System

Abstract

A system is provided.SOLUTION: A system comprising: means for obtaining a personal profile; means for training a production AI; means for recommending an optimal entertainment feature for a user based on the profile; means for providing additional content related to the recommended feature; means for managing a monthly subscription for the user; and means for targeting advertising based on the profile of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In recent years, entertainment options have become increasingly diverse, making it extremely difficult for users to find works that suit their preferences. In particular, the options in genres such as movies and comics are vast, forcing users to expend a great deal of time and effort to find works that suit their preferences. Furthermore, existing recommendation systems often do not adequately reflect user preferences and produce unsatisfactory results. The present invention aims to solve these problems and provide a more personalized entertainment experience. [Means for solving the problem]

[0005] The present invention solves these problems with a system that includes a means for acquiring personal profile data, a means for training a generating AI, a means for recommending optimal entertainment works to users based on the profile data, a means for providing additional content related to the recommended works, a means for managing monthly subscriptions for users, and a means for targeting advertisements based on the user's profile data. Specifically, users input their preferences and past viewing history, and the AI ​​uses that data to accurately recommend the most suitable works. Furthermore, by providing additional information about the works, such as comments and interviews from directors and writers, users can enjoy the works more deeply. Furthermore, by integrating monthly subscription management and the display of targeted advertisements, the system aims to strengthen the revenue model and improve user satisfaction.

[0006] "Profile Data" is a set of information about an individual user, such as the preferences the user has entered and past browsing history.

[0007] "Generative AI" is an artificial intelligence algorithm that learns patterns from collected data and generates optimal recommendations for users.

[0008] "Recommendation" is the act of suggesting suitable entertainment works to a user based on the user's profile data.

[0009] "Entertainment works" refers to content for users to enjoy, such as movies, manga, anime, and dramas.

[0010] "Additional Content" refers to additional information that accompanies a recommended entertainment piece, such as commentary from directors or writers, interviews, behind-the-scenes information, and the like.

[0011] A "monthly subscription" is a service model in which access to premium content is obtained by paying a set fee for a specific period of time.

[0012] "Targeted advertising" is a method of displaying advertisements optimized for a user based on the user's profile data.

[0013] "Database" means a system for systematically storing and managing user profile data and other related information. [Brief explanation of the drawings]

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

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

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

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

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

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

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

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

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0035] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized manga and movie recommendations. This system selects the most suitable works based on the user's past viewing history and preferences, and also provides additional information such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[0036] User profile data collection

[0037] 1. A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[0038] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[0039] 2. The device sends the user's input information to the server.

[0040] The terminal sends the entered data to the server as a JSON formatted payload.

[0041] 3. The server stores the received user data in a database.

[0042] The server analyzes the received data and stores it in the appropriate tables. For example, the user's basic information is stored in the "users" table, and the browsing history is stored in the "viewing_history" table.

[0043] Creating and training AI models

[0044] 1. The server trains the AI ​​model using user data in the database.

[0045] The server periodically extracts and pre-processes the data.

[0046] 2. The server uses common machine learning algorithms (e.g., deep learning) to generate a model based on the user's preferences.

[0047] Evaluate the accuracy of the model and adjust parameters or retrain as needed.

[0048] 3. The server deploys the trained model and incorporates it into the recommender system.

[0049] Once deployed, the model quickly generates recommendations upon request.

[0050] Providing recommendations

[0051] 1. A user logs in to the system and requests "new recommended works."

[0052] After logging in, you will be able to request recommendations on your dashboard.

[0053] 2. The device sends a recommendation request to the server.

[0054] Send the request data along with the user ID.

[0055] 3. The server uses an AI model to select works that match the user's preferences and generate recommendation results.

[0056] For example, if a user likes "horror movies," they can select "A," "B," or "C" from the latest horror movies.

[0057] 4. The server sends the recommendation results to the device.

[0058] JSON data including the work title, thumbnail, description, etc. is returned.

[0059] 5. The device displays the recommendation results to the user.

[0060] The user interface displays information about movies "A," "B," and "C."

[0061] Providing additional content

[0062] 1. The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[0063] We regularly obtain additional information from partner media and APIs.

[0064] 2. Display this additional content on the details page of the title for which your device was recommended.

[0065] For example, it provides users with comments and interviews from the director of movie "A."

[0066] Managing your monthly subscription

[0067] 1. A user wants access to premium content and signs up for a monthly subscription.

[0068] Enter your payment information and start your subscription.

[0069] 2. The terminal sends the payment information to the server and processes the payment.

[0070] 3. The server receives the payment processing result and updates the user's subscription status.

[0071] Updates the user status in the database to "active".

[0072] 4. The device displays a successful subscription notification to the user.

[0073] Advertising and Event Management

[0074] 1. The server receives advertising information from advertisers and production companies.

[0075] Store advertising materials provided by advertisers and save them in a database.

[0076] 2. The server selects appropriate ads based on the user's profile data.

[0077] Select targeted advertising based on your interests.

[0078] 3. The device displays appropriate advertisements in the user's interface.

[0079] Display targeted ads on your dashboard and product detail pages.

[0080] The above is a specific embodiment for carrying out the present invention. As a result, in a world where entertainment options are becoming more diverse, it is possible to recommend the most suitable works to users, enabling them to enjoy a deeper entertainment experience.

[0081] The processing flow will be explained below.

[0082] User profile data collection

[0083] Step 1:

[0084] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[0085] Step 2:

[0086] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[0087] Step 3:

[0088] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[0089] Creating and training AI models

[0090] Step 1:

[0091] The server periodically queries and extracts all user data stored in the database.

[0092] Step 2:

[0093] The server preprocesses the extracted data to generate a training dataset for the AI ​​model, including data cleaning and feature engineering.

[0094] Step 3:

[0095] The server runs machine learning algorithms (e.g., deep learning) to train an AI model based on user preferences.

[0096] Step 4:

[0097] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[0098] Step 5:

[0099] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[0100] Providing recommendations

[0101] Step 1:

[0102] A user logs into the system and requests "new recommended works."

[0103] Step 2:

[0104] The device sends the login user ID and recommendation request data to the server.

[0105] Step 3:

[0106] Based on the request data received by the server, a trained AI model is called up to select works that match the user's preferences.

[0107] Step 4:

[0108] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[0109] Step 5:

[0110] The device displays the recommendation results on the user interface.

[0111] Providing additional content

[0112] Step 1:

[0113] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[0114] Step 2:

[0115] The device will display this additional content to users on the details page of the recommended title.

[0116] Managing your monthly subscription

[0117] Step 1:

[0118] A user enters payment information to purchase a monthly subscription to access premium content.

[0119] Step 2:

[0120] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[0121] Step 3:

[0122] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[0123] Step 4:

[0124] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[0125] Step 5:

[0126] The device displays a successful subscription notification to the user.

[0127] Advertising and Event Management

[0128] Step 1:

[0129] The server receives advertising information from advertisers and production companies and stores it in a database.

[0130] Step 2:

[0131] The server selects appropriate ads based on the user's profile data.

[0132] Step 3:

[0133] The device displays targeted advertisements in the user interface.

[0134] Example 1

[0135] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0136] In today's entertainment industry, it is difficult for users to find the most suitable titles from the vast number of titles available. It is also not easy to provide additional content and advertisements that match users' interests. Furthermore, as user preferences change over time, AI models must be continuously updated. A method to solve these problems is needed.

[0137] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0138] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending entertainment works that are most suitable for the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for processing recommendation requests based on the user's visit history and preferences, means for providing comments and interviews from related creators as additional content, and means for periodically extracting user data from a database and updating the generative AI model. This allows users to easily find entertainment works and related content that suit their preferences. The user experience is also improved through individually optimized advertisements and continuously updated recommendations.

[0139] "Personal profile data" refers to data that includes a user's preferences, past browsing history, viewing history, personal information, etc.

[0140] "Generative AI" is an artificial intelligence model trained using user profile data to recommend entertainment content based on user preferences.

[0141] "Recommendation" is the act of recommending the most suitable entertainment works based on the user's profile data.

[0142] "Additional content" refers to additional information related to the recommended work, such as comments and interviews from directors and writers, and behind-the-scenes information.

[0143] A "monthly subscription" is a subscription system that allows users to access certain services or additional content by paying a fixed monthly fee.

[0144] "Targeting ads" means using a user's profile data to select and display ads that are most relevant to that user.

[0145] "Visit history" is a record of the pages and content a user has accessed within the system.

[0146] A "recommendation request" is a request from a user to the system for new recommendations.

[0147] "Updating using generative AI models" means continually retraining the artificial intelligence model with the latest user data to keep improving its accuracy.

[0148] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized entertainment recommendations and related additional content. Specific embodiments for implementing the present invention are described below.

[0149] User profile data collection

[0150] A user accesses the system and enters their preferences and past browsing history into a new registration form. For example, they might enter information such as "I like horror movies," "I often read suspense manga," or "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which then stores the received data in a database. This data is primarily exchanged using the JSON format.

[0151] Creating and training AI models

[0152] The server trains the AI ​​model using user data stored in the database. Specifically, it preprocesses the data using Python and deep learning frameworks such as TensorFlow and PyTorch, and then builds and trains the model. It periodically extracts data from the database and uses the generative AI model to update the model. This ensures that the model is always up to date with new user preferences.

[0153] Providing recommendations

[0154] A user logs in to the system and requests "new recommended movies." The device sends the recommendation request to the server, which uses an AI model to select movies that match the user's preferences. For example, if the user likes "horror movies," they can select "A," "B," and "C" from the latest horror movies. The server sends the recommendation results to the device, which then displays them to the user.

[0155] Providing additional content

[0156] The server retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, it might provide the user with comments and interviews from the director of film "A."

[0157] Managing your monthly subscription

[0158] A user wants access to premium content and signs up for a monthly subscription. The user enters payment information, which the device sends to the server for payment processing. The server receives the payment processing result, updates the user's subscription status, and the device displays a successful subscription notification to the user.

[0159] Advertising and Event Management

[0160] The server receives advertising information from advertisers and production companies and selects appropriate advertisements based on the user's profile data. The device displays the appropriate advertisements on the user's interface. In this way, the user can also be provided with other commercial information.

[0161] Examples of concrete examples and prompts

[0162] As a concrete example, the system may recommend the latest horror movies "X," "Y," and "Z" to User A, who previously registered that he "likes horror movies." It may also be possible to provide an interview with the author of the manga "Psychic Battle" as additional premium content.

[0163] Examples of prompts include:

[0164] "Recommend three horror movies based on the user's preferences."

[0165] "Please display an interview with the author of the manga 'Psychic Battle' as premium content."

[0166] This allows the present invention to optimize users' entertainment choices and provide additional value, and it also makes it possible to realize attractive services for users through targeted advertising and subscription management.

[0167] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0168] Step 1:

[0169] A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[0170] Input: New registration form, user preferences and browsing history

[0171] Specific actions: Enter information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C" into a web browser or mobile app.

[0172] Output: User information entered

[0173] Step 2:

[0174] The terminal transmits the user's input information to the server.

[0175] Input: Information entered by the user

[0176] Specific operation: Front-end code (JavaScript or Swift) converts the input information into JSON format and sends it to the server via an HTTPS request.

[0177] Output: JSON data sent to the server

[0178] Step 3:

[0179] The server stores the received user data in a database.

[0180] Input: JSON data sent from the terminal

[0181] What it does: The server uses backend code (Python or Node.js) to parse the incoming data, generate appropriate SQL queries, and store the data in a MySQL or PostgreSQL database.

[0182] Output: User data stored in the database

[0183] Step 4:

[0184] The server trains the AI ​​model using user data in the database.

[0185] Input: Raw data in the database

[0186] What it does: Use Python and TensorFlow or PyTorch to preprocess data and train a deep learning model, including the training and evaluation processes.

[0187] Output: A trained AI model

[0188] Step 5:

[0189] The server uses the generated AI model to generate recommendation results.

[0190] Input: A trained AI model and specific user data

[0191] How it works: User data is input into the AI ​​model to generate recommendations. For example, it recommends the latest horror movies to a user who likes "horror movies."

[0192] Output: Recommendation results

[0193] Step 6:

[0194] The server sends the recommendation results to the terminal.

[0195] Input: Generated recommendation results

[0196] Specific operation: The server converts the recommendation results into JSON format and sends them to the terminal as an HTTP response.

[0197] Output: Recommendation results sent to the device

[0198] Step 7:

[0199] The device displays the recommendation results to the user.

[0200] Input: JSON data received from the server

[0201] Specific operation: The front end parses the received data and displays information such as movies "A", "B", and "C" in the user interface.

[0202] Output: Recommendation results displayed to the user

[0203] Step 8:

[0204] The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[0205] Input: Additional information from external media or API

[0206] Specific operation: The server periodically obtains information using the API of the partner media and stores the obtained additional information in a database.

[0207] Output: Additional content stored in the database

[0208] Step 9:

[0209] The device will display this additional content on the details page of the recommended title.

[0210] Input: Additional content data obtained from the server

[0211] What happens: The front-end renders the additional content information on the detail page and displays it to the user.

[0212] Output: Additional content displayed on the details page

[0213] Step 10:

[0214] A user wants access to premium content and signs up for a monthly subscription.

[0215] Input: Premium content request and payment information

[0216] What it does: The user enters payment information and presses a button to start a monthly subscription.

[0217] Output: Subscription registration request

[0218] Step 11:

[0219] The terminal transmits the payment information to the server, which processes the payment.

[0220] Input: User's payment information

[0221] What it does: The terminal securely encodes the payment information and sends an HTTPS request to the server, which then processes the payment using the Stripe or PayPal API.

[0222] Output: Payment processing result

[0223] Step 12:

[0224] The server receives the payment transaction result and updates the user's subscription status.

[0225] Input: Payment processing result data

[0226] Specific behavior: The server receives the payment success response and updates the user's subscription status in the database to "active."

[0227] Output: Updated subscription status

[0228] Step 13:

[0229] The device will display a successful subscription notification to the user.

[0230] Input: Subscription status update

[0231] What happens: The front end displays a "Subscription successful" notification to the user.

[0232] Output: Success notification displayed to the user

[0233] Step 14:

[0234] The server receives advertising information from advertisers and production companies.

[0235] Input: Advertising data from advertisers and production companies

[0236] Specific operation: Uses the API provided by the advertiser to obtain advertising materials and save them in a database.

[0237] Output: Ad data stored in a database

[0238] Step 15:

[0239] The server selects appropriate advertisements based on the user's profile data.

[0240] Input: User profile data

[0241] What it does: The server analyzes user data and uses targeting algorithms to select appropriate ads.

[0242] Output: Selected advertising data

[0243] Step 16:

[0244] The device displays appropriate advertisements in the user's interface.

[0245] Input: Selected advertising data

[0246] What happens: The front-end renders the ad data into the interface and displays it to the user.

[0247] Output: The ad shown to the user

[0248] The above is the specific processing flow of the program of this system.

[0249] (Application example 1)

[0250] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0251] Today's entertainment consumers face challenges in finding content that suits their tastes among a wide variety of options, often lacking additional information to maximize the appeal of a content, and face the problem of insufficient integration between targeting advertising and payment management systems based on user preferences, resulting in an inconsistent and optimized user experience.

[0252] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0253] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending optimal entertainment works to the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for providing a visually easy-to-understand user interface on a smartphone, and means for notifying the user when new recommendations are available. This improves the ease of discovering entertainment works and maximizes the appeal of the works by providing additional information. It also consistently optimizes the user experience and enables effective targeted advertising and payment management.

[0254] "Personal profile data" refers to a set of information that a user has about themselves, including their preferences, past browsing history, and behavioral patterns.

[0255] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to learn patterns from users' profile data and generate appropriate recommendations.

[0256] "Entertainment works" refers to movies, comics, television programs, music, and other media content that users view or consume.

[0257] "Recommendation" refers to the act or result of recommending the most suitable entertainment content based on a user's preferences.

[0258] "Additional Content" refers to supplemental information, such as commentary, interviews, and behind-the-scenes information, related to an entertainment production.

[0259] "Monthly Subscription" refers to a subscription format that allows users to access premium content or services in exchange for a recurring payment.

[0260] "Targeted advertising" refers to the practice of displaying the most relevant advertisements to individual users based on their profile data.

[0261] A "smartphone" refers to a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[0262] "User interface" refers to the screen layout and operation methods used by users to interact with a system.

[0263] "Notification" refers to the act of the system informing the user that new information or recommendations are available.

[0264] This invention is a system that combines user profile data with a generative AI model to recommend customized entertainment works to users. It also provides additional content related to the recommended works, enriching the user's entertainment experience. Specific embodiments for implementing this invention are described below.

[0265] Profile Data Collection

[0266] Users access the system and enter information such as their preferences and past browsing history into a new registration form. For example, they provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which analyzes the received data and stores it in a database. For example, the user's basic information is stored in the users table, and their browsing history is stored in the viewing_history table.

[0267] Creating and training AI models

[0268] The server uses the user data in the database to train an AI model using machine learning algorithms (e.g., deep learning). This AI model is then used to recommend entertainment items based on the user's preferences. The trained AI model is then deployed to a recommender system, which quickly generates recommendation results upon request.

[0269] Providing recommendations

[0270] When a user logs in to the system and requests "new recommended titles," the device sends the request data along with the user ID to the server. The server uses an AI model to select titles that match the user's preferences and generates recommendation results. These results include titles, thumbnails, descriptions, etc., which the device displays to the user. The system also has a function to notify the user when new recommendations are available.

[0271] Providing additional content

[0272] The server periodically retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, the device can provide the user with comments and interviews from the director of film "A."

[0273] Managing your monthly subscription

[0274] If a user wants access to premium content, they sign up for a monthly subscription. Payment information is sent from the device to the server, which processes the payment. Based on the transaction result, the user's subscription status is updated in the database.

[0275] Advertising and Event Management

[0276] The server receives advertising information from advertisers and production companies and selects appropriate ads based on user profile data, allowing it to provide the most relevant ads to each individual user.

[0277] Examples and prompts

[0278] If a user says "I like horror movies" and enters "Movies I've recently seen are A, B, and C":

[0279] Register with user ID 123

[0280] Submit a recommendation request

[0281] AI recommends "latest horror movies D, E, F"

[0282] Also displays additional information including director comments and interviews

[0283] Example prompt sentence:

[0284] Input: User likes horror movies and requests new movie recommendations based on recently watched movies A, B, and C.

[0285] Output: A list of the latest horror movies D, E, F with additional information about them (director comments, interviews, etc.).

[0286] Using this system, users can be provided with the most suitable entertainment content, enriching their entertainment experience.

[0287] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0288] Step 1:

[0289] A user accesses the system and enters information such as their preferences and past viewing history into a new registration form. Input content includes "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input data to the server in JSON format. As data input, the user provides their preferred entertainment genre and past viewing history information, and as output, the data is transferred to the server in JSON format.

[0290] Step 2:

[0291] The server parses the received user profile data and stores basic information in the users table and browsing history in the viewing_history table in the database. The server receives the JSON data, parses its contents, and executes queries to store them in the appropriate tables. The input to this step is the user's JSON data, and the output is the creation of a record in the database.

[0292] Step 3:

[0293] The server extracts user profile data from the database and uses a generative AI model to train a recommendation model. A machine learning algorithm (e.g., deep learning) is used to learn patterns based on the profile data. The trained model results undergo accuracy evaluation and parameter adjustment before finally being deployed. The input is user data from the database, and the output is the trained AI model.

[0294] Step 4:

[0295] A user logs in to the system and requests new recommendations. The device sends the user ID and request data to the server. The input for this step is the user's request information, and the request content is sent to the server.

[0296] Step 5:

[0297] The server uses a trained AI model to recommend entertainment works that match the user's preferences. If the user likes "horror movies," it will select several of the latest horror movies. Specifically, the AI ​​model receives the user's profile data as input, generates a list of entertainment works, and returns it to the device in JSON format. The recommendation results are output from the server.

[0298] Step 6:

[0299] The device receives the recommendation results from the server and displays them to the user as a visually easy-to-understand user interface, showing the title, thumbnail, description, etc. of the recommended works. The input to this step is JSON data from the server, and the output is a visually structured display.

[0300] Step 7:

[0301] The server periodically retrieves comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database. Additional information is obtained from partner media and APIs and added to the database. The input to this step is external information data, and storing it in the database is the output.

[0302] Step 8:

[0303] The device displays additional content such as comments and interviews from the director and writer on the details page of the recommended work. Providing comments and interviews from the director of movie "A" provides the user with a deeper entertainment experience. The input of this step is additional information from the database, and the display on the details page is the output.

[0304] Step 9:

[0305] A user wants access to premium content and signs up for a monthly subscription from their device. Payment information is entered and sent from the device to the server. The input to this step is the user's payment information, and the output is the data sent to the server.

[0306] Step 10:

[0307] The server processes the received payment information and updates the user's subscription status in the database. For example, it updates the user's status in the database to "active". The input to this step is the payment information and the output is the status update in the database.

[0308] Step 11:

[0309] The server selects appropriate targeted advertisements based on the user's profile data. The server extracts the user's interests from the profile data stored on the server and selects targeted advertisements based on them. The input for this step is the profile data, and the selected advertisement information is the output.

[0310] Step 12:

[0311] The device displays appropriate advertisements on the user's interface. Targeted advertisements are visually displayed on the dashboard or product detail page. The input of this step is the advertisement information from the server, and the display on the device is the output.

[0312] These processing steps improve entertainment discovery, maximize the appeal of entertainment content by providing additional information, and consistently optimize the user experience, enabling effective targeted advertising and payment management.

[0313] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0314] The present invention is a system that combines personal profile data with generative AI and uses an emotion engine to recognize a user's emotions in real time, providing a customized entertainment experience. The system uses real-time emotion data in addition to the user's past viewing history and preferences to select the most suitable works. It also provides additional information, such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[0315] User profile data collection

[0316] 1. A user accesses the system and fills in a new registration form with information about their preferences and past browsing history.

[0317] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[0318] 2. The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[0319] 3. The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[0320] Combining Emotion Engines

[0321] 1. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice.

[0322] For example, it analyzes the user's facial expressions and tone of voice while they are watching a movie and recognizes emotions such as "surprise," "joy," and "fear."

[0323] 2. The device transmits the acquired emotion data to the server.

[0324] 3. The server integrates the received emotion data into the profile data and stores it in a database.

[0325] Creating and training AI models

[0326] 1. The server periodically queries and extracts all user and sentiment data stored in the database.

[0327] The emotion data and profile data are combined to generate a training dataset.

[0328] 2. The server runs a machine learning algorithm (e.g., deep learning) to train an AI model that includes the emotion data.

[0329] 3. The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[0330] 4. The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[0331] Providing recommendations

[0332] 1. A user logs in to the system and requests "new recommended works."

[0333] 2. The device sends the login user ID and recommendation request data to the server.

[0334] 3. The server uses an AI model to select the most suitable work based on the profile data and emotional data.

[0335] For example, based on past browsing history and current emotional data, the app will suggest "comedy movies" when the user is "relaxed," and "action movies" when the user is "stressed."

[0336] 4. The server constructs the recommendation results in JSON format and returns them to the device.

[0337] 5. The device displays the recommendation results on the user interface.

[0338] Providing additional content

[0339] 1. The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[0340] 2. Display this additional content to users on the details page of the title for which the device was recommended.

[0341] Managing your monthly subscription

[0342] 1. A user enters payment information to purchase a monthly subscription to access premium content.

[0343] 2. The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[0344] 3. The server processes the received payment information in cooperation with the payment gateway and receives the result.

[0345] 4. If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[0346] 5. The device displays a successful subscription notification to the user.

[0347] Advertising and Event Management

[0348] 1. The server receives advertising information from advertisers and production companies and stores it in a database.

[0349] 2. The server selects appropriate ads based on the user's profile data and emotional data.

[0350] For example, when a user is "excited," ads for related action movies might be shown, and when a user is "relaxed," ads for comedy movies might be shown.

[0351] 3. The device displays targeted ads in the user interface.

[0352] The above is a specific embodiment for implementing the present invention. As entertainment options become more diverse, this allows users to recommend the most suitable works and enjoy the entertainment experience more deeply. By combining it with an emotion engine, the degree of customization of the user experience can be further increased.

[0353] The processing flow will be explained below.

[0354] User profile data collection

[0355] Step 1:

[0356] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[0357] Step 2:

[0358] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[0359] Step 3:

[0360] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[0361] Combining Emotion Engines

[0362] Step 1:

[0363] Using the device's built-in camera and microphone, emotional data is collected in real time from the user's facial expressions and voice.

[0364] Step 2:

[0365] The device analyzes the emotional data it acquires and classifies emotions such as "joy," "surprise," and "sadness."

[0366] Step 3:

[0367] The device sends the analysis results to the server as a JSON format payload.

[0368] Step 4:

[0369] The server integrates the received emotion data into the profile data and stores it in a database.

[0370] Creating and training AI models

[0371] Step 1:

[0372] The server periodically queries and extracts all user and sentiment data stored in the database.

[0373] Step 2:

[0374] The server preprocesses the extracted data and generates a training dataset for the AI ​​model.

[0375] Step 3:

[0376] The server runs machine learning algorithms (e.g., deep learning) to train an AI model that includes emotion data.

[0377] Step 4:

[0378] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[0379] Step 5:

[0380] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[0381] Providing recommendations

[0382] Step 1:

[0383] A user logs into the system and requests "new recommended works."

[0384] Step 2:

[0385] The device sends the login user ID and recommendation request data to the server.

[0386] Step 3:

[0387] The server uses an AI model to select the most suitable work based on profile data and emotional data.

[0388] Step 4:

[0389] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[0390] Step 5:

[0391] The device displays the recommendation results on the user interface.

[0392] Providing additional content

[0393] Step 1:

[0394] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[0395] Step 2:

[0396] The device will display this additional content to users on the details page of the recommended title.

[0397] Managing your monthly subscription

[0398] Step 1:

[0399] The user enters payment information to purchase a monthly subscription to access premium content.

[0400] Step 2:

[0401] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[0402] Step 3:

[0403] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[0404] Step 4:

[0405] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[0406] Step 5:

[0407] The device displays a successful subscription notification to the user.

[0408] Advertising and Event Management

[0409] Step 1:

[0410] The server receives advertising information from advertisers and production companies and stores it in a database.

[0411] Step 2:

[0412] The server selects appropriate advertisements based on the user's profile data and emotional data.

[0413] Step 3:

[0414] The device displays targeted advertisements in the user interface.

[0415] Example 2

[0416] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0417] In the modern entertainment industry, there is a demand for providing optimal content based on users' diverse preferences and emotions. However, conventional recommendation systems rely solely on user profile data and do not consider real-time emotional data, making it difficult to provide an appropriate entertainment experience for each individual user. Furthermore, there is a lack of systems that handle emotional data and profile data in an integrated manner, which has hindered efforts to improve user experience.

[0418] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0419] In this invention, the server includes means for acquiring user profile data, means for acquiring and storing emotion data in real time, means for training a generative AI model based on the acquired profile data and emotion data, means for using the generative AI model to recommend optimal entertainment works based on the profile data and emotion data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for users, means for targeting advertisements based on the profile data and emotion data, and means for processing payment, thereby enabling the provision of a highly personalized entertainment experience based on the user's emotions and preferences.

[0420] "User profile data" refers to data about a user, such as personal information, preferences, and past browsing history.

[0421] "Emotional data" refers to data on the user's emotional state obtained in real time from their facial expressions and voice.

[0422] "Generative AI model" refers to an artificial intelligence model trained using machine learning algorithms based on user profile data and sentiment data.

[0423] "Entertainment content" refers to content provided based on users' hobbies and interests, such as movies, TV shows, books, music, and games.

[0424] "Additional content" refers to comments from directors and writers, interviews, behind-the-scenes information, etc. related to the recommended works.

[0425] "Monthly subscription" refers to a fee system where users pay a monthly fee to access premium content.

[0426] "Targeting ads" refers to the act of selecting and displaying the most appropriate ads to users based on their profile data and emotional data.

[0427] "Payment Processing" refers to the functionality that processes information and finalizes payments for users to make monthly subscription or other payments.

[0428] This invention is a system that combines personal profile data and emotional data to provide users with a customized entertainment experience. The system uses the user's past viewing history, preferences, and real-time emotional data to select the most suitable content and provide appropriate additional content and advertisements. An embodiment of this system is described below.

[0429] First, the user accesses the system and enters information about their preferences and past browsing history into the new registration form. Specifically, the user provides information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." This sends the user's profile data from the device to the server as a JSON-formatted payload. The server analyzes the received data and stores it in a database.

[0430] Next, the user's emotional data is collected. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice. For example, while the user is watching a movie, the device's camera captures a photo of the user's face and uses an expression analysis algorithm to recognize emotions such as "surprise," "happiness," and "fear." The acquired emotional data is sent to a server and stored in a database along with the user's profile data.

[0431] The server periodically queries and extracts all user and sentiment data from the database to generate a training dataset. This is used to run a machine learning algorithm, such as deep learning, to train a generative AI model. The accuracy of the trained model is evaluated, and parameters are adjusted or retrained as needed. The trained AI model is then deployed to an endpoint and incorporated into the recommender system.

[0432] When a user logs in and requests "new recommended movies," the device sends the logged-in user ID and recommendation request data to the server. The server uses an AI model to select the most suitable movie based on the user's profile and emotional data. For example, if the user is relaxed, it will suggest a "comedy movie," and if they are nervous, it will suggest an "action movie." The recommendation results are returned to the device in JSON format and displayed in the user interface.

[0433] Additionally, the server periodically collects and stores in its database comments, interviews, and behind-the-scenes information from directors and writers. This additional content is then displayed to users on the detail page of the recommended film.

[0434] When a user purchases a monthly subscription to access premium content, the device sends the user's payment information as a JSON-formatted payload to the server. The server processes the received payment information in conjunction with the payment gateway and receives the result. If the payment process is successful, the user's subscription status is updated in the database and set to "active." A success notification is displayed to the user on the device.

[0435] Finally, the server receives advertising information from advertisers and production companies and stores it in a database. Based on the user's profile data and emotional data, it selects appropriate advertisements. For example, if the user is excited, it will display advertisements for action movies, and if the user is relaxed, it will display advertisements for comedy movies. These advertisements are then displayed on the device's user interface.

[0436] Prompt Sentence Examples

[0437] "Suggest recommended works to users who are relaxing"

[0438] "How can we select the best entertainment based on user emotional data?"

[0439] In this way, the system of the present invention is able to provide a highly personalized entertainment experience based on the user's emotions and preferences.

[0440] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0441] Step 1:

[0442] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[0443] Input: User preferences and past browsing history (e.g., "I like horror movies," "I often read suspense manga," "Movies I've seen in the past: A, B, C")

[0444] Output: User registration data constructed in JSON format

[0445] Specific actions: A user accesses the system, enters information into a web form or application screen, and presses the submit button.

[0446] Step 2:

[0447] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[0448] Input: User-entered preferences and browsing history

[0449] Output: JSON format payload (constructed data)

[0450] Specific operation: The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0451] Step 3:

[0452] The server parses the received user data and stores it in the appropriate database tables.

[0453] Input: JSON format user data received from the device

[0454] Output: User information stored in the database

[0455] Specific operation: The server parses the JSON data and saves the data in tables such as user_info and viewing_history.

[0456] Step 4:

[0457] Using the device's built-in camera and microphone, emotional data is collected in real time from the user's facial expressions and voice.

[0458] Input: User's facial expressions and voice

[0459] Output: Obtained emotion data (e.g., "Emotion data: Surprise, Intensity: 0.8")

[0460] Specific operation: The device uses the camera and microphone to run facial expression analysis algorithms and voice analysis algorithms to recognize emotions.

[0461] Step 5:

[0462] The emotion data acquired by the device is transmitted to the server.

[0463] Input: Acquired emotion data

[0464] Output: Emotion data (payload) sent to the server

[0465] Specific operation: The emotion data acquired by the device is converted into JSON format and sent to the server.

[0466] Step 6:

[0467] The server integrates the received emotion data into the profile data and stores it in a database.

[0468] Input: Emotion data received from the device

[0469] Output: Consolidated data stored in a database

[0470] Specific operation: The server connects the received emotion data with the profile data and stores it in a table such as user_emotions.

[0471] Step 7:

[0472] The server periodically queries and extracts all user and sentiment data stored in the database.

[0473] Input: User information and emotion data from the database

[0474] Output: The generated training dataset

[0475] What happens: The server runs SQL queries to extract the necessary data and build a training dataset.

[0476] Step 8:

[0477] The server runs machine learning algorithms (e.g., deep learning) to train a generative AI model that includes emotion data.

[0478] Input: Training dataset

[0479] Output: A trained generative AI model

[0480] Specific operation: The server trains the model using libraries such as TensorFlow and PyTorch.

[0481] Step 9:

[0482] The server evaluates the accuracy of the trained generative AI model and adjusts parameters or retrains it as necessary.

[0483] Input: trained generative AI model, evaluation dataset

[0484] Output: Accuracy evaluation results, model after parameter adjustment

[0485] How it works: The server evaluates the accuracy of the model and, if improvement is needed, adjusts the hyperparameters and retrains it.

[0486] Step 10:

[0487] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[0488] Input: A trained AI model

[0489] Output: A deployed model endpoint

[0490] Specific behavior: The server deploys the model to an API endpoint, making it accessible externally.

[0491] Step 11:

[0492] A user logs into the system and requests "new recommended works."

[0493] Input: Login user ID, recommendation request

[0494] Output: Recommendation request data

[0495] What happens: A user logs into the system and requests new recommendations.

[0496] Step 12:

[0497] The device sends the login user ID and recommendation request data to the server.

[0498] Input: Login user ID, recommendation request data

[0499] Output: Recommendation request sent to the server

[0500] Specific operation: The device sends recommendation request data to the server.

[0501] Step 13:

[0502] The server uses a generative AI model to select the most suitable work based on profile data and emotional data.

[0503] Input: Profile data, emotion data, generative AI model

[0504] Output: Best work recommendations

[0505] How it works: The server uses the generated AI model to select the most suitable entertainment content based on the user's profile data and emotional data.

[0506] Step 14:

[0507] The server constructs the recommendation results in JSON format and sends them back to the device.

[0508] Input: Recommendation results

[0509] Output: Recommendation results in JSON format

[0510] Specific operation: The server converts the recommendation results into JSON format and returns them to the device as an HTTP response.

[0511] Step 15:

[0512] The device displays the recommendation results on the user interface.

[0513] Input: Recommendation results in JSON format

[0514] Output: Recommendations displayed in the user interface

[0515] Specific operation: The device analyzes the recommendation results received and displays them on the screen.

[0516] Step 16:

[0517] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[0518] Input: Comments, interviews, behind-the-scenes info

[0519] Output: Additional content stored in the database

[0520] Specific operation: The server periodically collects information from providers and stores it in a database.

[0521] Step 17:

[0522] The device will display this additional content to users on the details page of the recommended title.

[0523] Input: Additional content

[0524] Output: Additional content displayed on the details page

[0525] Specific behavior: The device retrieves the additional content and displays it on the work's details page.

[0526] Step 18:

[0527] The user enters payment information to purchase a monthly subscription to access premium content.

[0528] Input: Payment information (e.g. credit card number, expiration date)

[0529] Output: Payment information entered

[0530] What happens: The user enters payment information and clicks submit.

[0531] Step 19:

[0532] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[0533] Input: Payment information

[0534] Output: Payment information payload in JSON format

[0535] Specific operation: The terminal converts the payment information into JSON format and sends it to the server.

[0536] Step 20:

[0537] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[0538] Input: Payment information in JSON format

[0539] Output: Payment result

[0540] What happens: Your server sends a request to a payment gateway (e.g., Stripe, PayPal) to process the payment.

[0541] Step 21:

[0542] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[0543] Input: Payment result

[0544] Output: Updated subscription status

[0545] Specific behavior: The server receives notification of successful payment and updates the subscription status in the database to "active".

[0546] Step 22:

[0547] The device displays a successful subscription notification to the user.

[0548] Input: Subscription success notification

[0549] Output: Success notification displayed to the user

[0550] Specific behavior: The device displays the notification received from the server to the user.

[0551] Step 23:

[0552] The server receives advertising information from advertisers and production companies and stores it in a database.

[0553] Input: Advertisement information

[0554] Output: Advertisement information stored in the database

[0555] Specific operation: The server collects advertising data from advertisers and stores it in a database.

[0556] Step 24:

[0557] The server selects appropriate advertisements based on the user's profile data and emotional data.

[0558] Input: Profile data, emotion data, advertising information

[0559] Output: Targeted ads

[0560] How it works: The server analyzes the user's data and selects ads that match their emotional state at the time.

[0561] Step 25:

[0562] The device displays targeted advertisements in the user interface.

[0563] Enter: targeted advertising

[0564] Output: Ad displayed in the user interface

[0565] What happens: The device displays targeted ads in the user interface.

[0566] (Application example 2)

[0567] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0568] To improve the quality of individual entertainment experiences, there is a need to provide more accurate recommendations by taking into account not only users' preferences and viewing history, but also their real-time emotional state. Another challenge is to improve user satisfaction by appropriately providing additional content, comments, interviews, and other information about entertainment works. Furthermore, there is a need to improve the accuracy of targeted advertising and display appropriate ads to users.

[0569] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0570] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending optimal entertainment works to a user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for acquiring real-time emotional data of the user, and means for recommending entertainment works based on the acquired emotional data, thereby enabling advanced personalization based on user preferences and real-time emotional data.

[0571] "Personal profile data" refers to information related to an individual, such as a user's preferences, viewing history, and past viewing data.

[0572] "Generative AI" refers to a system that uses machine learning algorithms and deep learning technology to build and learn models based on user data and make predictions and recommendations.

[0573] "Recommendation methods" refers to technology that analyzes a user's profile data and emotional data to suggest the most suitable entertainment works for that user.

[0574] "Additional Content" refers to additional information accompanying an entertainment production, such as commentary, interviews, behind-the-scenes information, etc.

[0575] "Means for managing monthly subscriptions" refers to technology that manages the payment procedures and usage status required for users to use the service on an ongoing basis.

[0576] "Means for targeting ads" refers to technology that selects and displays appropriate ads to specific users based on their profile data.

[0577] "Real-time emotional data" refers to data that indicates the emotional state of the user at that moment, obtained from their facial expressions, voice, etc.

[0578] "Means of acquiring emotional data" refers to technology that uses devices such as cameras and microphones to analyze and acquire emotions from users' reactions.

[0579] The present invention relates to an entertainment recommendation system that utilizes user profile data and real-time emotional data to provide a personalized entertainment experience using generative AI.

[0580] User profile data collection

[0581] When a user registers with the system, they first enter information about their preferences and past browsing history into a new registration form. For example, they provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this information to the server as a JSON-formatted payload. The server analyzes the received data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[0582] Acquiring real-time emotion data

[0583] The device uses a built-in camera and microphone to capture emotional data in real time from the user's facial expressions and voice. For example, it analyzes the user's facial expressions and tone of voice while watching a movie and recognizes emotions such as "surprise," "happiness," and "fear." The device then transmits the captured emotional data to a server, which then integrates the received data into profile data and stores it in a database.

[0584] Tech stack for invention

[0585] Hardware: Smartphone, head-mounted display, built-in camera, microphone

[0586] Software: Python, OpenCV (facial expression recognition), PyAudio (voice recognition), TensorFlow (AI model), MySQL (database)

[0587] Creating and training AI models

[0588] The server periodically queries and extracts all user and sentiment data stored in the database, integrates the sentiment data with profile data, and generates a training dataset. The server then runs a machine learning algorithm (e.g., deep learning) to train a generative AI model that includes the sentiment data. The trained model is then deployed to an endpoint and incorporated into the recommender system.

[0589] Providing recommendations

[0590] When a user logs in to the system and requests "new recommended titles," the device sends the login user ID and recommendation request data to the server. The server uses a generative AI model to select the most suitable title based on the profile data and emotional data, and returns the recommendation results in JSON format to the device. The device then displays the recommendation results on the user interface.

[0591] Specific examples

[0592] For example, if a user is using a movie viewing app, the following prompt is used:

[0593] Example prompt for user registration:

[0594] What are your movie and TV preferences?

[0595] I like horror.

[0596] Recently seen movies: A, B, C

[0597] Emotion detection prompt example:

[0598] We're analyzing your facial expressions. Please smile and stay relaxed for the camera.

[0599] Providing additional content

[0600] The server periodically collects comments from directors and writers, interviews, and behind-the-scenes information, storing them in a database, and the device displays this additional content to the user on the detail page of the recommended film.

[0601] Managing your monthly subscription

[0602] When a user purchases a monthly subscription to access premium content, they enter their payment information and the terminal sends the user's payment information as a JSON-formatted payload to the server. The server processes the received payment information in conjunction with the payment gateway and receives the result. If the payment process is successful, the user's subscription status is updated in the database to "active." The terminal then displays a notification of successful subscription to the user.

[0603] Advertising and Event Management

[0604] The server receives advertising information from advertisers and production companies and stores it in a database. The server selects appropriate advertisements based on the user's profile data and emotional data. For example, when a user is "excited," it displays advertisements for related action movies, and when a user is "relaxed," it displays advertisements for comedy movies, displaying targeted advertisements that match the user's emotional state.

[0605] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0606] Step 1:

[0607] A user accesses the system and fills in a new registration form with information about their preferences and past browsing history.

[0608] Users provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[0609] The device sends this information to the server as a JSON-formatted payload.

[0610] Input: User profile information

[0611] Output: Payload in JSON format

[0612] Step 2:

[0613] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[0614] Input: User data in JSON format

[0615] Output: User data stored in the database

[0616] Step 3:

[0617] The device uses its built-in camera and microphone to capture emotional data in real time from the user's facial expressions and voice.

[0618] For example, it analyzes the user's facial expressions and tone of voice while they are watching a movie and recognizes emotions such as "surprise," "joy," and "fear."

[0619] Input: User's facial expression video and voice data

[0620] Output: Real-time emotion data

[0621] Step 4:

[0622] The device transmits the acquired emotion data to the server.

[0623] The server integrates the emotion data with the profile data and stores it in a database.

[0624] Input: Real-time emotion data

[0625] Output: Unified profile data

[0626] Step 5:

[0627] The server periodically queries and extracts all user and emotion data stored in the database.

[0628] Integrate the data and generate a training dataset.

[0629] Input: User data and emotion data in the database

[0630] Output: Training dataset

[0631] Step 6:

[0632] The server runs machine learning algorithms (e.g., deep learning) to train generative AI models that include emotion data.

[0633] Input: Training dataset

[0634] Output: A trained generative AI model

[0635] Step 7:

[0636] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[0637] Input: A trained model

[0638] Output: Accuracy evaluation results, optimized generative AI model

[0639] Step 8:

[0640] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[0641] Input: Optimized generative AI model

[0642] Output: Deployed AI model

[0643] Step 9:

[0644] The user logs into the system and requests "new recommended works."

[0645] Input: User login information, recommendation request

[0646] Output: Request data

[0647] Step 10:

[0648] The server receives the request data and uses a generative AI model to select the most suitable work based on the profile data and emotional data.

[0649] Input: Request data, profile data, emotion data

[0650] Output: Optimized recommendation results

[0651] Step 11:

[0652] The server constructs the recommendation results in JSON format and sends them back to the device.

[0653] Input: Optimized recommendation results

[0654] Output: Recommendation data in JSON format

[0655] Step 12:

[0656] The device displays the recommendation results in the user interface.

[0657] Users can select from the displayed works and enjoy entertainment.

[0658] Input: Recommendation data in JSON format

[0659] Output: Recommendation results displayed on the screen

[0660] Step 13:

[0661] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[0662] Input: Additional information from directors and writers

[0663] Output: Additional content stored in the database

[0664] Step 14:

[0665] The device will display this additional content to the user on the detail page of the recommended title.

[0666] Input: detailed data of recommended works, additional content

[0667] Output: Additional content shown on the display

[0668] Step 15:

[0669] The user enters payment information to purchase a monthly subscription to access premium content.

[0670] The terminal sends the user's payment information to the server as a JSON-formatted payload.

[0671] Input: User's payment information

[0672] Output: Payment data in JSON format

[0673] Step 16:

[0674] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[0675] If the payment is successful, the server updates the user's subscription status in the database to "active" and the terminal displays a successful subscription notification to the user.

[0676] Input: Payment data in JSON format, payment gateway results

[0677] Output: Subscription status in "Active" state

[0678] Step 17:

[0679] The server receives advertising information from advertisers and production companies and stores it in a database.

[0680] Input: Advertisement information

[0681] Output: Ad data stored in a database

[0682] Step 18:

[0683] The server selects appropriate advertisements based on the user's profile data and emotional data.

[0684] For example, when a user is "excited," ads for related action movies are displayed, and when a user is "relaxed," ads for comedy movies are displayed.

[0685] Input: Profile data, emotion data, advertising information

[0686] Output: Optimized advertising data

[0687] Step 19:

[0688] The device displays targeted advertisements in the user interface.

[0689] Input: Optimized Ad Data

[0690] Output: Targeted ads displayed on the screen

[0691] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0692] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0693] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0694] [Second embodiment]

[0695] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0696] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0697] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0698] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0699] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0700] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0701] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0702] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0703] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[0704] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0705] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0706] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0707] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized manga and movie recommendations. This system selects the most suitable works based on the user's past viewing history and preferences, and also provides additional information such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[0708] User profile data collection

[0709] 1. A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[0710] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[0711] 2. The device sends the user's input information to the server.

[0712] The terminal sends the entered data to the server as a JSON formatted payload.

[0713] 3. The server stores the received user data in a database.

[0714] The server analyzes the received data and stores it in the appropriate tables. For example, the user's basic information is stored in the "users" table, and the browsing history is stored in the "viewing_history" table.

[0715] Creating and training AI models

[0716] 1. The server trains the AI ​​model using user data in the database.

[0717] The server periodically extracts and pre-processes the data.

[0718] 2. The server uses common machine learning algorithms (e.g., deep learning) to generate a model based on the user's preferences.

[0719] Evaluate the accuracy of the model and adjust parameters or retrain as needed.

[0720] 3. The server deploys the trained model and incorporates it into the recommender system.

[0721] Once deployed, the model quickly generates recommendations upon request.

[0722] Providing recommendations

[0723] 1. A user logs in to the system and requests "new recommended works."

[0724] After logging in, you will be able to request recommendations on your dashboard.

[0725] 2. The device sends a recommendation request to the server.

[0726] Send the request data along with the user ID.

[0727] 3. The server uses an AI model to select works that match the user's preferences and generate recommendation results.

[0728] For example, if a user likes "horror movies," they can select "A," "B," or "C" from the latest horror movies.

[0729] 4. The server sends the recommendation results to the device.

[0730] JSON data including the work title, thumbnail, description, etc. is returned.

[0731] 5. The device displays the recommendation results to the user.

[0732] The user interface displays information about movies "A," "B," and "C."

[0733] Providing additional content

[0734] 1. The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[0735] We regularly obtain additional information from partner media and APIs.

[0736] 2. Display this additional content on the details page of the title for which your device was recommended.

[0737] For example, it provides users with comments and interviews from the director of movie "A."

[0738] Managing your monthly subscription

[0739] 1. A user wants access to premium content and signs up for a monthly subscription.

[0740] Enter your payment information and start your subscription.

[0741] 2. The terminal sends the payment information to the server and processes the payment.

[0742] 3. The server receives the payment processing result and updates the user's subscription status.

[0743] Updates the user status in the database to "active".

[0744] 4. The device displays a successful subscription notification to the user.

[0745] Advertising and Event Management

[0746] 1. The server receives advertising information from advertisers and production companies.

[0747] Store advertising materials provided by advertisers and save them in a database.

[0748] 2. The server selects appropriate ads based on the user's profile data.

[0749] Select targeted advertising based on your interests.

[0750] 3. The device displays appropriate advertisements in the user's interface.

[0751] Display targeted ads on your dashboard and product detail pages.

[0752] The above is a specific embodiment for carrying out the present invention. As a result, in a world where entertainment options are becoming more diverse, it is possible to recommend the most suitable works to users, enabling them to enjoy a deeper entertainment experience.

[0753] The processing flow will be explained below.

[0754] User profile data collection

[0755] Step 1:

[0756] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[0757] Step 2:

[0758] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[0759] Step 3:

[0760] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[0761] Creating and training AI models

[0762] Step 1:

[0763] The server periodically queries and extracts all user data stored in the database.

[0764] Step 2:

[0765] The server preprocesses the extracted data to generate a training dataset for the AI ​​model, including data cleaning and feature engineering.

[0766] Step 3:

[0767] The server runs machine learning algorithms (e.g., deep learning) to train an AI model based on user preferences.

[0768] Step 4:

[0769] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[0770] Step 5:

[0771] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[0772] Providing recommendations

[0773] Step 1:

[0774] A user logs into the system and requests "new recommended works."

[0775] Step 2:

[0776] The device sends the login user ID and recommendation request data to the server.

[0777] Step 3:

[0778] Based on the request data received by the server, a trained AI model is called up to select works that match the user's preferences.

[0779] Step 4:

[0780] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[0781] Step 5:

[0782] The device displays the recommendation results on the user interface.

[0783] Providing additional content

[0784] Step 1:

[0785] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[0786] Step 2:

[0787] The device will display this additional content to users on the details page of the recommended title.

[0788] Managing your monthly subscription

[0789] Step 1:

[0790] A user enters payment information to purchase a monthly subscription to access premium content.

[0791] Step 2:

[0792] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[0793] Step 3:

[0794] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[0795] Step 4:

[0796] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[0797] Step 5:

[0798] The device displays a successful subscription notification to the user.

[0799] Advertising and Event Management

[0800] Step 1:

[0801] The server receives advertising information from advertisers and production companies and stores it in a database.

[0802] Step 2:

[0803] The server selects appropriate ads based on the user's profile data.

[0804] Step 3:

[0805] The device displays targeted advertisements in the user interface.

[0806] Example 1

[0807] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0808] In today's entertainment industry, it is difficult for users to find the most suitable titles from the vast number of titles available. It is also not easy to provide additional content and advertisements that match users' interests. Furthermore, as user preferences change over time, AI models must be continuously updated. A method to solve these problems is needed.

[0809] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0810] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending entertainment works that are most suitable for the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for processing recommendation requests based on the user's visit history and preferences, means for providing comments and interviews from related creators as additional content, and means for periodically extracting user data from a database and updating the generative AI model. This allows users to easily find entertainment works and related content that suit their preferences. The user experience is also improved through individually optimized advertisements and continuously updated recommendations.

[0811] "Personal profile data" refers to data that includes a user's preferences, past browsing history, viewing history, personal information, etc.

[0812] "Generative AI" is an artificial intelligence model trained using user profile data to recommend entertainment content based on user preferences.

[0813] "Recommendation" is the act of recommending the most suitable entertainment works based on the user's profile data.

[0814] "Additional content" refers to additional information related to the recommended work, such as comments and interviews from directors and writers, and behind-the-scenes information.

[0815] A "monthly subscription" is a subscription system that allows users to access certain services or additional content by paying a fixed monthly fee.

[0816] "Targeting ads" means using a user's profile data to select and display ads that are most relevant to that user.

[0817] "Visit history" is a record of the pages and content a user has accessed within the system.

[0818] A "recommendation request" is a request from a user to the system for new recommendations.

[0819] "Updating using generative AI models" means continually retraining the artificial intelligence model with the latest user data to keep improving its accuracy.

[0820] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized entertainment recommendations and related additional content. Specific embodiments for implementing the present invention are described below.

[0821] User profile data collection

[0822] A user accesses the system and enters their preferences and past browsing history into a new registration form. For example, they might enter information such as "I like horror movies," "I often read suspense manga," or "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which then stores the received data in a database. This data is primarily exchanged using the JSON format.

[0823] Creating and training AI models

[0824] The server trains the AI ​​model using user data stored in the database. Specifically, it preprocesses the data using Python and deep learning frameworks such as TensorFlow and PyTorch, and then builds and trains the model. It periodically extracts data from the database and uses the generative AI model to update the model. This ensures that the model is always up to date with new user preferences.

[0825] Providing recommendations

[0826] A user logs in to the system and requests "new recommended movies." The device sends the recommendation request to the server, which uses an AI model to select movies that match the user's preferences. For example, if the user likes "horror movies," they can select "A," "B," and "C" from the latest horror movies. The server sends the recommendation results to the device, which then displays them to the user.

[0827] Providing additional content

[0828] The server retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, it might provide the user with comments and interviews from the director of film "A."

[0829] Managing your monthly subscription

[0830] A user wants access to premium content and signs up for a monthly subscription. The user enters payment information, which the device sends to the server for payment processing. The server receives the payment processing result, updates the user's subscription status, and the device displays a successful subscription notification to the user.

[0831] Advertising and Event Management

[0832] The server receives advertising information from advertisers and production companies and selects appropriate advertisements based on the user's profile data. The device displays the appropriate advertisements on the user's interface. In this way, the user can also be provided with other commercial information.

[0833] Examples of concrete examples and prompts

[0834] As a concrete example, the system may recommend the latest horror movies "X," "Y," and "Z" to User A, who previously registered that he "likes horror movies." It may also be possible to provide an interview with the author of the manga "Psychic Battle" as additional premium content.

[0835] Examples of prompts include:

[0836] "Recommend three horror movies based on the user's preferences."

[0837] "Please display an interview with the author of the manga 'Psychic Battle' as premium content."

[0838] This allows the present invention to optimize users' entertainment choices and provide additional value, and it also makes it possible to realize attractive services for users through targeted advertising and subscription management.

[0839] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0840] Step 1:

[0841] A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[0842] Input: New registration form, user preferences and browsing history

[0843] Specific actions: Enter information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C" into a web browser or mobile app.

[0844] Output: User information entered

[0845] Step 2:

[0846] The terminal transmits the user's input information to the server.

[0847] Input: Information entered by the user

[0848] Specific operation: Front-end code (JavaScript or Swift) converts the input information into JSON format and sends it to the server via an HTTPS request.

[0849] Output: JSON data sent to the server

[0850] Step 3:

[0851] The server stores the received user data in a database.

[0852] Input: JSON data sent from the terminal

[0853] What it does: The server uses backend code (Python or Node.js) to parse the incoming data, generate appropriate SQL queries, and store the data in a MySQL or PostgreSQL database.

[0854] Output: User data stored in the database

[0855] Step 4:

[0856] The server trains the AI ​​model using user data in the database.

[0857] Input: Raw data in the database

[0858] What it does: Use Python and TensorFlow or PyTorch to preprocess data and train a deep learning model, including the training and evaluation processes.

[0859] Output: A trained AI model

[0860] Step 5:

[0861] The server uses the generated AI model to generate recommendation results.

[0862] Input: A trained AI model and specific user data

[0863] How it works: User data is input into the AI ​​model to generate recommendations. For example, it recommends the latest horror movies to a user who likes "horror movies."

[0864] Output: Recommendation results

[0865] Step 6:

[0866] The server sends the recommendation results to the terminal.

[0867] Input: Generated recommendation results

[0868] Specific operation: The server converts the recommendation results into JSON format and sends them to the terminal as an HTTP response.

[0869] Output: Recommendation results sent to the device

[0870] Step 7:

[0871] The device displays the recommendation results to the user.

[0872] Input: JSON data received from the server

[0873] Specific operation: The front end parses the received data and displays information such as movies "A", "B", and "C" in the user interface.

[0874] Output: Recommendation results displayed to the user

[0875] Step 8:

[0876] The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[0877] Input: Additional information from external media or API

[0878] Specific operation: The server periodically obtains information using the API of the partner media and stores the obtained additional information in a database.

[0879] Output: Additional content stored in the database

[0880] Step 9:

[0881] The device will display this additional content on the details page of the recommended title.

[0882] Input: Additional content data obtained from the server

[0883] What happens: The front-end renders the additional content information on the detail page and displays it to the user.

[0884] Output: Additional content displayed on the details page

[0885] Step 10:

[0886] A user wants access to premium content and signs up for a monthly subscription.

[0887] Input: Premium content request and payment information

[0888] What it does: The user enters payment information and presses a button to start a monthly subscription.

[0889] Output: Subscription registration request

[0890] Step 11:

[0891] The terminal transmits the payment information to the server, which processes the payment.

[0892] Input: User's payment information

[0893] What it does: The terminal securely encodes the payment information and sends an HTTPS request to the server, which then processes the payment using the Stripe or PayPal API.

[0894] Output: Payment processing result

[0895] Step 12:

[0896] The server receives the payment transaction result and updates the user's subscription status.

[0897] Input: Payment processing result data

[0898] Specific behavior: The server receives the payment success response and updates the user's subscription status in the database to "active."

[0899] Output: Updated subscription status

[0900] Step 13:

[0901] The device will display a successful subscription notification to the user.

[0902] Input: Subscription status update

[0903] What happens: The front end displays a "Subscription successful" notification to the user.

[0904] Output: Success notification displayed to the user

[0905] Step 14:

[0906] The server receives advertising information from advertisers and production companies.

[0907] Input: Advertising data from advertisers and production companies

[0908] Specific operation: Uses the API provided by the advertiser to obtain advertising materials and save them in a database.

[0909] Output: Ad data stored in a database

[0910] Step 15:

[0911] The server selects appropriate advertisements based on the user's profile data.

[0912] Input: User profile data

[0913] What it does: The server analyzes user data and uses targeting algorithms to select appropriate ads.

[0914] Output: Selected advertising data

[0915] Step 16:

[0916] The device displays appropriate advertisements in the user's interface.

[0917] Input: Selected advertising data

[0918] What happens: The front-end renders the ad data into the interface and displays it to the user.

[0919] Output: The ad shown to the user

[0920] The above is the specific processing flow of the program of this system.

[0921] (Application example 1)

[0922] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0923] Today's entertainment consumers face challenges in finding content that suits their tastes among a wide variety of options, often lacking additional information to maximize the appeal of a content, and face the problem of insufficient integration between targeting advertising and payment management systems based on user preferences, resulting in an inconsistent and optimized user experience.

[0924] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0925] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending optimal entertainment works to the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for providing a visually easy-to-understand user interface on a smartphone, and means for notifying the user when new recommendations are available. This improves the ease of discovering entertainment works and maximizes the appeal of the works by providing additional information. It also consistently optimizes the user experience and enables effective targeted advertising and payment management.

[0926] "Personal profile data" refers to a set of information that a user has about themselves, including their preferences, past browsing history, and behavioral patterns.

[0927] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to learn patterns from users' profile data and generate appropriate recommendations.

[0928] "Entertainment works" refers to movies, comics, television programs, music, and other media content that users view or consume.

[0929] "Recommendation" refers to the act or result of recommending the most suitable entertainment content based on a user's preferences.

[0930] "Additional Content" refers to supplemental information, such as commentary, interviews, and behind-the-scenes information, related to an entertainment production.

[0931] "Monthly Subscription" refers to a subscription format that allows users to access premium content or services in exchange for a recurring payment.

[0932] "Targeted advertising" refers to the practice of displaying the most relevant advertisements to individual users based on their profile data.

[0933] A "smartphone" refers to a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[0934] "User interface" refers to the screen layout and operation methods used by users to interact with a system.

[0935] "Notification" refers to the act of the system informing the user that new information or recommendations are available.

[0936] This invention is a system that combines user profile data with a generative AI model to recommend customized entertainment works to users. It also provides additional content related to the recommended works, enriching the user's entertainment experience. Specific embodiments for implementing this invention are described below.

[0937] Profile Data Collection

[0938] Users access the system and enter information such as their preferences and past browsing history into a new registration form. For example, they provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which analyzes the received data and stores it in a database. For example, the user's basic information is stored in the users table, and their browsing history is stored in the viewing_history table.

[0939] Creating and training AI models

[0940] The server uses the user data in the database to train an AI model using machine learning algorithms (e.g., deep learning). This AI model is then used to recommend entertainment items based on the user's preferences. The trained AI model is then deployed to a recommender system, which quickly generates recommendation results upon request.

[0941] Providing recommendations

[0942] When a user logs in to the system and requests "new recommended titles," the device sends the request data along with the user ID to the server. The server uses an AI model to select titles that match the user's preferences and generates recommendation results. These results include titles, thumbnails, descriptions, etc., which the device displays to the user. The system also has a function to notify the user when new recommendations are available.

[0943] Providing additional content

[0944] The server periodically retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, the device can provide the user with comments and interviews from the director of film "A."

[0945] Managing your monthly subscription

[0946] If a user wants access to premium content, they sign up for a monthly subscription. Payment information is sent from the device to the server, which processes the payment. Based on the transaction result, the user's subscription status is updated in the database.

[0947] Advertising and Event Management

[0948] The server receives advertising information from advertisers and production companies and selects appropriate ads based on user profile data, allowing it to provide the most relevant ads to each individual user.

[0949] Examples and prompts

[0950] If a user says "I like horror movies" and enters "Movies I've recently seen are A, B, and C":

[0951] Register with user ID 123

[0952] Submit a recommendation request

[0953] AI recommends "latest horror movies D, E, F"

[0954] Also displays additional information including director comments and interviews

[0955] Example prompt sentence:

[0956] Input: User likes horror movies and requests new movie recommendations based on recently watched movies A, B, and C.

[0957] Output: A list of the latest horror movies D, E, F with additional information about them (director comments, interviews, etc.).

[0958] Using this system, users can be provided with the most suitable entertainment content, enriching their entertainment experience.

[0959] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0960] Step 1:

[0961] A user accesses the system and enters information such as their preferences and past viewing history into a new registration form. Input content includes "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input data to the server in JSON format. As data input, the user provides their preferred entertainment genre and past viewing history information, and as output, the data is transferred to the server in JSON format.

[0962] Step 2:

[0963] The server parses the received user profile data and stores basic information in the users table and browsing history in the viewing_history table in the database. The server receives the JSON data, parses its contents, and executes queries to store them in the appropriate tables. The input to this step is the user's JSON data, and the output is the creation of a record in the database.

[0964] Step 3:

[0965] The server extracts user profile data from the database and uses a generative AI model to train a recommendation model. A machine learning algorithm (e.g., deep learning) is used to learn patterns based on the profile data. The trained model results undergo accuracy evaluation and parameter adjustment before finally being deployed. The input is user data from the database, and the output is the trained AI model.

[0966] Step 4:

[0967] A user logs in to the system and requests new recommendations. The device sends the user ID and request data to the server. The input for this step is the user's request information, and the request content is sent to the server.

[0968] Step 5:

[0969] The server uses a trained AI model to recommend entertainment works that match the user's preferences. If the user likes "horror movies," it will select several of the latest horror movies. Specifically, the AI ​​model receives the user's profile data as input, generates a list of entertainment works, and returns it to the device in JSON format. The recommendation results are output from the server.

[0970] Step 6:

[0971] The device receives the recommendation results from the server and displays them to the user as a visually easy-to-understand user interface, showing the title, thumbnail, description, etc. of the recommended works. The input to this step is JSON data from the server, and the output is a visually structured display.

[0972] Step 7:

[0973] The server periodically retrieves comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database. Additional information is obtained from partner media and APIs and added to the database. The input to this step is external information data, and storing it in the database is the output.

[0974] Step 8:

[0975] The device displays additional content such as comments and interviews from the director and writer on the details page of the recommended work. Providing comments and interviews from the director of movie "A" provides the user with a deeper entertainment experience. The input of this step is additional information from the database, and the display on the details page is the output.

[0976] Step 9:

[0977] A user wants access to premium content and signs up for a monthly subscription from their device. Payment information is entered and sent from the device to the server. The input to this step is the user's payment information, and the output is the data sent to the server.

[0978] Step 10:

[0979] The server processes the received payment information and updates the user's subscription status in the database. For example, it updates the user's status in the database to "active". The input to this step is the payment information and the output is the status update in the database.

[0980] Step 11:

[0981] The server selects appropriate targeted advertisements based on the user's profile data. The server extracts the user's interests from the profile data stored on the server and selects targeted advertisements based on them. The input for this step is the profile data, and the selected advertisement information is the output.

[0982] Step 12:

[0983] The device displays appropriate advertisements on the user's interface. Targeted advertisements are visually displayed on the dashboard or product detail page. The input of this step is the advertisement information from the server, and the display on the device is the output.

[0984] These processing steps improve entertainment discovery, maximize the appeal of entertainment content by providing additional information, and consistently optimize the user experience, enabling effective targeted advertising and payment management.

[0985] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0986] The present invention is a system that combines personal profile data with generative AI and uses an emotion engine to recognize a user's emotions in real time, providing a customized entertainment experience. The system uses real-time emotion data in addition to the user's past viewing history and preferences to select the most suitable works. It also provides additional information, such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[0987] User profile data collection

[0988] 1. A user accesses the system and fills in a new registration form with information about their preferences and past browsing history.

[0989] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[0990] 2. The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[0991] 3. The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[0992] Combining Emotion Engines

[0993] 1. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice.

[0994] For example, it analyzes the user's facial expressions and tone of voice while they are watching a movie and recognizes emotions such as "surprise," "joy," and "fear."

[0995] 2. The device transmits the acquired emotion data to the server.

[0996] 3. The server integrates the received emotion data into the profile data and stores it in a database.

[0997] Creating and training AI models

[0998] 1. The server periodically queries and extracts all user and sentiment data stored in the database.

[0999] The emotion data and profile data are combined to generate a training dataset.

[1000] 2. The server runs a machine learning algorithm (e.g., deep learning) to train an AI model that includes the emotion data.

[1001] 3. The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[1002] 4. The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1003] Providing recommendations

[1004] 1. A user logs in to the system and requests "new recommended works."

[1005] 2. The device sends the login user ID and recommendation request data to the server.

[1006] 3. The server uses an AI model to select the most suitable work based on the profile data and emotional data.

[1007] For example, based on past browsing history and current emotional data, the app will suggest "comedy movies" when the user is "relaxed," and "action movies" when the user is "stressed."

[1008] 4. The server constructs the recommendation results in JSON format and returns them to the device.

[1009] 5. The device displays the recommendation results on the user interface.

[1010] Providing additional content

[1011] 1. The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1012] 2. Display this additional content to users on the details page of the title for which the device was recommended.

[1013] Managing your monthly subscription

[1014] 1. A user enters payment information to purchase a monthly subscription to access premium content.

[1015] 2. The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[1016] 3. The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1017] 4. If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[1018] 5. The device displays a successful subscription notification to the user.

[1019] Advertising and Event Management

[1020] 1. The server receives advertising information from advertisers and production companies and stores it in a database.

[1021] 2. The server selects appropriate ads based on the user's profile data and emotional data.

[1022] For example, when a user is "excited," ads for related action movies might be shown, and when a user is "relaxed," ads for comedy movies might be shown.

[1023] 3. The device displays targeted ads in the user interface.

[1024] The above is a specific embodiment for implementing the present invention. As entertainment options become more diverse, this allows users to recommend the most suitable works and enjoy the entertainment experience more deeply. By combining it with an emotion engine, the degree of customization of the user experience can be further increased.

[1025] The processing flow will be explained below.

[1026] User profile data collection

[1027] Step 1:

[1028] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[1029] Step 2:

[1030] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[1031] Step 3:

[1032] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1033] Combining Emotion Engines

[1034] Step 1:

[1035] Using the device's built-in camera and microphone, emotional data is collected in real time from the user's facial expressions and voice.

[1036] Step 2:

[1037] The device analyzes the emotional data it acquires and classifies emotions such as "joy," "surprise," and "sadness."

[1038] Step 3:

[1039] The device sends the analysis results to the server as a JSON format payload.

[1040] Step 4:

[1041] The server integrates the received emotion data into the profile data and stores it in a database.

[1042] Creating and training AI models

[1043] Step 1:

[1044] The server periodically queries and extracts all user and sentiment data stored in the database.

[1045] Step 2:

[1046] The server preprocesses the extracted data and generates a training dataset for the AI ​​model.

[1047] Step 3:

[1048] The server runs machine learning algorithms (e.g., deep learning) to train an AI model that includes emotion data.

[1049] Step 4:

[1050] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[1051] Step 5:

[1052] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1053] Providing recommendations

[1054] Step 1:

[1055] A user logs into the system and requests "new recommended works."

[1056] Step 2:

[1057] The device sends the login user ID and recommendation request data to the server.

[1058] Step 3:

[1059] The server uses an AI model to select the most suitable work based on profile data and emotional data.

[1060] Step 4:

[1061] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[1062] Step 5:

[1063] The device displays the recommendation results on the user interface.

[1064] Providing additional content

[1065] Step 1:

[1066] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1067] Step 2:

[1068] The device will display this additional content to users on the details page of the recommended title.

[1069] Managing your monthly subscription

[1070] Step 1:

[1071] The user enters payment information to purchase a monthly subscription to access premium content.

[1072] Step 2:

[1073] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[1074] Step 3:

[1075] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1076] Step 4:

[1077] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[1078] Step 5:

[1079] The device displays a successful subscription notification to the user.

[1080] Advertising and Event Management

[1081] Step 1:

[1082] The server receives advertising information from advertisers and production companies and stores it in a database.

[1083] Step 2:

[1084] The server selects appropriate advertisements based on the user's profile data and emotional data.

[1085] Step 3:

[1086] The device displays targeted advertisements in the user interface.

[1087] Example 2

[1088] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1089] In the modern entertainment industry, there is a demand for providing optimal content based on users' diverse preferences and emotions. However, conventional recommendation systems rely solely on user profile data and do not consider real-time emotional data, making it difficult to provide an appropriate entertainment experience for each individual user. Furthermore, there is a lack of systems that handle emotional data and profile data in an integrated manner, which has hindered efforts to improve user experience.

[1090] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1091] In this invention, the server includes means for acquiring user profile data, means for acquiring and storing emotion data in real time, means for training a generative AI model based on the acquired profile data and emotion data, means for using the generative AI model to recommend optimal entertainment works based on the profile data and emotion data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for users, means for targeting advertisements based on the profile data and emotion data, and means for processing payment, thereby enabling the provision of a highly personalized entertainment experience based on the user's emotions and preferences.

[1092] "User profile data" refers to data about a user, such as personal information, preferences, and past browsing history.

[1093] "Emotional data" refers to data on the user's emotional state obtained in real time from their facial expressions and voice.

[1094] "Generative AI model" refers to an artificial intelligence model trained using machine learning algorithms based on user profile data and sentiment data.

[1095] "Entertainment content" refers to content provided based on users' hobbies and interests, such as movies, TV shows, books, music, and games.

[1096] "Additional content" refers to comments from directors and writers, interviews, behind-the-scenes information, etc. related to the recommended works.

[1097] "Monthly subscription" refers to a fee system where users pay a monthly fee to access premium content.

[1098] "Targeting ads" refers to the act of selecting and displaying the most appropriate ads to users based on their profile data and emotional data.

[1099] "Payment Processing" refers to the functionality that processes information and finalizes payments for users to make monthly subscription or other payments.

[1100] This invention is a system that combines personal profile data and emotional data to provide users with a customized entertainment experience. The system uses the user's past viewing history, preferences, and real-time emotional data to select the most suitable content and provide appropriate additional content and advertisements. An embodiment of this system is described below.

[1101] First, the user accesses the system and enters information about their preferences and past browsing history into the new registration form. Specifically, the user provides information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." This sends the user's profile data from the device to the server as a JSON-formatted payload. The server analyzes the received data and stores it in a database.

[1102] Next, the user's emotional data is collected. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice. For example, while the user is watching a movie, the device's camera captures a photo of the user's face and uses an expression analysis algorithm to recognize emotions such as "surprise," "happiness," and "fear." The acquired emotional data is sent to a server and stored in a database along with the user's profile data.

[1103] The server periodically queries and extracts all user and sentiment data from the database to generate a training dataset. This is used to run a machine learning algorithm, such as deep learning, to train a generative AI model. The accuracy of the trained model is evaluated, and parameters are adjusted or retrained as needed. The trained AI model is then deployed to an endpoint and incorporated into the recommender system.

[1104] When a user logs in and requests "new recommended movies," the device sends the logged-in user ID and recommendation request data to the server. The server uses an AI model to select the most suitable movie based on the user's profile and emotional data. For example, if the user is relaxed, it will suggest a "comedy movie," and if they are nervous, it will suggest an "action movie." The recommendation results are returned to the device in JSON format and displayed in the user interface.

[1105] Additionally, the server periodically collects and stores in its database comments, interviews, and behind-the-scenes information from directors and writers. This additional content is then displayed to users on the detail page of the recommended film.

[1106] When a user purchases a monthly subscription to access premium content, the device sends the user's payment information as a JSON-formatted payload to the server. The server processes the received payment information in conjunction with the payment gateway and receives the result. If the payment process is successful, the user's subscription status is updated in the database and set to "active." A success notification is displayed to the user on the device.

[1107] Finally, the server receives advertising information from advertisers and production companies and stores it in a database. Based on the user's profile data and emotional data, it selects appropriate advertisements. For example, if the user is excited, it will display advertisements for action movies, and if the user is relaxed, it will display advertisements for comedy movies. These advertisements are then displayed on the device's user interface.

[1108] Prompt Sentence Examples

[1109] "Suggest recommended works to users who are relaxing"

[1110] "How can we select the best entertainment based on user emotional data?"

[1111] In this way, the system of the present invention is able to provide a highly personalized entertainment experience based on the user's emotions and preferences.

[1112] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1113] Step 1:

[1114] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[1115] Input: User preferences and past browsing history (e.g., "I like horror movies," "I often read suspense manga," "Movies I've seen in the past: A, B, C")

[1116] Output: User registration data constructed in JSON format

[1117] Specific actions: A user accesses the system, enters information into a web form or application screen, and presses the submit button.

[1118] Step 2:

[1119] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[1120] Input: User-entered preferences and browsing history

[1121] Output: JSON format payload (constructed data)

[1122] Specific operation: The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[1123] Step 3:

[1124] The server parses the received user data and stores it in the appropriate database tables.

[1125] Input: JSON format user data received from the device

[1126] Output: User information stored in the database

[1127] Specific operation: The server parses the JSON data and saves the data in tables such as user_info and viewing_history.

[1128] Step 4:

[1129] Using the device's built-in camera and microphone, emotional data is collected in real time from the user's facial expressions and voice.

[1130] Input: User's facial expressions and voice

[1131] Output: Obtained emotion data (e.g., "Emotion data: Surprise, Intensity: 0.8")

[1132] Specific operation: The device uses the camera and microphone to run facial expression analysis algorithms and voice analysis algorithms to recognize emotions.

[1133] Step 5:

[1134] The emotion data acquired by the device is transmitted to the server.

[1135] Input: Acquired emotion data

[1136] Output: Emotion data (payload) sent to the server

[1137] Specific operation: The emotion data acquired by the device is converted into JSON format and sent to the server.

[1138] Step 6:

[1139] The server integrates the received emotion data into the profile data and stores it in a database.

[1140] Input: Emotion data received from the device

[1141] Output: Consolidated data stored in a database

[1142] Specific operation: The server connects the received emotion data with the profile data and stores it in a table such as user_emotions.

[1143] Step 7:

[1144] The server periodically queries and extracts all user and sentiment data stored in the database.

[1145] Input: User information and emotion data from the database

[1146] Output: The generated training dataset

[1147] What happens: The server runs SQL queries to extract the necessary data and build a training dataset.

[1148] Step 8:

[1149] The server runs machine learning algorithms (e.g., deep learning) to train a generative AI model that includes emotion data.

[1150] Input: Training dataset

[1151] Output: A trained generative AI model

[1152] Specific operation: The server trains the model using libraries such as TensorFlow and PyTorch.

[1153] Step 9:

[1154] The server evaluates the accuracy of the trained generative AI model and adjusts parameters or retrains it as necessary.

[1155] Input: trained generative AI model, evaluation dataset

[1156] Output: Accuracy evaluation results, model after parameter adjustment

[1157] How it works: The server evaluates the accuracy of the model and, if improvement is needed, adjusts the hyperparameters and retrains it.

[1158] Step 10:

[1159] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1160] Input: A trained AI model

[1161] Output: A deployed model endpoint

[1162] Specific behavior: The server deploys the model to an API endpoint, making it accessible externally.

[1163] Step 11:

[1164] A user logs into the system and requests "new recommended works."

[1165] Input: Login user ID, recommendation request

[1166] Output: Recommendation request data

[1167] What happens: A user logs into the system and requests new recommendations.

[1168] Step 12:

[1169] The device sends the login user ID and recommendation request data to the server.

[1170] Input: Login user ID, recommendation request data

[1171] Output: Recommendation request sent to the server

[1172] Specific operation: The device sends recommendation request data to the server.

[1173] Step 13:

[1174] The server uses a generative AI model to select the most suitable work based on profile data and emotional data.

[1175] Input: Profile data, emotion data, generative AI model

[1176] Output: Best work recommendations

[1177] How it works: The server uses the generated AI model to select the most suitable entertainment content based on the user's profile data and emotional data.

[1178] Step 14:

[1179] The server constructs the recommendation results in JSON format and sends them back to the device.

[1180] Input: Recommendation results

[1181] Output: Recommendation results in JSON format

[1182] Specific operation: The server converts the recommendation results into JSON format and returns them to the device as an HTTP response.

[1183] Step 15:

[1184] The device displays the recommendation results on the user interface.

[1185] Input: Recommendation results in JSON format

[1186] Output: Recommendations displayed in the user interface

[1187] Specific operation: The device analyzes the recommendation results received and displays them on the screen.

[1188] Step 16:

[1189] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1190] Input: Comments, interviews, behind-the-scenes info

[1191] Output: Additional content stored in the database

[1192] Specific operation: The server periodically collects information from providers and stores it in a database.

[1193] Step 17:

[1194] The device will display this additional content to users on the details page of the recommended title.

[1195] Input: Additional content

[1196] Output: Additional content displayed on the details page

[1197] Specific behavior: The device retrieves the additional content and displays it on the work's details page.

[1198] Step 18:

[1199] The user enters payment information to purchase a monthly subscription to access premium content.

[1200] Input: Payment information (e.g. credit card number, expiration date)

[1201] Output: Payment information entered

[1202] What happens: The user enters payment information and clicks submit.

[1203] Step 19:

[1204] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[1205] Input: Payment information

[1206] Output: Payment information payload in JSON format

[1207] Specific operation: The terminal converts the payment information into JSON format and sends it to the server.

[1208] Step 20:

[1209] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1210] Input: Payment information in JSON format

[1211] Output: Payment result

[1212] What happens: Your server sends a request to a payment gateway (e.g., Stripe, PayPal) to process the payment.

[1213] Step 21:

[1214] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[1215] Input: Payment result

[1216] Output: Updated subscription status

[1217] Specific behavior: The server receives notification of successful payment and updates the subscription status in the database to "active".

[1218] Step 22:

[1219] The device displays a successful subscription notification to the user.

[1220] Input: Subscription success notification

[1221] Output: Success notification displayed to the user

[1222] Specific behavior: The device displays the notification received from the server to the user.

[1223] Step 23:

[1224] The server receives advertising information from advertisers and production companies and stores it in a database.

[1225] Input: Advertisement information

[1226] Output: Advertisement information stored in the database

[1227] Specific operation: The server collects advertising data from advertisers and stores it in a database.

[1228] Step 24:

[1229] The server selects appropriate advertisements based on the user's profile data and emotional data.

[1230] Input: Profile data, emotion data, advertising information

[1231] Output: Targeted ads

[1232] How it works: The server analyzes the user's data and selects ads that match their emotional state at the time.

[1233] Step 25:

[1234] The device displays targeted advertisements in the user interface.

[1235] Enter: targeted advertising

[1236] Output: Ad displayed in the user interface

[1237] What happens: The device displays targeted ads in the user interface.

[1238] (Application example 2)

[1239] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1240] To improve the quality of individual entertainment experiences, there is a need to provide more accurate recommendations by taking into account not only users' preferences and viewing history, but also their real-time emotional state. Another challenge is to improve user satisfaction by appropriately providing additional content, comments, interviews, and other information about entertainment works. Furthermore, there is a need to improve the accuracy of targeted advertising and display appropriate ads to users.

[1241] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1242] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending optimal entertainment works to a user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for acquiring real-time emotional data of the user, and means for recommending entertainment works based on the acquired emotional data, thereby enabling advanced personalization based on user preferences and real-time emotional data.

[1243] "Personal profile data" refers to information related to an individual, such as a user's preferences, viewing history, and past viewing data.

[1244] "Generative AI" refers to a system that uses machine learning algorithms and deep learning technology to build and learn models based on user data and make predictions and recommendations.

[1245] "Recommendation methods" refers to technology that analyzes a user's profile data and emotional data to suggest the most suitable entertainment works for that user.

[1246] "Additional Content" refers to additional information accompanying an entertainment production, such as commentary, interviews, behind-the-scenes information, etc.

[1247] "Means for managing monthly subscriptions" refers to technology that manages the payment procedures and usage status required for users to use the service on an ongoing basis.

[1248] "Means for targeting ads" refers to technology that selects and displays appropriate ads to specific users based on their profile data.

[1249] "Real-time emotional data" refers to data that indicates the emotional state of the user at that moment, obtained from their facial expressions, voice, etc.

[1250] "Means of acquiring emotional data" refers to technology that uses devices such as cameras and microphones to analyze and acquire emotions from users' reactions.

[1251] The present invention relates to an entertainment recommendation system that utilizes user profile data and real-time emotional data to provide a personalized entertainment experience using generative AI.

[1252] User profile data collection

[1253] When a user registers with the system, they first enter information about their preferences and past browsing history into a new registration form. For example, they provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this information to the server as a JSON-formatted payload. The server analyzes the received data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1254] Acquiring real-time emotion data

[1255] The device uses a built-in camera and microphone to capture emotional data in real time from the user's facial expressions and voice. For example, it analyzes the user's facial expressions and tone of voice while watching a movie and recognizes emotions such as "surprise," "happiness," and "fear." The device then transmits the captured emotional data to a server, which then integrates the received data into profile data and stores it in a database.

[1256] Tech stack for invention

[1257] Hardware: Smartphone, head-mounted display, built-in camera, microphone

[1258] Software: Python, OpenCV (facial expression recognition), PyAudio (voice recognition), TensorFlow (AI model), MySQL (database)

[1259] Creating and training AI models

[1260] The server periodically queries and extracts all user and sentiment data stored in the database, integrates the sentiment data with profile data, and generates a training dataset. The server then runs a machine learning algorithm (e.g., deep learning) to train a generative AI model that includes the sentiment data. The trained model is then deployed to an endpoint and incorporated into the recommender system.

[1261] Providing recommendations

[1262] When a user logs in to the system and requests "new recommended titles," the device sends the login user ID and recommendation request data to the server. The server uses a generative AI model to select the most suitable title based on the profile data and emotional data, and returns the recommendation results in JSON format to the device. The device then displays the recommendation results on the user interface.

[1263] Specific examples

[1264] For example, if a user is using a movie viewing app, the following prompt is used:

[1265] Example prompt for user registration:

[1266] What are your movie and TV preferences?

[1267] I like horror.

[1268] Recently seen movies: A, B, C

[1269] Emotion detection prompt example:

[1270] We're analyzing your facial expressions. Please smile and stay relaxed for the camera.

[1271] Providing additional content

[1272] The server periodically collects comments from directors and writers, interviews, and behind-the-scenes information, storing them in a database, and the device displays this additional content to the user on the detail page of the recommended film.

[1273] Managing your monthly subscription

[1274] When a user purchases a monthly subscription to access premium content, they enter their payment information and the terminal sends the user's payment information as a JSON-formatted payload to the server. The server processes the received payment information in conjunction with the payment gateway and receives the result. If the payment process is successful, the user's subscription status is updated in the database to "active." The terminal then displays a notification of successful subscription to the user.

[1275] Advertising and Event Management

[1276] The server receives advertising information from advertisers and production companies and stores it in a database. The server selects appropriate advertisements based on the user's profile data and emotional data. For example, when a user is "excited," it displays advertisements for related action movies, and when a user is "relaxed," it displays advertisements for comedy movies, displaying targeted advertisements that match the user's emotional state.

[1277] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1278] Step 1:

[1279] A user accesses the system and fills in a new registration form with information about their preferences and past browsing history.

[1280] Users provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[1281] The device sends this information to the server as a JSON-formatted payload.

[1282] Input: User profile information

[1283] Output: Payload in JSON format

[1284] Step 2:

[1285] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1286] Input: User data in JSON format

[1287] Output: User data stored in the database

[1288] Step 3:

[1289] The device uses its built-in camera and microphone to capture emotional data in real time from the user's facial expressions and voice.

[1290] For example, it analyzes the user's facial expressions and tone of voice while they are watching a movie and recognizes emotions such as "surprise," "joy," and "fear."

[1291] Input: User's facial expression video and voice data

[1292] Output: Real-time emotion data

[1293] Step 4:

[1294] The device transmits the acquired emotion data to the server.

[1295] The server integrates the emotion data with the profile data and stores it in a database.

[1296] Input: Real-time emotion data

[1297] Output: Unified profile data

[1298] Step 5:

[1299] The server periodically queries and extracts all user and emotion data stored in the database.

[1300] Integrate the data and generate a training dataset.

[1301] Input: User data and emotion data in the database

[1302] Output: Training dataset

[1303] Step 6:

[1304] The server runs machine learning algorithms (e.g., deep learning) to train generative AI models that include emotion data.

[1305] Input: Training dataset

[1306] Output: A trained generative AI model

[1307] Step 7:

[1308] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[1309] Input: A trained model

[1310] Output: Accuracy evaluation results, optimized generative AI model

[1311] Step 8:

[1312] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1313] Input: Optimized generative AI model

[1314] Output: Deployed AI model

[1315] Step 9:

[1316] The user logs into the system and requests "new recommended works."

[1317] Input: User login information, recommendation request

[1318] Output: Request data

[1319] Step 10:

[1320] The server receives the request data and uses a generative AI model to select the most suitable work based on the profile data and emotional data.

[1321] Input: Request data, profile data, emotion data

[1322] Output: Optimized recommendation results

[1323] Step 11:

[1324] The server constructs the recommendation results in JSON format and sends them back to the device.

[1325] Input: Optimized recommendation results

[1326] Output: Recommendation data in JSON format

[1327] Step 12:

[1328] The device displays the recommendation results in the user interface.

[1329] Users can select from the displayed works and enjoy entertainment.

[1330] Input: Recommendation data in JSON format

[1331] Output: Recommendation results displayed on the screen

[1332] Step 13:

[1333] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1334] Input: Additional information from directors and writers

[1335] Output: Additional content stored in the database

[1336] Step 14:

[1337] The device will display this additional content to the user on the detail page of the recommended title.

[1338] Input: detailed data of recommended works, additional content

[1339] Output: Additional content shown on the display

[1340] Step 15:

[1341] The user enters payment information to purchase a monthly subscription to access premium content.

[1342] The terminal sends the user's payment information to the server as a JSON-formatted payload.

[1343] Input: User's payment information

[1344] Output: Payment data in JSON format

[1345] Step 16:

[1346] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1347] If the payment is successful, the server updates the user's subscription status in the database to "active" and the terminal displays a successful subscription notification to the user.

[1348] Input: Payment data in JSON format, payment gateway results

[1349] Output: Subscription status in "Active" state

[1350] Step 17:

[1351] The server receives advertising information from advertisers and production companies and stores it in a database.

[1352] Input: Advertisement information

[1353] Output: Ad data stored in a database

[1354] Step 18:

[1355] The server selects appropriate advertisements based on the user's profile data and emotional data.

[1356] For example, when a user is "excited," ads for related action movies are displayed, and when a user is "relaxed," ads for comedy movies are displayed.

[1357] Input: Profile data, emotion data, advertising information

[1358] Output: Optimized advertising data

[1359] Step 19:

[1360] The device displays targeted advertisements in the user interface.

[1361] Input: Optimized Ad Data

[1362] Output: Targeted ads displayed on the screen

[1363] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1364] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1365] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1366] [Third embodiment]

[1367] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1368] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1369] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1370] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1371] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1372] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1373] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1374] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1375] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[1376] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1377] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1378] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1379] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized manga and movie recommendations. This system selects the most suitable works based on the user's past viewing history and preferences, and also provides additional information such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[1380] User profile data collection

[1381] 1. A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[1382] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[1383] 2. The device sends the user's input information to the server.

[1384] The terminal sends the entered data to the server as a JSON formatted payload.

[1385] 3. The server stores the received user data in a database.

[1386] The server analyzes the received data and stores it in the appropriate tables. For example, the user's basic information is stored in the "users" table, and the browsing history is stored in the "viewing_history" table.

[1387] Creating and training AI models

[1388] 1. The server trains the AI ​​model using user data in the database.

[1389] The server periodically extracts and pre-processes the data.

[1390] 2. The server uses common machine learning algorithms (e.g., deep learning) to generate a model based on the user's preferences.

[1391] Evaluate the accuracy of the model and adjust parameters or retrain as needed.

[1392] 3. The server deploys the trained model and incorporates it into the recommender system.

[1393] Once deployed, the model quickly generates recommendations upon request.

[1394] Providing recommendations

[1395] 1. A user logs in to the system and requests "new recommended works."

[1396] After logging in, you will be able to request recommendations on your dashboard.

[1397] 2. The device sends a recommendation request to the server.

[1398] Send the request data along with the user ID.

[1399] 3. The server uses an AI model to select works that match the user's preferences and generate recommendation results.

[1400] For example, if a user likes "horror movies," they can select "A," "B," or "C" from the latest horror movies.

[1401] 4. The server sends the recommendation results to the device.

[1402] JSON data including the work title, thumbnail, description, etc. is returned.

[1403] 5. The device displays the recommendation results to the user.

[1404] The user interface displays information about movies "A," "B," and "C."

[1405] Providing additional content

[1406] 1. The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[1407] We regularly obtain additional information from partner media and APIs.

[1408] 2. Display this additional content on the details page of the title for which your device was recommended.

[1409] For example, it provides users with comments and interviews from the director of movie "A."

[1410] Managing your monthly subscription

[1411] 1. A user wants access to premium content and signs up for a monthly subscription.

[1412] Enter your payment information and start your subscription.

[1413] 2. The terminal sends the payment information to the server and processes the payment.

[1414] 3. The server receives the payment processing result and updates the user's subscription status.

[1415] Updates the user status in the database to "active".

[1416] 4. The device displays a successful subscription notification to the user.

[1417] Advertising and Event Management

[1418] 1. The server receives advertising information from advertisers and production companies.

[1419] Store advertising materials provided by advertisers and save them in a database.

[1420] 2. The server selects appropriate ads based on the user's profile data.

[1421] Select targeted advertising based on your interests.

[1422] 3. The device displays appropriate advertisements in the user's interface.

[1423] Display targeted ads on your dashboard and product detail pages.

[1424] The above is a specific embodiment for carrying out the present invention. As a result, in a world where entertainment options are becoming more diverse, it is possible to recommend the most suitable works to users, enabling them to enjoy a deeper entertainment experience.

[1425] The processing flow will be explained below.

[1426] User profile data collection

[1427] Step 1:

[1428] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[1429] Step 2:

[1430] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[1431] Step 3:

[1432] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1433] Creating and training AI models

[1434] Step 1:

[1435] The server periodically queries and extracts all user data stored in the database.

[1436] Step 2:

[1437] The server preprocesses the extracted data to generate a training dataset for the AI ​​model, including data cleaning and feature engineering.

[1438] Step 3:

[1439] The server runs machine learning algorithms (e.g., deep learning) to train an AI model based on user preferences.

[1440] Step 4:

[1441] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[1442] Step 5:

[1443] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1444] Providing recommendations

[1445] Step 1:

[1446] A user logs into the system and requests "new recommended works."

[1447] Step 2:

[1448] The device sends the login user ID and recommendation request data to the server.

[1449] Step 3:

[1450] Based on the request data received by the server, a trained AI model is called up to select works that match the user's preferences.

[1451] Step 4:

[1452] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[1453] Step 5:

[1454] The device displays the recommendation results on the user interface.

[1455] Providing additional content

[1456] Step 1:

[1457] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1458] Step 2:

[1459] The device will display this additional content to users on the details page of the recommended title.

[1460] Managing your monthly subscription

[1461] Step 1:

[1462] A user enters payment information to purchase a monthly subscription to access premium content.

[1463] Step 2:

[1464] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[1465] Step 3:

[1466] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1467] Step 4:

[1468] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[1469] Step 5:

[1470] The device displays a successful subscription notification to the user.

[1471] Advertising and Event Management

[1472] Step 1:

[1473] The server receives advertising information from advertisers and production companies and stores it in a database.

[1474] Step 2:

[1475] The server selects appropriate ads based on the user's profile data.

[1476] Step 3:

[1477] The device displays targeted advertisements in the user interface.

[1478] Example 1

[1479] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1480] In today's entertainment industry, it is difficult for users to find the most suitable titles from the vast number of titles available. It is also not easy to provide additional content and advertisements that match users' interests. Furthermore, as user preferences change over time, AI models must be continuously updated. A method to solve these problems is needed.

[1481] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1482] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending entertainment works that are most suitable for the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for processing recommendation requests based on the user's visit history and preferences, means for providing comments and interviews from related creators as additional content, and means for periodically extracting user data from a database and updating the generative AI model. This allows users to easily find entertainment works and related content that suit their preferences. The user experience is also improved through individually optimized advertisements and continuously updated recommendations.

[1483] "Personal profile data" refers to data that includes a user's preferences, past browsing history, viewing history, personal information, etc.

[1484] "Generative AI" is an artificial intelligence model trained using user profile data to recommend entertainment content based on user preferences.

[1485] "Recommendation" is the act of recommending the most suitable entertainment works based on the user's profile data.

[1486] "Additional content" refers to additional information related to the recommended work, such as comments and interviews from directors and writers, and behind-the-scenes information.

[1487] A "monthly subscription" is a subscription system that allows users to access certain services or additional content by paying a fixed monthly fee.

[1488] "Targeting ads" means using a user's profile data to select and display ads that are most relevant to that user.

[1489] "Visit history" is a record of the pages and content a user has accessed within the system.

[1490] A "recommendation request" is a request from a user to the system for new recommendations.

[1491] "Updating using generative AI models" means continually retraining the artificial intelligence model with the latest user data to keep improving its accuracy.

[1492] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized entertainment recommendations and related additional content. Specific embodiments for implementing the present invention are described below.

[1493] User profile data collection

[1494] A user accesses the system and enters their preferences and past browsing history into a new registration form. For example, they might enter information such as "I like horror movies," "I often read suspense manga," or "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which then stores the received data in a database. This data is primarily exchanged using the JSON format.

[1495] Creating and training AI models

[1496] The server trains the AI ​​model using user data stored in the database. Specifically, it preprocesses the data using Python and deep learning frameworks such as TensorFlow and PyTorch, and then builds and trains the model. It periodically extracts data from the database and uses the generative AI model to update the model. This ensures that the model is always up to date with new user preferences.

[1497] Providing recommendations

[1498] A user logs in to the system and requests "new recommended movies." The device sends the recommendation request to the server, which uses an AI model to select movies that match the user's preferences. For example, if the user likes "horror movies," they can select "A," "B," and "C" from the latest horror movies. The server sends the recommendation results to the device, which then displays them to the user.

[1499] Providing additional content

[1500] The server retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, it might provide the user with comments and interviews from the director of film "A."

[1501] Managing your monthly subscription

[1502] A user wants access to premium content and signs up for a monthly subscription. The user enters payment information, which the device sends to the server for payment processing. The server receives the payment processing result, updates the user's subscription status, and the device displays a successful subscription notification to the user.

[1503] Advertising and Event Management

[1504] The server receives advertising information from advertisers and production companies and selects appropriate advertisements based on the user's profile data. The device displays the appropriate advertisements on the user's interface. In this way, the user can also be provided with other commercial information.

[1505] Examples of concrete examples and prompts

[1506] As a concrete example, the system may recommend the latest horror movies "X," "Y," and "Z" to User A, who previously registered that he "likes horror movies." It may also be possible to provide an interview with the author of the manga "Psychic Battle" as additional premium content.

[1507] Examples of prompts include:

[1508] "Recommend three horror movies based on the user's preferences."

[1509] "Please display an interview with the author of the manga 'Psychic Battle' as premium content."

[1510] This allows the present invention to optimize users' entertainment choices and provide additional value, and it also makes it possible to realize attractive services for users through targeted advertising and subscription management.

[1511] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1512] Step 1:

[1513] A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[1514] Input: New registration form, user preferences and browsing history

[1515] Specific actions: Enter information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C" into a web browser or mobile app.

[1516] Output: User information entered

[1517] Step 2:

[1518] The terminal transmits the user's input information to the server.

[1519] Input: Information entered by the user

[1520] Specific operation: Front-end code (JavaScript or Swift) converts the input information into JSON format and sends it to the server via an HTTPS request.

[1521] Output: JSON data sent to the server

[1522] Step 3:

[1523] The server stores the received user data in a database.

[1524] Input: JSON data sent from the terminal

[1525] What it does: The server uses backend code (Python or Node.js) to parse the incoming data, generate appropriate SQL queries, and store the data in a MySQL or PostgreSQL database.

[1526] Output: User data stored in the database

[1527] Step 4:

[1528] The server trains the AI ​​model using user data in the database.

[1529] Input: Raw data in the database

[1530] What it does: Use Python and TensorFlow or PyTorch to preprocess data and train a deep learning model, including the training and evaluation processes.

[1531] Output: A trained AI model

[1532] Step 5:

[1533] The server uses the generated AI model to generate recommendation results.

[1534] Input: A trained AI model and specific user data

[1535] How it works: User data is input into the AI ​​model to generate recommendations. For example, it recommends the latest horror movies to a user who likes "horror movies."

[1536] Output: Recommendation results

[1537] Step 6:

[1538] The server sends the recommendation results to the terminal.

[1539] Input: Generated recommendation results

[1540] Specific operation: The server converts the recommendation results into JSON format and sends them to the terminal as an HTTP response.

[1541] Output: Recommendation results sent to the device

[1542] Step 7:

[1543] The device displays the recommendation results to the user.

[1544] Input: JSON data received from the server

[1545] Specific operation: The front end parses the received data and displays information such as movies "A", "B", and "C" in the user interface.

[1546] Output: Recommendation results displayed to the user

[1547] Step 8:

[1548] The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[1549] Input: Additional information from external media or API

[1550] Specific operation: The server periodically obtains information using the API of the partner media and stores the obtained additional information in a database.

[1551] Output: Additional content stored in the database

[1552] Step 9:

[1553] The device will display this additional content on the details page of the recommended title.

[1554] Input: Additional content data obtained from the server

[1555] What happens: The front-end renders the additional content information on the detail page and displays it to the user.

[1556] Output: Additional content displayed on the details page

[1557] Step 10:

[1558] A user wants access to premium content and signs up for a monthly subscription.

[1559] Input: Premium content request and payment information

[1560] What it does: The user enters payment information and presses a button to start a monthly subscription.

[1561] Output: Subscription registration request

[1562] Step 11:

[1563] The terminal transmits the payment information to the server, which processes the payment.

[1564] Input: User's payment information

[1565] What it does: The terminal securely encodes the payment information and sends an HTTPS request to the server, which then processes the payment using the Stripe or PayPal API.

[1566] Output: Payment processing result

[1567] Step 12:

[1568] The server receives the payment transaction result and updates the user's subscription status.

[1569] Input: Payment processing result data

[1570] Specific behavior: The server receives the payment success response and updates the user's subscription status in the database to "active."

[1571] Output: Updated subscription status

[1572] Step 13:

[1573] The device will display a successful subscription notification to the user.

[1574] Input: Subscription status update

[1575] What happens: The front end displays a "Subscription successful" notification to the user.

[1576] Output: Success notification displayed to the user

[1577] Step 14:

[1578] The server receives advertising information from advertisers and production companies.

[1579] Input: Advertising data from advertisers and production companies

[1580] Specific operation: Uses the API provided by the advertiser to obtain advertising materials and save them in a database.

[1581] Output: Ad data stored in a database

[1582] Step 15:

[1583] The server selects appropriate advertisements based on the user's profile data.

[1584] Input: User profile data

[1585] What it does: The server analyzes user data and uses targeting algorithms to select appropriate ads.

[1586] Output: Selected advertising data

[1587] Step 16:

[1588] The device displays appropriate advertisements in the user's interface.

[1589] Input: Selected advertising data

[1590] What happens: The front-end renders the ad data into the interface and displays it to the user.

[1591] Output: The ad shown to the user

[1592] The above is the specific processing flow of the program of this system.

[1593] (Application example 1)

[1594] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1595] Today's entertainment consumers face challenges in finding content that suits their tastes among a wide variety of options, often lacking additional information to maximize the appeal of a content, and face the problem of insufficient integration between targeting advertising and payment management systems based on user preferences, resulting in an inconsistent and optimized user experience.

[1596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1597] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending optimal entertainment works to the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for providing a visually easy-to-understand user interface on a smartphone, and means for notifying the user when new recommendations are available. This improves the ease of discovering entertainment works and maximizes the appeal of the works by providing additional information. It also consistently optimizes the user experience and enables effective targeted advertising and payment management.

[1598] "Personal profile data" refers to a set of information that a user has about themselves, including their preferences, past browsing history, and behavioral patterns.

[1599] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to learn patterns from users' profile data and generate appropriate recommendations.

[1600] "Entertainment works" refers to movies, comics, television programs, music, and other media content that users view or consume.

[1601] "Recommendation" refers to the act or result of recommending the most suitable entertainment content based on a user's preferences.

[1602] "Additional Content" refers to supplemental information, such as commentary, interviews, and behind-the-scenes information, related to an entertainment production.

[1603] "Monthly Subscription" refers to a subscription format that allows users to access premium content or services in exchange for a recurring payment.

[1604] "Targeted advertising" refers to the practice of displaying the most relevant advertisements to individual users based on their profile data.

[1605] A "smartphone" refers to a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[1606] "User interface" refers to the screen layout and operation methods used by users to interact with a system.

[1607] "Notification" refers to the act of the system informing the user that new information or recommendations are available.

[1608] This invention is a system that combines user profile data with a generative AI model to recommend customized entertainment works to users. It also provides additional content related to the recommended works, enriching the user's entertainment experience. Specific embodiments for implementing this invention are described below.

[1609] Profile Data Collection

[1610] Users access the system and enter information such as their preferences and past browsing history into a new registration form. For example, they provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which analyzes the received data and stores it in a database. For example, the user's basic information is stored in the users table, and their browsing history is stored in the viewing_history table.

[1611] Creating and training AI models

[1612] The server uses the user data in the database to train an AI model using machine learning algorithms (e.g., deep learning). This AI model is then used to recommend entertainment items based on the user's preferences. The trained AI model is then deployed to a recommender system, which quickly generates recommendation results upon request.

[1613] Providing recommendations

[1614] When a user logs in to the system and requests "new recommended titles," the device sends the request data along with the user ID to the server. The server uses an AI model to select titles that match the user's preferences and generates recommendation results. These results include titles, thumbnails, descriptions, etc., which the device displays to the user. The system also has a function to notify the user when new recommendations are available.

[1615] Providing additional content

[1616] The server periodically retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, the device can provide the user with comments and interviews from the director of film "A."

[1617] Managing your monthly subscription

[1618] If a user wants access to premium content, they sign up for a monthly subscription. Payment information is sent from the device to the server, which processes the payment. Based on the transaction result, the user's subscription status is updated in the database.

[1619] Advertising and Event Management

[1620] The server receives advertising information from advertisers and production companies and selects appropriate ads based on user profile data, allowing it to provide the most relevant ads to each individual user.

[1621] Examples and prompts

[1622] If a user says "I like horror movies" and enters "Movies I've recently seen are A, B, and C":

[1623] Register with user ID 123

[1624] Submit a recommendation request

[1625] AI recommends "latest horror movies D, E, F"

[1626] Also displays additional information including director comments and interviews

[1627] Example prompt sentence:

[1628] Input: User likes horror movies and requests new movie recommendations based on recently watched movies A, B, and C.

[1629] Output: A list of the latest horror movies D, E, F with additional information about them (director comments, interviews, etc.).

[1630] Using this system, users can be provided with the most suitable entertainment content, enriching their entertainment experience.

[1631] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1632] Step 1:

[1633] A user accesses the system and enters information such as their preferences and past viewing history into a new registration form. Input content includes "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input data to the server in JSON format. As data input, the user provides their preferred entertainment genre and past viewing history information, and as output, the data is transferred to the server in JSON format.

[1634] Step 2:

[1635] The server parses the received user profile data and stores basic information in the users table and browsing history in the viewing_history table in the database. The server receives the JSON data, parses its contents, and executes queries to store them in the appropriate tables. The input to this step is the user's JSON data, and the output is the creation of a record in the database.

[1636] Step 3:

[1637] The server extracts user profile data from the database and uses a generative AI model to train a recommendation model. A machine learning algorithm (e.g., deep learning) is used to learn patterns based on the profile data. The trained model results undergo accuracy evaluation and parameter adjustment before finally being deployed. The input is user data from the database, and the output is the trained AI model.

[1638] Step 4:

[1639] A user logs in to the system and requests new recommendations. The device sends the user ID and request data to the server. The input for this step is the user's request information, and the request content is sent to the server.

[1640] Step 5:

[1641] The server uses a trained AI model to recommend entertainment works that match the user's preferences. If the user likes "horror movies," it will select several of the latest horror movies. Specifically, the AI ​​model receives the user's profile data as input, generates a list of entertainment works, and returns it to the device in JSON format. The recommendation results are output from the server.

[1642] Step 6:

[1643] The device receives the recommendation results from the server and displays them to the user as a visually easy-to-understand user interface, showing the title, thumbnail, description, etc. of the recommended works. The input to this step is JSON data from the server, and the output is a visually structured display.

[1644] Step 7:

[1645] The server periodically retrieves comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database. Additional information is obtained from partner media and APIs and added to the database. The input to this step is external information data, and storing it in the database is the output.

[1646] Step 8:

[1647] The device displays additional content such as comments and interviews from the director and writer on the details page of the recommended work. Providing comments and interviews from the director of movie "A" provides the user with a deeper entertainment experience. The input of this step is additional information from the database, and the display on the details page is the output.

[1648] Step 9:

[1649] A user wants access to premium content and signs up for a monthly subscription from their device. Payment information is entered and sent from the device to the server. The input to this step is the user's payment information, and the output is the data sent to the server.

[1650] Step 10:

[1651] The server processes the received payment information and updates the user's subscription status in the database. For example, it updates the user's status in the database to "active". The input to this step is the payment information and the output is the status update in the database.

[1652] Step 11:

[1653] The server selects appropriate targeted advertisements based on the user's profile data. The server extracts the user's interests from the profile data stored on the server and selects targeted advertisements based on them. The input for this step is the profile data, and the selected advertisement information is the output.

[1654] Step 12:

[1655] The device displays appropriate advertisements on the user's interface. Targeted advertisements are visually displayed on the dashboard or product detail page. The input of this step is the advertisement information from the server, and the display on the device is the output.

[1656] These processing steps improve entertainment discovery, maximize the appeal of entertainment content by providing additional information, and consistently optimize the user experience, enabling effective targeted advertising and payment management.

[1657] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1658] The present invention is a system that combines personal profile data with generative AI and uses an emotion engine to recognize a user's emotions in real time, providing a customized entertainment experience. The system uses real-time emotion data in addition to the user's past viewing history and preferences to select the most suitable works. It also provides additional information, such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[1659] User profile data collection

[1660] 1. A user accesses the system and fills in a new registration form with information about their preferences and past browsing history.

[1661] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[1662] 2. The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[1663] 3. The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1664] Combining Emotion Engines

[1665] 1. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice.

[1666] For example, it analyzes the user's facial expressions and tone of voice while they are watching a movie and recognizes emotions such as "surprise," "joy," and "fear."

[1667] 2. The device transmits the acquired emotion data to the server.

[1668] 3. The server integrates the received emotion data into the profile data and stores it in a database.

[1669] Creating and training AI models

[1670] 1. The server periodically queries and extracts all user and sentiment data stored in the database.

[1671] The emotion data and profile data are combined to generate a training dataset.

[1672] 2. The server runs a machine learning algorithm (e.g., deep learning) to train an AI model that includes the emotion data.

[1673] 3. The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[1674] 4. The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1675] Providing recommendations

[1676] 1. A user logs in to the system and requests "new recommended works."

[1677] 2. The device sends the login user ID and recommendation request data to the server.

[1678] 3. The server uses an AI model to select the most suitable work based on the profile data and emotional data.

[1679] For example, based on past browsing history and current emotional data, the app will suggest "comedy movies" when the user is "relaxed," and "action movies" when the user is "stressed."

[1680] 4. The server constructs the recommendation results in JSON format and returns them to the device.

[1681] 5. The device displays the recommendation results on the user interface.

[1682] Providing additional content

[1683] 1. The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1684] 2. Display this additional content to users on the details page of the title for which the device was recommended.

[1685] Managing your monthly subscription

[1686] 1. A user enters payment information to purchase a monthly subscription to access premium content.

[1687] 2. The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[1688] 3. The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1689] 4. If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[1690] 5. The device displays a successful subscription notification to the user.

[1691] Advertising and Event Management

[1692] 1. The server receives advertising information from advertisers and production companies and stores it in a database.

[1693] 2. The server selects appropriate ads based on the user's profile data and emotional data.

[1694] For example, when a user is "excited," ads for related action movies might be shown, and when a user is "relaxed," ads for comedy movies might be shown.

[1695] 3. The device displays targeted ads in the user interface.

[1696] The above is a specific embodiment for implementing the present invention. As entertainment options become more diverse, this allows users to recommend the most suitable works and enjoy the entertainment experience more deeply. By combining it with an emotion engine, the degree of customization of the user experience can be further increased.

[1697] The processing flow will be explained below.

[1698] User profile data collection

[1699] Step 1:

[1700] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[1701] Step 2:

[1702] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[1703] Step 3:

[1704] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1705] Combining Emotion Engines

[1706] Step 1:

[1707] Using the device's built-in camera and microphone, emotional data is collected in real time from the user's facial expressions and voice.

[1708] Step 2:

[1709] The device analyzes the emotional data it acquires and classifies emotions such as "joy," "surprise," and "sadness."

[1710] Step 3:

[1711] The device sends the analysis results to the server as a JSON format payload.

[1712] Step 4:

[1713] The server integrates the received emotion data into the profile data and stores it in a database.

[1714] Creating and training AI models

[1715] Step 1:

[1716] The server periodically queries and extracts all user and sentiment data stored in the database.

[1717] Step 2:

[1718] The server preprocesses the extracted data and generates a training dataset for the AI ​​model.

[1719] Step 3:

[1720] The server runs machine learning algorithms (e.g., deep learning) to train an AI model that includes emotion data.

[1721] Step 4:

[1722] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[1723] Step 5:

[1724] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1725] Providing recommendations

[1726] Step 1:

[1727] A user logs into the system and requests "new recommended works."

[1728] Step 2:

[1729] The device sends the login user ID and recommendation request data to the server.

[1730] Step 3:

[1731] The server uses an AI model to select the most suitable work based on profile data and emotional data.

[1732] Step 4:

[1733] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[1734] Step 5:

[1735] The device displays the recommendation results on the user interface.

[1736] Providing additional content

[1737] Step 1:

[1738] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1739] Step 2:

[1740] The device will display this additional content to users on the details page of the recommended title.

[1741] Managing your monthly subscription

[1742] Step 1:

[1743] The user enters payment information to purchase a monthly subscription to access premium content.

[1744] Step 2:

[1745] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[1746] Step 3:

[1747] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1748] Step 4:

[1749] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[1750] Step 5:

[1751] The device displays a successful subscription notification to the user.

[1752] Advertising and Event Management

[1753] Step 1:

[1754] The server receives advertising information from advertisers and production companies and stores it in a database.

[1755] Step 2:

[1756] The server selects appropriate advertisements based on the user's profile data and emotional data.

[1757] Step 3:

[1758] The device displays targeted advertisements in the user interface.

[1759] Example 2

[1760] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1761] In the modern entertainment industry, there is a demand for providing optimal content based on users' diverse preferences and emotions. However, conventional recommendation systems rely solely on user profile data and do not consider real-time emotional data, making it difficult to provide an appropriate entertainment experience for each individual user. Furthermore, there is a lack of systems that handle emotional data and profile data in an integrated manner, which has hindered efforts to improve user experience.

[1762] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1763] In this invention, the server includes means for acquiring user profile data, means for acquiring and storing emotion data in real time, means for training a generative AI model based on the acquired profile data and emotion data, means for using the generative AI model to recommend optimal entertainment works based on the profile data and emotion data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for users, means for targeting advertisements based on the profile data and emotion data, and means for processing payment, thereby enabling the provision of a highly personalized entertainment experience based on the user's emotions and preferences.

[1764] "User profile data" refers to data about a user, such as personal information, preferences, and past browsing history.

[1765] "Emotional data" refers to data on the user's emotional state obtained in real time from their facial expressions and voice.

[1766] "Generative AI model" refers to an artificial intelligence model trained using machine learning algorithms based on user profile data and sentiment data.

[1767] "Entertainment content" refers to content provided based on users' hobbies and interests, such as movies, TV shows, books, music, and games.

[1768] "Additional content" refers to comments from directors and writers, interviews, behind-the-scenes information, etc. related to the recommended works.

[1769] "Monthly subscription" refers to a fee system where users pay a monthly fee to access premium content.

[1770] "Targeting ads" refers to the act of selecting and displaying the most appropriate ads to users based on their profile data and emotional data.

[1771] "Payment Processing" refers to the functionality that processes information and finalizes payments for users to make monthly subscription or other payments.

[1772] This invention is a system that combines personal profile data and emotional data to provide users with a customized entertainment experience. The system uses the user's past viewing history, preferences, and real-time emotional data to select the most suitable content and provide appropriate additional content and advertisements. An embodiment of this system is described below.

[1773] First, the user accesses the system and enters information about their preferences and past browsing history into the new registration form. Specifically, the user provides information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." This sends the user's profile data from the device to the server as a JSON-formatted payload. The server analyzes the received data and stores it in a database.

[1774] Next, the user's emotional data is collected. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice. For example, while the user is watching a movie, the device's camera captures a photo of the user's face and uses an expression analysis algorithm to recognize emotions such as "surprise," "happiness," and "fear." The acquired emotional data is sent to a server and stored in a database along with the user's profile data.

[1775] The server periodically queries and extracts all user and sentiment data from the database to generate a training dataset. This is used to run a machine learning algorithm, such as deep learning, to train a generative AI model. The accuracy of the trained model is evaluated, and parameters are adjusted or retrained as needed. The trained AI model is then deployed to an endpoint and incorporated into the recommender system.

[1776] When a user logs in and requests "new recommended movies," the device sends the logged-in user ID and recommendation request data to the server. The server uses an AI model to select the most suitable movie based on the user's profile and emotional data. For example, if the user is relaxed, it will suggest a "comedy movie," and if they are nervous, it will suggest an "action movie." The recommendation results are returned to the device in JSON format and displayed in the user interface.

[1777] Additionally, the server periodically collects and stores in its database comments, interviews, and behind-the-scenes information from directors and writers. This additional content is then displayed to users on the detail page of the recommended film.

[1778] When a user purchases a monthly subscription to access premium content, the device sends the user's payment information as a JSON-formatted payload to the server. The server processes the received payment information in conjunction with the payment gateway and receives the result. If the payment process is successful, the user's subscription status is updated in the database and set to "active." A success notification is displayed to the user on the device.

[1779] Finally, the server receives advertising information from advertisers and production companies and stores it in a database. Based on the user's profile data and emotional data, it selects appropriate advertisements. For example, if the user is excited, it will display advertisements for action movies, and if the user is relaxed, it will display advertisements for comedy movies. These advertisements are then displayed on the device's user interface.

[1780] Prompt Sentence Examples

[1781] "Suggest recommended works to users who are relaxing"

[1782] "How can we select the best entertainment based on user emotional data?"

[1783] In this way, the system of the present invention is able to provide a highly personalized entertainment experience based on the user's emotions and preferences.

[1784] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1785] Step 1:

[1786] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[1787] Input: User preferences and past browsing history (e.g., "I like horror movies," "I often read suspense manga," "Movies I've seen in the past: A, B, C")

[1788] Output: User registration data constructed in JSON format

[1789] Specific actions: A user accesses the system, enters information into a web form or application screen, and presses the submit button.

[1790] Step 2:

[1791] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[1792] Input: User-entered preferences and browsing history

[1793] Output: JSON format payload (constructed data)

[1794] Specific operation: The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[1795] Step 3:

[1796] The server parses the received user data and stores it in the appropriate database tables.

[1797] Input: JSON format user data received from the device

[1798] Output: User information stored in the database

[1799] Specific operation: The server parses the JSON data and saves the data in tables such as user_info and viewing_history.

[1800] Step 4:

[1801] Using the device's built-in camera and microphone, emotional data is collected in real time from the user's facial expressions and voice.

[1802] Input: User's facial expressions and voice

[1803] Output: Obtained emotion data (e.g., "Emotion data: Surprise, Intensity: 0.8")

[1804] Specific operation: The device uses the camera and microphone to run facial expression analysis algorithms and voice analysis algorithms to recognize emotions.

[1805] Step 5:

[1806] The emotion data acquired by the device is transmitted to the server.

[1807] Input: Acquired emotion data

[1808] Output: Emotion data (payload) sent to the server

[1809] Specific operation: The emotion data acquired by the device is converted into JSON format and sent to the server.

[1810] Step 6:

[1811] The server integrates the received emotion data into the profile data and stores it in a database.

[1812] Input: Emotion data received from the device

[1813] Output: Consolidated data stored in a database

[1814] Specific operation: The server connects the received emotion data with the profile data and stores it in a table such as user_emotions.

[1815] Step 7:

[1816] The server periodically queries and extracts all user and sentiment data stored in the database.

[1817] Input: User information and emotion data from the database

[1818] Output: The generated training dataset

[1819] What happens: The server runs SQL queries to extract the necessary data and build a training dataset.

[1820] Step 8:

[1821] The server runs machine learning algorithms (e.g., deep learning) to train a generative AI model that includes emotion data.

[1822] Input: Training dataset

[1823] Output: A trained generative AI model

[1824] Specific operation: The server trains the model using libraries such as TensorFlow and PyTorch.

[1825] Step 9:

[1826] The server evaluates the accuracy of the trained generative AI model and adjusts parameters or retrains it as necessary.

[1827] Input: trained generative AI model, evaluation dataset

[1828] Output: Accuracy evaluation results, model after parameter adjustment

[1829] How it works: The server evaluates the accuracy of the model and, if improvement is needed, adjusts the hyperparameters and retrains it.

[1830] Step 10:

[1831] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1832] Input: A trained AI model

[1833] Output: A deployed model endpoint

[1834] Specific behavior: The server deploys the model to an API endpoint, making it accessible externally.

[1835] Step 11:

[1836] A user logs into the system and requests "new recommended works."

[1837] Input: Login user ID, recommendation request

[1838] Output: Recommendation request data

[1839] What happens: A user logs into the system and requests new recommendations.

[1840] Step 12:

[1841] The device sends the login user ID and recommendation request data to the server.

[1842] Input: Login user ID, recommendation request data

[1843] Output: Recommendation request sent to the server

[1844] Specific operation: The device sends recommendation request data to the server.

[1845] Step 13:

[1846] The server uses a generative AI model to select the most suitable work based on profile data and emotional data.

[1847] Input: Profile data, emotion data, generative AI model

[1848] Output: Best work recommendations

[1849] How it works: The server uses the generated AI model to select the most suitable entertainment content based on the user's profile data and emotional data.

[1850] Step 14:

[1851] The server constructs the recommendation results in JSON format and sends them back to the device.

[1852] Input: Recommendation results

[1853] Output: Recommendation results in JSON format

[1854] Specific operation: The server converts the recommendation results into JSON format and returns them to the device as an HTTP response.

[1855] Step 15:

[1856] The device displays the recommendation results on the user interface.

[1857] Input: Recommendation results in JSON format

[1858] Output: Recommendations displayed in the user interface

[1859] Specific operation: The device analyzes the recommendation results received and displays them on the screen.

[1860] Step 16:

[1861] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[1862] Input: Comments, interviews, behind-the-scenes info

[1863] Output: Additional content stored in the database

[1864] Specific operation: The server periodically collects information from providers and stores it in a database.

[1865] Step 17:

[1866] The device will display this additional content to users on the details page of the recommended title.

[1867] Input: Additional content

[1868] Output: Additional content displayed on the details page

[1869] Specific behavior: The device retrieves the additional content and displays it on the work's details page.

[1870] Step 18:

[1871] The user enters payment information to purchase a monthly subscription to access premium content.

[1872] Input: Payment information (e.g. credit card number, expiration date)

[1873] Output: Payment information entered

[1874] What happens: The user enters payment information and clicks submit.

[1875] Step 19:

[1876] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[1877] Input: Payment information

[1878] Output: Payment information payload in JSON format

[1879] Specific operation: The terminal converts the payment information into JSON format and sends it to the server.

[1880] Step 20:

[1881] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[1882] Input: Payment information in JSON format

[1883] Output: Payment result

[1884] What happens: Your server sends a request to a payment gateway (e.g., Stripe, PayPal) to process the payment.

[1885] Step 21:

[1886] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[1887] Input: Payment result

[1888] Output: Updated subscription status

[1889] Specific behavior: The server receives notification of successful payment and updates the subscription status in the database to "active".

[1890] Step 22:

[1891] The device displays a successful subscription notification to the user.

[1892] Input: Subscription success notification

[1893] Output: Success notification displayed to the user

[1894] Specific behavior: The device displays the notification received from the server to the user.

[1895] Step 23:

[1896] The server receives advertising information from advertisers and production companies and stores it in a database.

[1897] Input: Advertisement information

[1898] Output: Advertisement information stored in the database

[1899] Specific operation: The server collects advertising data from advertisers and stores it in a database.

[1900] Step 24:

[1901] The server selects appropriate advertisements based on the user's profile data and emotional data.

[1902] Input: Profile data, emotion data, advertising information

[1903] Output: Targeted ads

[1904] How it works: The server analyzes the user's data and selects ads that match their emotional state at the time.

[1905] Step 25:

[1906] The device displays targeted advertisements in the user interface.

[1907] Enter: targeted advertising

[1908] Output: Ad displayed in the user interface

[1909] What happens: The device displays targeted ads in the user interface.

[1910] (Application example 2)

[1911] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1912] To improve the quality of individual entertainment experiences, there is a need to provide more accurate recommendations by taking into account not only users' preferences and viewing history, but also their real-time emotional state. Another challenge is to improve user satisfaction by appropriately providing additional content, comments, interviews, and other information about entertainment works. Furthermore, there is a need to improve the accuracy of targeted advertising and display appropriate ads to users.

[1913] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1914] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending optimal entertainment works to a user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for acquiring real-time emotional data of the user, and means for recommending entertainment works based on the acquired emotional data, thereby enabling advanced personalization based on user preferences and real-time emotional data.

[1915] "Personal profile data" refers to information related to an individual, such as a user's preferences, viewing history, and past viewing data.

[1916] "Generative AI" refers to a system that uses machine learning algorithms and deep learning technology to build and learn models based on user data and make predictions and recommendations.

[1917] "Recommendation methods" refers to technology that analyzes a user's profile data and emotional data to suggest the most suitable entertainment works for that user.

[1918] "Additional Content" refers to additional information accompanying an entertainment production, such as commentary, interviews, behind-the-scenes information, etc.

[1919] "Means for managing monthly subscriptions" refers to technology that manages the payment procedures and usage status required for users to use the service on an ongoing basis.

[1920] "Means for targeting ads" refers to technology that selects and displays appropriate ads to specific users based on their profile data.

[1921] "Real-time emotional data" refers to data that indicates the emotional state of the user at that moment, obtained from their facial expressions, voice, etc.

[1922] "Means of acquiring emotional data" refers to technology that uses devices such as cameras and microphones to analyze and acquire emotions from users' reactions.

[1923] The present invention relates to an entertainment recommendation system that utilizes user profile data and real-time emotional data to provide a personalized entertainment experience using generative AI.

[1924] User profile data collection

[1925] When a user registers with the system, they first enter information about their preferences and past browsing history into a new registration form. For example, they provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this information to the server as a JSON-formatted payload. The server analyzes the received data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1926] Acquiring real-time emotion data

[1927] The device uses a built-in camera and microphone to capture emotional data in real time from the user's facial expressions and voice. For example, it analyzes the user's facial expressions and tone of voice while watching a movie and recognizes emotions such as "surprise," "happiness," and "fear." The device then transmits the captured emotional data to a server, which then integrates the received data into profile data and stores it in a database.

[1928] Tech stack for invention

[1929] Hardware: Smartphone, head-mounted display, built-in camera, microphone

[1930] Software: Python, OpenCV (facial expression recognition), PyAudio (voice recognition), TensorFlow (AI model), MySQL (database)

[1931] Creating and training AI models

[1932] The server periodically queries and extracts all user and sentiment data stored in the database, integrates the sentiment data with profile data, and generates a training dataset. The server then runs a machine learning algorithm (e.g., deep learning) to train a generative AI model that includes the sentiment data. The trained model is then deployed to an endpoint and incorporated into the recommender system.

[1933] Providing recommendations

[1934] When a user logs in to the system and requests "new recommended titles," the device sends the login user ID and recommendation request data to the server. The server uses a generative AI model to select the most suitable title based on the profile data and emotional data, and returns the recommendation results in JSON format to the device. The device then displays the recommendation results on the user interface.

[1935] Specific examples

[1936] For example, if a user is using a movie viewing app, the following prompt is used:

[1937] Example prompt for user registration:

[1938] What are your movie and TV preferences?

[1939] I like horror.

[1940] Recently seen movies: A, B, C

[1941] Emotion detection prompt example:

[1942] We're analyzing your facial expressions. Please smile and stay relaxed for the camera.

[1943] Providing additional content

[1944] The server periodically collects comments from directors and writers, interviews, and behind-the-scenes information, storing them in a database, and the device displays this additional content to the user on the detail page of the recommended film.

[1945] Managing your monthly subscription

[1946] When a user purchases a monthly subscription to access premium content, they enter their payment information and the terminal sends the user's payment information as a JSON-formatted payload to the server. The server processes the received payment information in conjunction with the payment gateway and receives the result. If the payment process is successful, the user's subscription status is updated in the database to "active." The terminal then displays a notification of successful subscription to the user.

[1947] Advertising and Event Management

[1948] The server receives advertising information from advertisers and production companies and stores it in a database. The server selects appropriate advertisements based on the user's profile data and emotional data. For example, when a user is "excited," it displays advertisements for related action movies, and when a user is "relaxed," it displays advertisements for comedy movies, displaying targeted advertisements that match the user's emotional state.

[1949] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1950] Step 1:

[1951] A user accesses the system and fills in a new registration form with information about their preferences and past browsing history.

[1952] Users provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[1953] The device sends this information to the server as a JSON-formatted payload.

[1954] Input: User profile information

[1955] Output: Payload in JSON format

[1956] Step 2:

[1957] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[1958] Input: User data in JSON format

[1959] Output: User data stored in the database

[1960] Step 3:

[1961] The device uses its built-in camera and microphone to capture emotional data in real time from the user's facial expressions and voice.

[1962] For example, it analyzes the user's facial expressions and tone of voice while they are watching a movie and recognizes emotions such as "surprise," "joy," and "fear."

[1963] Input: User's facial expression video and voice data

[1964] Output: Real-time emotion data

[1965] Step 4:

[1966] The device transmits the acquired emotion data to the server.

[1967] The server integrates the emotion data with the profile data and stores it in a database.

[1968] Input: Real-time emotion data

[1969] Output: Unified profile data

[1970] Step 5:

[1971] The server periodically queries and extracts all user and emotion data stored in the database.

[1972] Integrate the data and generate a training dataset.

[1973] Input: User data and emotion data in the database

[1974] Output: Training dataset

[1975] Step 6:

[1976] The server runs machine learning algorithms (e.g., deep learning) to train generative AI models that include emotion data.

[1977] Input: Training dataset

[1978] Output: A trained generative AI model

[1979] Step 7:

[1980] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[1981] Input: A trained model

[1982] Output: Accuracy evaluation results, optimized generative AI model

[1983] Step 8:

[1984] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[1985] Input: Optimized generative AI model

[1986] Output: Deployed AI model

[1987] Step 9:

[1988] The user logs into the system and requests "new recommended works."

[1989] Input: User login information, recommendation request

[1990] Output: Request data

[1991] Step 10:

[1992] The server receives the request data and uses a generative AI model to select the most suitable work based on the profile data and emotional data.

[1993] Input: Request data, profile data, emotion data

[1994] Output: Optimized recommendation results

[1995] Step 11:

[1996] The server constructs the recommendation results in JSON format and sends them back to the device.

[1997] Input: Optimized recommendation results

[1998] Output: Recommendation data in JSON format

[1999] Step 12:

[2000] The device displays the recommendation results in the user interface.

[2001] Users can select from the displayed works and enjoy entertainment.

[2002] Input: Recommendation data in JSON format

[2003] Output: Recommendation results displayed on the screen

[2004] Step 13:

[2005] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[2006] Input: Additional information from directors and writers

[2007] Output: Additional content stored in the database

[2008] Step 14:

[2009] The device will display this additional content to the user on the detail page of the recommended title.

[2010] Input: detailed data of recommended works, additional content

[2011] Output: Additional content shown on the display

[2012] Step 15:

[2013] The user enters payment information to purchase a monthly subscription to access premium content.

[2014] The terminal sends the user's payment information to the server as a JSON-formatted payload.

[2015] Input: User's payment information

[2016] Output: Payment data in JSON format

[2017] Step 16:

[2018] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[2019] If the payment is successful, the server updates the user's subscription status in the database to "active" and the terminal displays a successful subscription notification to the user.

[2020] Input: Payment data in JSON format, payment gateway results

[2021] Output: Subscription status in "Active" state

[2022] Step 17:

[2023] The server receives advertising information from advertisers and production companies and stores it in a database.

[2024] Input: Advertisement information

[2025] Output: Ad data stored in a database

[2026] Step 18:

[2027] The server selects appropriate advertisements based on the user's profile data and emotional data.

[2028] For example, when a user is "excited," ads for related action movies are displayed, and when a user is "relaxed," ads for comedy movies are displayed.

[2029] Input: Profile data, emotion data, advertising information

[2030] Output: Optimized advertising data

[2031] Step 19:

[2032] The device displays targeted advertisements in the user interface.

[2033] Input: Optimized Ad Data

[2034] Output: Targeted ads displayed on the screen

[2035] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[2036] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2037] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[2038] [Fourth embodiment]

[2039] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[2040] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[2041] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[2042] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[2043] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[2044] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[2045] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[2046] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[2047] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[2048] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific 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.

[2049] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[2050] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[2051] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2052] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized manga and movie recommendations. This system selects the most suitable works based on the user's past viewing history and preferences, and also provides additional information such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[2053] User profile data collection

[2054] 1. A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[2055] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[2056] 2. The device sends the user's input information to the server.

[2057] The terminal sends the entered data to the server as a JSON formatted payload.

[2058] 3. The server stores the received user data in a database.

[2059] The server analyzes the received data and stores it in the appropriate tables. For example, the user's basic information is stored in the "users" table, and the browsing history is stored in the "viewing_history" table.

[2060] Creating and training AI models

[2061] 1. The server trains the AI ​​model using user data in the database.

[2062] The server periodically extracts and pre-processes the data.

[2063] 2. The server uses common machine learning algorithms (e.g., deep learning) to generate a model based on the user's preferences.

[2064] Evaluate the accuracy of the model and adjust parameters or retrain as needed.

[2065] 3. The server deploys the trained model and incorporates it into the recommender system.

[2066] Once deployed, the model quickly generates recommendations upon request.

[2067] Providing recommendations

[2068] 1. A user logs in to the system and requests "new recommended works."

[2069] After logging in, you will be able to request recommendations on your dashboard.

[2070] 2. The device sends a recommendation request to the server.

[2071] Send the request data along with the user ID.

[2072] 3. The server uses an AI model to select works that match the user's preferences and generate recommendation results.

[2073] For example, if a user likes "horror movies," they can select "A," "B," or "C" from the latest horror movies.

[2074] 4. The server sends the recommendation results to the device.

[2075] JSON data including the work title, thumbnail, description, etc. is returned.

[2076] 5. The device displays the recommendation results to the user.

[2077] The user interface displays information about movies "A," "B," and "C."

[2078] Providing additional content

[2079] 1. The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[2080] We regularly obtain additional information from partner media and APIs.

[2081] 2. Display this additional content on the details page of the title for which your device was recommended.

[2082] For example, it provides users with comments and interviews from the director of movie "A."

[2083] Managing your monthly subscription

[2084] 1. A user wants access to premium content and signs up for a monthly subscription.

[2085] Enter your payment information and start your subscription.

[2086] 2. The terminal sends the payment information to the server and processes the payment.

[2087] 3. The server receives the payment processing result and updates the user's subscription status.

[2088] Updates the user status in the database to "active".

[2089] 4. The device displays a successful subscription notification to the user.

[2090] Advertising and Event Management

[2091] 1. The server receives advertising information from advertisers and production companies.

[2092] Store advertising materials provided by advertisers and save them in a database.

[2093] 2. The server selects appropriate ads based on the user's profile data.

[2094] Select targeted advertising based on your interests.

[2095] 3. The device displays appropriate advertisements in the user's interface.

[2096] Display targeted ads on your dashboard and product detail pages.

[2097] The above is a specific embodiment for carrying out the present invention. As a result, in a world where entertainment options are becoming more diverse, it is possible to recommend the most suitable works to users, enabling them to enjoy a deeper entertainment experience.

[2098] The processing flow will be explained below.

[2099] User profile data collection

[2100] Step 1:

[2101] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[2102] Step 2:

[2103] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[2104] Step 3:

[2105] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[2106] Creating and training AI models

[2107] Step 1:

[2108] The server periodically queries and extracts all user data stored in the database.

[2109] Step 2:

[2110] The server preprocesses the extracted data to generate a training dataset for the AI ​​model, including data cleaning and feature engineering.

[2111] Step 3:

[2112] The server runs machine learning algorithms (e.g., deep learning) to train an AI model based on user preferences.

[2113] Step 4:

[2114] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[2115] Step 5:

[2116] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[2117] Providing recommendations

[2118] Step 1:

[2119] A user logs into the system and requests "new recommended works."

[2120] Step 2:

[2121] The device sends the login user ID and recommendation request data to the server.

[2122] Step 3:

[2123] Based on the request data received by the server, a trained AI model is called up to select works that match the user's preferences.

[2124] Step 4:

[2125] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[2126] Step 5:

[2127] The device displays the recommendation results on the user interface.

[2128] Providing additional content

[2129] Step 1:

[2130] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[2131] Step 2:

[2132] The device will display this additional content to users on the details page of the recommended title.

[2133] Managing your monthly subscription

[2134] Step 1:

[2135] A user enters payment information to purchase a monthly subscription to access premium content.

[2136] Step 2:

[2137] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[2138] Step 3:

[2139] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[2140] Step 4:

[2141] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[2142] Step 5:

[2143] The device displays a successful subscription notification to the user.

[2144] Advertising and Event Management

[2145] Step 1:

[2146] The server receives advertising information from advertisers and production companies and stores it in a database.

[2147] Step 2:

[2148] The server selects appropriate ads based on the user's profile data.

[2149] Step 3:

[2150] The device displays targeted advertisements in the user interface.

[2151] Example 1

[2152] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2153] In today's entertainment industry, it is difficult for users to find the most suitable titles from the vast number of titles available. It is also not easy to provide additional content and advertisements that match users' interests. Furthermore, as user preferences change over time, AI models must be continuously updated. A method to solve these problems is needed.

[2154] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2155] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending entertainment works that are most suitable for the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for processing recommendation requests based on the user's visit history and preferences, means for providing comments and interviews from related creators as additional content, and means for periodically extracting user data from a database and updating the generative AI model. This allows users to easily find entertainment works and related content that suit their preferences. The user experience is also improved through individually optimized advertisements and continuously updated recommendations.

[2156] "Personal profile data" refers to data that includes a user's preferences, past browsing history, viewing history, personal information, etc.

[2157] "Generative AI" is an artificial intelligence model trained using user profile data to recommend entertainment content based on user preferences.

[2158] "Recommendation" is the act of recommending the most suitable entertainment works based on the user's profile data.

[2159] "Additional content" refers to additional information related to the recommended work, such as comments and interviews from directors and writers, and behind-the-scenes information.

[2160] A "monthly subscription" is a subscription system that allows users to access certain services or additional content by paying a fixed monthly fee.

[2161] "Targeting ads" means using a user's profile data to select and display ads that are most relevant to that user.

[2162] "Visit history" is a record of the pages and content a user has accessed within the system.

[2163] A "recommendation request" is a request from a user to the system for new recommendations.

[2164] "Updating using generative AI models" means continually retraining the artificial intelligence model with the latest user data to keep improving its accuracy.

[2165] The present invention is a system that combines personal profile data and generative AI to analyze user preferences and provide customized entertainment recommendations and related additional content. Specific embodiments for implementing the present invention are described below.

[2166] User profile data collection

[2167] A user accesses the system and enters their preferences and past browsing history into a new registration form. For example, they might enter information such as "I like horror movies," "I often read suspense manga," or "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which then stores the received data in a database. This data is primarily exchanged using the JSON format.

[2168] Creating and training AI models

[2169] The server trains the AI ​​model using user data stored in the database. Specifically, it preprocesses the data using Python and deep learning frameworks such as TensorFlow and PyTorch, and then builds and trains the model. It periodically extracts data from the database and uses the generative AI model to update the model. This ensures that the model is always up to date with new user preferences.

[2170] Providing recommendations

[2171] A user logs in to the system and requests "new recommended movies." The device sends the recommendation request to the server, which uses an AI model to select movies that match the user's preferences. For example, if the user likes "horror movies," they can select "A," "B," and "C" from the latest horror movies. The server sends the recommendation results to the device, which then displays them to the user.

[2172] Providing additional content

[2173] The server retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, it might provide the user with comments and interviews from the director of film "A."

[2174] Managing your monthly subscription

[2175] A user wants access to premium content and signs up for a monthly subscription. The user enters payment information, which the device sends to the server for payment processing. The server receives the payment processing result, updates the user's subscription status, and the device displays a successful subscription notification to the user.

[2176] Advertising and Event Management

[2177] The server receives advertising information from advertisers and production companies and selects appropriate advertisements based on the user's profile data. The device displays the appropriate advertisements on the user's interface. In this way, the user can also be provided with other commercial information.

[2178] Examples of concrete examples and prompts

[2179] As a concrete example, the system may recommend the latest horror movies "X," "Y," and "Z" to User A, who previously registered that he "likes horror movies." It may also be possible to provide an interview with the author of the manga "Psychic Battle" as additional premium content.

[2180] Examples of prompts include:

[2181] "Recommend three horror movies based on the user's preferences."

[2182] "Please display an interview with the author of the manga 'Psychic Battle' as premium content."

[2183] This allows the present invention to optimize users' entertainment choices and provide additional value, and it also makes it possible to realize attractive services for users through targeted advertising and subscription management.

[2184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2185] Step 1:

[2186] A user accesses the system and enters information such as preferences and past browsing history into a new registration form.

[2187] Input: New registration form, user preferences and browsing history

[2188] Specific actions: Enter information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C" into a web browser or mobile app.

[2189] Output: User information entered

[2190] Step 2:

[2191] The terminal transmits the user's input information to the server.

[2192] Input: Information entered by the user

[2193] Specific operation: Front-end code (JavaScript or Swift) converts the input information into JSON format and sends it to the server via an HTTPS request.

[2194] Output: JSON data sent to the server

[2195] Step 3:

[2196] The server stores the received user data in a database.

[2197] Input: JSON data sent from the terminal

[2198] What it does: The server uses backend code (Python or Node.js) to parse the incoming data, generate appropriate SQL queries, and store the data in a MySQL or PostgreSQL database.

[2199] Output: User data stored in the database

[2200] Step 4:

[2201] The server trains the AI ​​model using user data in the database.

[2202] Input: Raw data in the database

[2203] What it does: Use Python and TensorFlow or PyTorch to preprocess data and train a deep learning model, including the training and evaluation processes.

[2204] Output: A trained AI model

[2205] Step 5:

[2206] The server uses the generated AI model to generate recommendation results.

[2207] Input: A trained AI model and specific user data

[2208] How it works: User data is input into the AI ​​model to generate recommendations. For example, it recommends the latest horror movies to a user who likes "horror movies."

[2209] Output: Recommendation results

[2210] Step 6:

[2211] The server sends the recommendation results to the terminal.

[2212] Input: Generated recommendation results

[2213] Specific operation: The server converts the recommendation results into JSON format and sends them to the terminal as an HTTP response.

[2214] Output: Recommendation results sent to the device

[2215] Step 7:

[2216] The device displays the recommendation results to the user.

[2217] Input: JSON data received from the server

[2218] Specific operation: The front end parses the received data and displays information such as movies "A", "B", and "C" in the user interface.

[2219] Output: Recommendation results displayed to the user

[2220] Step 8:

[2221] The server retrieves comments, interviews, and behind-the-scenes information from relevant directors and writers and stores them in a database.

[2222] Input: Additional information from external media or API

[2223] Specific operation: The server periodically obtains information using the API of the partner media and stores the obtained additional information in a database.

[2224] Output: Additional content stored in the database

[2225] Step 9:

[2226] The device will display this additional content on the details page of the recommended title.

[2227] Input: Additional content data obtained from the server

[2228] What happens: The front-end renders the additional content information on the detail page and displays it to the user.

[2229] Output: Additional content displayed on the details page

[2230] Step 10:

[2231] A user wants access to premium content and signs up for a monthly subscription.

[2232] Input: Premium content request and payment information

[2233] What it does: The user enters payment information and presses a button to start a monthly subscription.

[2234] Output: Subscription registration request

[2235] Step 11:

[2236] The terminal transmits the payment information to the server, which processes the payment.

[2237] Input: User's payment information

[2238] What it does: The terminal securely encodes the payment information and sends an HTTPS request to the server, which then processes the payment using the Stripe or PayPal API.

[2239] Output: Payment processing result

[2240] Step 12:

[2241] The server receives the payment transaction result and updates the user's subscription status.

[2242] Input: Payment processing result data

[2243] Specific behavior: The server receives the payment success response and updates the user's subscription status in the database to "active."

[2244] Output: Updated subscription status

[2245] Step 13:

[2246] The device will display a successful subscription notification to the user.

[2247] Input: Subscription status update

[2248] What happens: The front end displays a "Subscription successful" notification to the user.

[2249] Output: Success notification displayed to the user

[2250] Step 14:

[2251] The server receives advertising information from advertisers and production companies.

[2252] Input: Advertising data from advertisers and production companies

[2253] Specific operation: Uses the API provided by the advertiser to obtain advertising materials and save them in a database.

[2254] Output: Ad data stored in a database

[2255] Step 15:

[2256] The server selects appropriate advertisements based on the user's profile data.

[2257] Input: User profile data

[2258] What it does: The server analyzes user data and uses targeting algorithms to select appropriate ads.

[2259] Output: Selected advertising data

[2260] Step 16:

[2261] The device displays appropriate advertisements in the user's interface.

[2262] Input: Selected advertising data

[2263] What happens: The front-end renders the ad data into the interface and displays it to the user.

[2264] Output: The ad shown to the user

[2265] The above is the specific processing flow of the program of this system.

[2266] (Application example 1)

[2267] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2268] Today's entertainment consumers face challenges in finding content that suits their tastes among a wide variety of options, often lacking additional information to maximize the appeal of a content, and face the problem of insufficient integration between targeting advertising and payment management systems based on user preferences, resulting in an inconsistent and optimized user experience.

[2269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2270] In this invention, the server includes means for acquiring personal profile data, means for training a generative AI, means for recommending optimal entertainment works to the user based on the profile data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for the user, means for targeting advertisements based on the user's profile data, means for providing a visually easy-to-understand user interface on a smartphone, and means for notifying the user when new recommendations are available. This improves the ease of discovering entertainment works and maximizes the appeal of the works by providing additional information. It also consistently optimizes the user experience and enables effective targeted advertising and payment management.

[2271] "Personal profile data" refers to a set of information that a user has about themselves, including their preferences, past browsing history, and behavioral patterns.

[2272] "Generative AI" refers to artificial intelligence systems that use machine learning algorithms to learn patterns from users' profile data and generate appropriate recommendations.

[2273] "Entertainment works" refers to movies, comics, television programs, music, and other media content that users view or consume.

[2274] "Recommendation" refers to the act or result of recommending the most suitable entertainment content based on a user's preferences.

[2275] "Additional Content" refers to supplemental information, such as commentary, interviews, and behind-the-scenes information, related to an entertainment production.

[2276] "Monthly Subscription" refers to a subscription format that allows users to access premium content or services in exchange for a recurring payment.

[2277] "Targeted advertising" refers to the practice of displaying the most relevant advertisements to individual users based on their profile data.

[2278] A "smartphone" refers to a portable information terminal that has the functionality of a mobile phone and can run a variety of applications.

[2279] "User interface" refers to the screen layout and operation methods used by users to interact with a system.

[2280] "Notification" refers to the act of the system informing the user that new information or recommendations are available.

[2281] This invention is a system that combines user profile data with a generative AI model to recommend customized entertainment works to users. It also provides additional content related to the recommended works, enriching the user's entertainment experience. Specific embodiments for implementing this invention are described below.

[2282] Profile Data Collection

[2283] Users access the system and enter information such as their preferences and past browsing history into a new registration form. For example, they provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input information to the server, which analyzes the received data and stores it in a database. For example, the user's basic information is stored in the users table, and their browsing history is stored in the viewing_history table.

[2284] Creating and training AI models

[2285] The server uses the user data in the database to train an AI model using machine learning algorithms (e.g., deep learning). This AI model is then used to recommend entertainment items based on the user's preferences. The trained AI model is then deployed to a recommender system, which quickly generates recommendation results upon request.

[2286] Providing recommendations

[2287] When a user logs in to the system and requests "new recommended titles," the device sends the request data along with the user ID to the server. The server uses an AI model to select titles that match the user's preferences and generates recommendation results. These results include titles, thumbnails, descriptions, etc., which the device displays to the user. The system also has a function to notify the user when new recommendations are available.

[2288] Providing additional content

[2289] The server periodically retrieves comments, interviews, and behind-the-scenes information from related directors and writers and stores them in a database. The device displays this additional content on the details page of the recommended film. For example, the device can provide the user with comments and interviews from the director of film "A."

[2290] Managing your monthly subscription

[2291] If a user wants access to premium content, they sign up for a monthly subscription. Payment information is sent from the device to the server, which processes the payment. Based on the transaction result, the user's subscription status is updated in the database.

[2292] Advertising and Event Management

[2293] The server receives advertising information from advertisers and production companies and selects appropriate ads based on user profile data, allowing it to provide the most relevant ads to each individual user.

[2294] Examples and prompts

[2295] If a user says "I like horror movies" and enters "Movies I've recently seen are A, B, and C":

[2296] Register with user ID 123

[2297] Submit a recommendation request

[2298] AI recommends "latest horror movies D, E, F"

[2299] Also displays additional information including director comments and interviews

[2300] Example prompt sentence:

[2301] Input: User likes horror movies and requests new movie recommendations based on recently watched movies A, B, and C.

[2302] Output: A list of the latest horror movies D, E, F with additional information about them (director comments, interviews, etc.).

[2303] Using this system, users can be provided with the most suitable entertainment content, enriching their entertainment experience.

[2304] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2305] Step 1:

[2306] A user accesses the system and enters information such as their preferences and past viewing history into a new registration form. Input content includes "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." The device sends this input data to the server in JSON format. As data input, the user provides their preferred entertainment genre and past viewing history information, and as output, the data is transferred to the server in JSON format.

[2307] Step 2:

[2308] The server parses the received user profile data and stores basic information in the users table and browsing history in the viewing_history table in the database. The server receives the JSON data, parses its contents, and executes queries to store them in the appropriate tables. The input to this step is the user's JSON data, and the output is the creation of a record in the database.

[2309] Step 3:

[2310] The server extracts user profile data from the database and uses a generative AI model to train a recommendation model. A machine learning algorithm (e.g., deep learning) is used to learn patterns based on the profile data. The trained model results undergo accuracy evaluation and parameter adjustment before finally being deployed. The input is user data from the database, and the output is the trained AI model.

[2311] Step 4:

[2312] A user logs in to the system and requests new recommendations. The device sends the user ID and request data to the server. The input for this step is the user's request information, and the request content is sent to the server.

[2313] Step 5:

[2314] The server uses a trained AI model to recommend entertainment works that match the user's preferences. If the user likes "horror movies," it will select several of the latest horror movies. Specifically, the AI ​​model receives the user's profile data as input, generates a list of entertainment works, and returns it to the device in JSON format. The recommendation results are output from the server.

[2315] Step 6:

[2316] The device receives the recommendation results from the server and displays them to the user as a visually easy-to-understand user interface, showing the title, thumbnail, description, etc. of the recommended works. The input to this step is JSON data from the server, and the output is a visually structured display.

[2317] Step 7:

[2318] The server periodically retrieves comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database. Additional information is obtained from partner media and APIs and added to the database. The input to this step is external information data, and storing it in the database is the output.

[2319] Step 8:

[2320] The device displays additional content such as comments and interviews from the director and writer on the details page of the recommended work. Providing comments and interviews from the director of movie "A" provides the user with a deeper entertainment experience. The input of this step is additional information from the database, and the display on the details page is the output.

[2321] Step 9:

[2322] A user wants access to premium content and signs up for a monthly subscription from their device. Payment information is entered and sent from the device to the server. The input to this step is the user's payment information, and the output is the data sent to the server.

[2323] Step 10:

[2324] The server processes the received payment information and updates the user's subscription status in the database. For example, it updates the user's status in the database to "active". The input to this step is the payment information and the output is the status update in the database.

[2325] Step 11:

[2326] The server selects appropriate targeted advertisements based on the user's profile data. The server extracts the user's interests from the profile data stored on the server and selects targeted advertisements based on them. The input for this step is the profile data, and the selected advertisement information is the output.

[2327] Step 12:

[2328] The device displays appropriate advertisements on the user's interface. Targeted advertisements are visually displayed on the dashboard or product detail page. The input of this step is the advertisement information from the server, and the display on the device is the output.

[2329] These processing steps improve entertainment discovery, maximize the appeal of entertainment content by providing additional information, and consistently optimize the user experience, enabling effective targeted advertising and payment management.

[2330] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2331] The present invention is a system that combines personal profile data with generative AI and uses an emotion engine to recognize a user's emotions in real time, providing a customized entertainment experience. The system uses real-time emotion data in addition to the user's past viewing history and preferences to select the most suitable works. It also provides additional information, such as comments and interviews from directors and writers, allowing users to enjoy the works more deeply. Specific embodiments for implementing the present invention are described below.

[2332] User profile data collection

[2333] 1. A user accesses the system and fills in a new registration form with information about their preferences and past browsing history.

[2334] For example, you can provide information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C."

[2335] 2. The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[2336] 3. The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[2337] Combining Emotion Engines

[2338] 1. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice.

[2339] For example, it analyzes the user's facial expressions and tone of voice while they are watching a movie and recognizes emotions such as "surprise," "joy," and "fear."

[2340] 2. The device transmits the acquired emotion data to the server.

[2341] 3. The server integrates the received emotion data into the profile data and stores it in a database.

[2342] Creating and training AI models

[2343] 1. The server periodically queries and extracts all user and sentiment data stored in the database.

[2344] The emotion data and profile data are combined to generate a training dataset.

[2345] 2. The server runs a machine learning algorithm (e.g., deep learning) to train an AI model that includes the emotion data.

[2346] 3. The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[2347] 4. The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[2348] Providing recommendations

[2349] 1. A user logs in to the system and requests "new recommended works."

[2350] 2. The device sends the login user ID and recommendation request data to the server.

[2351] 3. The server uses an AI model to select the most suitable work based on the profile data and emotional data.

[2352] For example, based on past browsing history and current emotional data, the app will suggest "comedy movies" when the user is "relaxed," and "action movies" when the user is "stressed."

[2353] 4. The server constructs the recommendation results in JSON format and returns them to the device.

[2354] 5. The device displays the recommendation results on the user interface.

[2355] Providing additional content

[2356] 1. The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[2357] 2. Display this additional content to users on the details page of the title for which the device was recommended.

[2358] Managing your monthly subscription

[2359] 1. A user enters payment information to purchase a monthly subscription to access premium content.

[2360] 2. The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[2361] 3. The server processes the received payment information in cooperation with the payment gateway and receives the result.

[2362] 4. If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[2363] 5. The device displays a successful subscription notification to the user.

[2364] Advertising and Event Management

[2365] 1. The server receives advertising information from advertisers and production companies and stores it in a database.

[2366] 2. The server selects appropriate ads based on the user's profile data and emotional data.

[2367] For example, when a user is "excited," ads for related action movies might be shown, and when a user is "relaxed," ads for comedy movies might be shown.

[2368] 3. The device displays targeted ads in the user interface.

[2369] The above is a specific embodiment for implementing the present invention. As entertainment options become more diverse, this allows users to recommend the most suitable works and enjoy the entertainment experience more deeply. By combining it with an emotion engine, the degree of customization of the user experience can be further increased.

[2370] The processing flow will be explained below.

[2371] User profile data collection

[2372] Step 1:

[2373] A user accesses the system and enters information about their preferences and past browsing history into a new registration form.

[2374] Step 2:

[2375] The device constructs the user's input information as a JSON-formatted payload and sends it to the server.

[2376] Step 3:

[2377] The server parses the received user data and stores it in the appropriate database tables, such as the user_info table and the viewing_history table.

[2378] Combining Emotion Engines

[2379] Step 1:

[2380] Using the device's built-in camera and microphone, emotional data is collected in real time from the user's facial expressions and voice.

[2381] Step 2:

[2382] The device analyzes the emotional data it acquires and classifies emotions such as "joy," "surprise," and "sadness."

[2383] Step 3:

[2384] The device sends the analysis results to the server as a JSON format payload.

[2385] Step 4:

[2386] The server integrates the received emotion data into the profile data and stores it in a database.

[2387] Creating and training AI models

[2388] Step 1:

[2389] The server periodically queries and extracts all user and sentiment data stored in the database.

[2390] Step 2:

[2391] The server preprocesses the extracted data and generates a training dataset for the AI ​​model.

[2392] Step 3:

[2393] The server runs machine learning algorithms (e.g., deep learning) to train an AI model that includes emotion data.

[2394] Step 4:

[2395] The server evaluates the accuracy of the trained model and adjusts parameters or retrains it as needed.

[2396] Step 5:

[2397] The server deploys the trained AI model to the endpoint and incorporates it into the recommender system.

[2398] Providing recommendations

[2399] Step 1:

[2400] A user logs into the system and requests "new recommended works."

[2401] Step 2:

[2402] The device sends the login user ID and recommendation request data to the server.

[2403] Step 3:

[2404] The server uses an AI model to select the most suitable work based on profile data and emotional data.

[2405] Step 4:

[2406] The server constructs the selected recommendation results in JSON format and returns them to the terminal.

[2407] Step 5:

[2408] The device displays the recommendation results on the user interface.

[2409] Providing additional content

[2410] Step 1:

[2411] The server periodically collects comments, interviews, and behind-the-scenes information from directors and writers and stores them in a database.

[2412] Step 2:

[2413] The device will display this additional content to users on the details page of the recommended title.

[2414] Managing your monthly subscription

[2415] Step 1:

[2416] The user enters payment information to purchase a monthly subscription to access premium content.

[2417] Step 2:

[2418] The terminal constructs the user's payment information as a JSON-formatted payload and sends it to the server.

[2419] Step 3:

[2420] The server processes the received payment information in cooperation with the payment gateway and receives the result.

[2421] Step 4:

[2422] If the server successfully processes the payment, it updates the user's subscription status in the database to "active".

[2423] Step 5:

[2424] The device displays a successful subscription notification to the user.

[2425] Advertising and Event Management

[2426] Step 1:

[2427] The server receives advertising information from advertisers and production companies and stores it in a database.

[2428] Step 2:

[2429] The server selects appropriate advertisements based on the user's profile data and emotional data.

[2430] Step 3:

[2431] The device displays targeted advertisements in the user interface.

[2432] Example 2

[2433] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2434] In the modern entertainment industry, there is a demand for providing optimal content based on users' diverse preferences and emotions. However, conventional recommendation systems rely solely on user profile data and do not consider real-time emotional data, making it difficult to provide an appropriate entertainment experience for each individual user. Furthermore, there is a lack of systems that handle emotional data and profile data in an integrated manner, which has hindered efforts to improve user experience.

[2435] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[2436] In this invention, the server includes means for acquiring user profile data, means for acquiring and storing emotion data in real time, means for training a generative AI model based on the acquired profile data and emotion data, means for using the generative AI model to recommend optimal entertainment works based on the profile data and emotion data, means for providing additional content related to the recommended works, means for managing monthly subscriptions for users, means for targeting advertisements based on the profile data and emotion data, and means for processing payment, thereby enabling the provision of a highly personalized entertainment experience based on the user's emotions and preferences.

[2437] "User profile data" refers to data about a user, such as personal information, preferences, and past browsing history.

[2438] "Emotional data" refers to data on the user's emotional state obtained in real time from their facial expressions and voice.

[2439] "Generative AI model" refers to an artificial intelligence model trained using machine learning algorithms based on user profile data and sentiment data.

[2440] "Entertainment content" refers to content provided based on users' hobbies and interests, such as movies, TV shows, books, music, and games.

[2441] "Additional content" refers to comments from directors and writers, interviews, behind-the-scenes information, etc. related to the recommended works.

[2442] "Monthly subscription" refers to a fee system where users pay a monthly fee to access premium content.

[2443] "Targeting ads" refers to the act of selecting and displaying the most appropriate ads to users based on their profile data and emotional data.

[2444] "Payment Processing" refers to the functionality that processes information and finalizes payments for users to make monthly subscription or other payments.

[2445] This invention is a system that combines personal profile data and emotional data to provide users with a customized entertainment experience. The system uses the user's past viewing history, preferences, and real-time emotional data to select the most suitable content and provide appropriate additional content and advertisements. An embodiment of this system is described below.

[2446] First, the user accesses the system and enters information about their preferences and past browsing history into the new registration form. Specifically, the user provides information such as "I like horror movies," "I often read suspense manga," and "Movies I've seen in the past: A, B, C." This sends the user's profile data from the device to the server as a JSON-formatted payload. The server analyzes the received data and stores it in a database.

[2447] Next, the user's emotional data is collected. Using the device's built-in camera and microphone, emotional data is acquired in real time from the user's facial expressions and voice. For example, while the user is watching a movie, the device's camera captures a photo of the user's face and uses an expression analysis algorithm to recognize emotions such as "surprise," "happiness," and "fear." The acquired emotional data is sent to a server and stored in a database along with the user's profile data.

[2448] The server periodically queries and extracts all user and sentiment data from the database to generate a training dataset. This is used to run a machine learning algorithm, such as deep learning, to train a generative AI model. The accuracy of the trained model is evaluated, and parameters are adjusted or retrained as needed. The trained AI model is then deployed to an endpoint and incorporated into the recommender system.

[2449] When a user logs in and requests "new recommended movies," the device sends the logged-in user ID and recommendation request data to the server. The server uses an AI model to select the most suitable movie based on the user's profile and emotional data. For example, if the user is relaxed, it will suggest a "comedy movie," and if they are nervous, it will suggest an "action movie." The recommendation results are returned to the device in JSON format and displayed in the user interface.

[2450] Additionally, the server periodically collects and stores in its database comments, interviews, and behind-the-scenes information from directors and writers. This additional content is then displayed to users on the detail page of the recommended film.

[2451] When a user purchases a monthly subscription to access premium content, the device sends the user's payment information as a JSON-formatted payload to the server. The server processes the received payment information in conjunction with the payment gateway and receives the result. If the payment process is successful, the user's subscription status is updated in the database and set to "active." A success notification is displayed to the user on the device.

[2452] Finally, the server receives advertising information from advertisers and production companies and stores it in a database. Based on the user's profile data and emotional data, it selects appropriate advertisements. For example, if the user is excited, it will display advertisements for action movies, and if the user is relaxed, it will display advertisements for comedy movies. These advertisements are then displayed on the device's user interface.

[2453] Prompt Sentence Examples

[2454] "Suggest recommended works to users who are relaxing"

[2455] "How can we select the best entertainment based on user emotional data?"

[2456] In this way, the system of the present invention is able to provide a highly personalized entertainment experience based on the user's emotions and preferences.

[2457] The flow of the identification process in the second embodiment will be ...

Claims

1. a means for obtaining personal profile data; A means to train the generative AI; A means of recommending the most suitable entertainment content to users based on their profile data; and a means for providing additional content related to the recommended works; A way to manage monthly subscriptions for users, and A means of targeting advertisements based on user profile data; and A system including:

2. 10. The system of claim 1, which provides additional content including commentary and interviews from directors and writers.

3. 10. The system of claim 1, wherein the AI ​​model is continuously updated based on the user's viewing history and preferences.

Images