808] A system that includes this.

[0809] (Claim 2)

[0810] The system according to claim 1, which trains the machine learning model using an individual's language data or language records.

[0811] (Claim 3)

[0812] The system according to claim 1, which enables a user to select and access a knowledge system on the aforementioned online platform.

[0813] "Application Example 1"

[0814] (Claim 1)

[0815] means for collecting personal data collections and preprocessing said data collections,

[0816] A means for training a generative model using preprocessed data and generating individual intelligent models,

[0817] A means of providing the generated individual intelligent models on an e-commerce platform and distributing profits based on their sales performance,

[0818] A means of generating personalized stories based on users' personal data and providing them on visualization devices,

[0819] A system that includes this.

[0820] (Claim 2)

[0821] The system according to claim 1, which trains the generative model using personal creative works and records of statements.

[0822] (Claim 3)

[0823] The system according to claim 1, which enables a buyer to select and use an intelligent model on the aforementioned e-commerce platform.

[0824] "Example 2 of combining an emotion engine"

[0825] (Claim 1)

[0826] A means for collecting a set of personal information and preprocessing the set of information,

[0827] A means for training a generative model using preprocessed information and generating individual generative intelligences,

[0828] A means of providing individually generated generative intelligences on an e-commerce platform and distributing profits based on their transaction performance,

[0829] A means for analyzing the user's emotional state obtained from the terminal and adjusting the generative model based on the analysis results,

[0830] A means for analyzing user emotions in real time and optimizing the response of an intelligent entity using the analysis results,

[0831] A system that includes this.

[0832] (Claim 2)

[0833] The system according to claim 1, which trains the generative model using personal creative works and records of statements.

[0834] (Claim 3)

[0835] The system according to claim 1, which enables a user to select and use a generated intelligent entity in the aforementioned e-commerce platform.

[0836] "Application example 2 when combining with an emotional engine"

[0837] (Claim 1)

[0838] A means for collecting individual datasets and preprocessing said datasets,

[0839] A means for training a generative model using preprocessed data and generating individual generative intelligences,

[0840] A means for analyzing the user's emotions and selecting or adjusting content based on those emotions,

[0841] A platform for selling modified generative intelligences, and a means of distributing profits based on sales performance,

[0842] A system that includes this.

[0843] (Claim 2)

[0844] The system according to claim 1, which uses personal copyrighted works and transcripts of statements to train the generative model and provides content suitable for the emotion.

[0845] (Claim 3)

[0846] The system according to claim 1, which enables a buyer to select and use a generative intelligence based on recommendations derived from sentiment analysis on the sales platform. [Explanation of Symbols]

[0847] 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 for collecting individual datasets and preprocessing said datasets, A means for training a generative model using preprocessed data and generating individual generative intelligences, A means of providing individually generated generative intelligences on a sales platform and distributing profits based on their sales performance, A system that includes this.

2. The system according to claim 1, which trains the generative model using personal copyrighted works and transcripts of statements.

3. The system according to claim 1, which enables a purchaser to select and use a generated intelligent entity on the sales platform.

Images