System

Abstract

A system is provided.SOLUTION: A system comprising: devices for a user to input preferences and past browsing history; a database for storing profile information of the user; generative AI model means for selecting a work based on the profile information; display means for presenting the selected work to the user; means for collecting and presenting detailed information about the work; and means for generating hybrid recommendations that combine different genres and styles.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] Today, entertainment options are vast, making it time-consuming and laborious for users to find the perfect content. Furthermore, their busy lives can make it stressful for them to be unable to efficiently select content. Under these circumstances, users need assistance in finding content they truly enjoy. Furthermore, users have limited access to detailed information behind the content, making it difficult for them to deepen their understanding and attachment to it. To address these challenges, the present invention aims to provide an entertainment recommendation system that uses generative AI technology based on user profile data. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means. A device is provided for users to input their preferences and past browsing history, and user profile information is stored in a database. Based on this profile information, a generative AI model means selects the most suitable works for the user. It also includes a display means for presenting the selected works to the user. Additionally, a means for collecting and presenting detailed information related to the selected works allows users to deepen their understanding of the works. Furthermore, a system is realized that includes a means for generating hybrid recommendations that combine different genres and styles, providing users with a fresh entertainment experience. This allows users to easily find the best works that suit their preferences and deepen their attachment to the works by accessing detailed information.

[0006] "User" refers to an individual who uses the System to receive entertainment recommendations.

[0007] "Profile information" is a collection of information based on a user's preferences and past browsing history, and is data used to recommend works that are best suited to the user.

[0008] "Database" refers to a system for storing and managing digital data such as profile information.

[0009] "Generative AI model" refers to an artificial intelligence algorithm that selects relevant works based on a user's profile information.

[0010] "Display means" refers to a device for visually presenting selected works and related information to a user.

[0011] "Detailed information" refers to comments from directors and writers related to the work, interviews, behind-the-scenes information, etc., which allows users to deepen their understanding of the work.

[0012] "Hybrid recommendations" refers to the recommendation of new entertainment works that are generated by combining different genres and styles. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. The embodiments of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[0035] 1. Collecting user profiles

[0036] 1.1 Entering information when logging in for the first time

[0037] User: When logging into the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, if they like the "action" and "comedy" genres and have a preference for specific writers and directors, they enter that information.

[0038] On your device: The information you enter is temporarily stored and then sent to a server. The data is encrypted to protect your privacy.

[0039] 2. Saving User Profile Information

[0040] 2.1 Saving Profile Data

[0041] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[0042] 3. Generating Recommendations

[0043] 3.1 Recommendation Algorithm Implementation

[0044] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[0045] 3.2 Presentation of recommendation results

[0046] Server: Sends the generated recommendation results to the device.

[0047] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[0048] 4. Providing additional information

[0049] 4.1 Requesting and Providing More Information

[0050] User: Select the title of interest from the displayed recommendations and request more information.

[0051] Terminal: Sends the request to the server.

[0052] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[0053] Terminal: Visually displays the received details to the user.

[0054] 5. Generating Hybrid Recommendations

[0055] 5.1 Implementing the Hybrid Recommendation Algorithm

[0056] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits.

[0057] 5.2 Presenting a new proposal

[0058] Server: Sends the generated hybrid recommendation results to the device.

[0059] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[0060] Specific examples

[0061] Here are some concrete examples:

[0062] 1. User: This is the first time they visit the system and they state that they like action and comedy and have watched a lot of "Marvel movies."

[0063] 2. Terminal: Sends input information to the server.

[0064] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[0065] 4. Device: Display the recommendation results to the user.

[0066] 5. User: Requests more information about "Action X" that interests them.

[0067] 6. Terminal: Sends the request to the server.

[0068] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[0069] 8. Terminal: Display detailed information to the user.

[0070] 9. Server: Generates a hybrid recommendation of the new movie "Action Laughter" that combines different genres based on the user profile and sends it to the device.

[0071] 10. Terminal: Display the hybrid recommendation results to the user.

[0072] This allows users to find the entertainment that best suits their tastes, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[0073] The processing flow will be explained below.

[0074] I understand. The process steps are explained in detail below.

[0075] Collecting user profiles

[0076] Step 1:

[0077] User: Enter their preferences and past viewing history into a questionnaire-style input screen. For example, they may enter that they like movies in the "action" and "comedy" genres and that they have watched many "Marvel movies."

[0078] Step 2:

[0079] On the device: Temporarily store the information entered by the user locally and display a confirmation screen for the entered information.

[0080] Step 3:

[0081] Terminal: After the user confirms and corrects the input, the data is sent to the server. At this time, the data is encrypted before being transferred.

[0082] Storing user profile information

[0083] Step 4:

[0084] Server: Receives profile information sent from the device.

[0085] Step 5:

[0086] Server: The received profile information is stored in a database and managed in association with the user ID.

[0087] Generating recommendations

[0088] Step 6:

[0089] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[0090] Step 7:

[0091] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[0092] Step 8:

[0093] Server: Generates a list of selected works and sends it to the device.

[0094] Step 9:

[0095] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[0096] Providing additional information

[0097] Step 10:

[0098] User: Click on a recommendation that interests them and request more information.

[0099] Step 11:

[0100] Terminal: Sends the request to the server.

[0101] Step 12:

[0102] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[0103] Step 13:

[0104] Server: Sends the collected details to the device.

[0105] Step 14:

[0106] Terminal: Displays the received details to the user.

[0107] Generating Hybrid Recommendations

[0108] Step 15:

[0109] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[0110] Step 16:

[0111] Server: Sends the generated hybrid recommendation results to the device.

[0112] Step 17:

[0113] Terminal: Displays the received hybrid recommendation results to the user.

[0114] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, and generating hybrid recommendations, allowing users to efficiently and effectively find the entertainment content that best suits them, and deepening their understanding and attachment to the content through detailed information.

[0115] Example 1

[0116] 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."

[0117] Conventional entertainment recommendation systems only suggest a limited number of works based on a user's preferences and past viewing history, limiting the opportunities for users to be exposed to new genres and styles. Furthermore, there was a lack of a way for users to quickly obtain detailed information about works. This made it difficult for users to find entertainment works that matched their preferences, and to deepen their understanding and attachment to works.

[0118] 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.

[0119] In this invention, the server includes a terminal means for users to input their preferences and past browsing history, a server means for storing the user's profile information, and a generative AI model means for selecting entertainment works based on the profile information. This enables users to quickly find the entertainment works that best suit their preferences, and provides detailed work information and opportunities to experience new genres and styles.

[0120] "Terminal means" refers to a device through which a user inputs preferences and past browsing history.

[0121] "Server means" refers to a device or system for storing said user profile information.

[0122] "Generative AI model means" refers to an artificial intelligence model for selecting entertainment works based on the profile information.

[0123] "Display means" refers to a device or interface for presenting selected entertainment pieces to a user.

[0124] "Detailed information gathering means" refers to a device or system for gathering and presenting detailed information about said entertainment work.

[0125] "Means for generating hybrid recommendations" refers to a device or system for generating recommendations that combine different genres or styles.

[0126] The system of the present invention provides entertainment recommendations based on user input of preferences and past browsing history, and includes a terminal means, a server means, a generating AI model means, a display means, a detailed information collection means, and a means for generating hybrid recommendations.

[0127] 1. Collecting user profiles

[0128] 1.1 Entering information when logging in for the first time

[0129] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, say they like "action" and "comedy" and have watched many "Marvel movies." They enter this information and provide it to the system.

[0130] Terminal: The information entered by the user is temporarily stored in the terminal's memory. The stored information is then encrypted and sent to the server. This encryption process uses standard encryption techniques (e.g., AES-256).

[0131] 2. Saving User Profile Information

[0132] Server: Stores information received from the device about the user's preferences and past browsing history in a database. The information is managed by linking it to the user ID and used in subsequent processing. A general relational database (e.g., MySQL or PostgreSQL) can be used as the database.

[0133] 3. Generating Recommendations

[0134] Server: Launches the generative AI model based on the saved user profile. Prompts include the user's preferences, past browsing history, and the latest trending information. The AI ​​model uses this information to select the most suitable entertainment title. For example, for a user who likes "action" and "comedy," the AI ​​model might recommend "Action X."

[0135] Examples of prompts:

[0136] User Profile Data:

[0137] Favorite genres: Action, comedy

[0138] Viewing history: Many Marvel movies

[0139] Generate recommendations based on algorithms, taking into account the latest trends.

[0140] Server: Sends the generated recommendation results to the device.

[0141] On the device: The received recommendation results are displayed to the user in list and grid format, with thumbnail images and brief descriptions.

[0142] 4. Providing additional information

[0143] User: Selects an item from the recommendations that interests them and requests more information about it.

[0144] Terminal: Sends requests to the server.

[0145] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[0146] Terminal: Visually displays the received details to the user.

[0147] 5. Generating Hybrid Recommendations

[0148] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy."

[0149] Server: Sends the generated hybrid recommendation results to the device.

[0150] Device: The received hybrid recommendation results are displayed to the user, allowing them to discover new genres and styles.

[0151] This allows users to quickly find the entertainment works that best suit their preferences, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1:

[0154] When a user logs in for the first time, they enter their preferences and past browsing history through the application or web interface. Specifically, the user enters that they like "action" and "comedy" and have watched many "Marvel movies." The entered data is temporarily stored on the device as the user's profile information.

[0155] Step 2:

[0156] The device encrypts the stored user profile information and sends it to the server. This encryption process uses, for example, AES-256. The server decodes the received information and stores it in a database along with the user ID. The input data is the user's preferences and past browsing history, and the output data is the user profile information stored in the database.

[0157] Step 3:

[0158] The server launches a generative AI model based on the stored user profile information. The AI ​​model runs an algorithm to recommend the most suitable entertainment titles, taking into account the user's preferences, past browsing history, and the latest trend information. The input data is the user profile information and the latest trend information, and the output data is the recommendation results. An example of a prompt is as follows:

[0159] User Profile Data:

[0160] Favorite genres: Action, comedy

[0161] Viewing history: Many Marvel movies

[0162] Generate recommendations based on algorithms, taking into account the latest trends.

[0163] Step 4:

[0164] The server sends the generated recommendation results to the terminal. The input data is the recommendation results, and the output data is the data sent to the terminal.

[0165] Step 5:

[0166] The terminal visually displays the received recommendation results to the user in a list or grid format, including thumbnail images and brief descriptions. The input data are the recommendation results received from the server, and the output data are the recommendation results displayed to the user.

[0167] Step 6:

[0168] The user selects an item of interest from the displayed recommendation results and requests detailed information about it. The input data is the item selected by the user, and the output data is a request for detailed information.

[0169] Step 7:

[0170] The terminal sends the user's request to the server, where the input data is the user's request and the output data is the request sent to the server.

[0171] Step 8:

[0172] In response to the request, the server collects detailed information related to the specified work and sends it to the terminal. The collected detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The input data is the work information related to the user's request, and the output data is the detailed information sent to the terminal.

[0173] Step 9:

[0174] The terminal visually displays the received detailed information to the user, with the input data being the detailed information received from the server and the output data being the detailed information displayed to the user.

[0175] Step 10:

[0176] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy." The input data is the user profile and viewing habits, and the output data is the hybrid recommendation results.

[0177] Step 11:

[0178] The server sends the generated hybrid recommendation result to the terminal, where the input data is the hybrid recommendation result and the output data is the data sent to the terminal.

[0179] Step 12:

[0180] The terminal displays the received hybrid recommendation results to the user, allowing the user to experience new genres and styles. The input data is the hybrid recommendation results received from the server, and the output data is the results displayed to the user.

[0181] (Application example 1)

[0182] 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."

[0183] Conventional content distribution services lack personalized recommendation systems based on user preferences and past browsing history, making it difficult for users to efficiently find the content they really want to watch. Furthermore, they lack innovative recommendations that combine different genres and the ability to provide detailed background information, limiting the user experience.

[0184] 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.

[0185] In this invention, the server includes a device for users to input their preferences and past browsing history, a database that stores the user's profile information, a generative AI model means that selects works based on the profile information, a display means that presents the selected works to the user, a means that collects and presents detailed information about the works, a means that generates hybrid recommendations that combine different genres and styles, and a content distribution service application means that is installed on the smartphone. This enables highly accurate recommendations based on the user's preferences and past browsing history, as well as new proposals that combine detailed work information and different genres.

[0186] The "device for a user to input preferences and past viewing history" is a terminal for a user to input his or her own viewing preferences and a history of content that has been viewed in the past.

[0187] The "database that stores the user's profile information" is a database system that organizes and stores the viewing preferences and past history information entered by the user.

[0188] The "generative AI model means for selecting works based on the profile information" refers to an artificial intelligence model that uses the saved user profile information to select the most suitable content.

[0189] "Display means for presenting selected works to a user" means a device or screen for visually displaying to a user the content selected by the generative AI model.

[0190] The "means for collecting and presenting detailed information about the work" is a function for collecting detailed information about the content that the user wishes to view, such as background information, comments and interviews from the creator, and displaying this information to the user.

[0191] "Means for generating hybrid recommendations that combine different genres and styles" is a mechanism for generating novel content recommendations that combine different genres and styles based on user profile information.

[0192] The "content distribution service application means installed on a smartphone" is an application that runs on a smartphone and distributes and recommends content to users.

[0193] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Hereinafter, specific embodiments of the present invention will be described.

[0194] 1. Collecting user profiles

[0195] 1.1 Entering information when logging in for the first time

[0196] When users log in to the system for the first time, they must enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. They can enter their preferred genres, specific authors, or production companies. For example, a user might enter that they like "action" and "comedy," and that they particularly prefer works from "popular series."

[0197] 1.2 Data storage

[0198] The device temporarily stores the information entered by the user and then transmits it to the server. The transmitted data is encrypted and appropriate security measures are used to protect the user's privacy. The server stores the received data in a database and manages it by linking it to the user ID.

[0199] 2. Generating Recommendations

[0200] 2.1 Organization and analysis

[0201] The server uses the stored user profile information to generate appropriate content recommendations using a generative AI model that considers the user's preferences, past browsing history, and the latest trends to select the most suitable entertainment content. The AI ​​model used includes popular deep learning frameworks such as TensorFlow and PyTorch.

[0202] 2.2 Presenting Recommendations

[0203] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions.

[0204] 3. Providing additional information

[0205] 3.1 Requesting and Providing More Information

[0206] The user selects a work of interest from the displayed recommendation results and requests detailed information. The device then sends this request to the server. The server collects relevant detailed information and sends it to the device. The detailed information may include director's comments, interviews with the writers, behind-the-scenes information, etc. The device then visually displays this information to the user.

[0207] 4. Generating Hybrid Recommendations

[0208] 4.1 Hybridization

[0209] The server generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data, again using generative AI models.

[0210] 4.2 Presenting a new proposal

[0211] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from conventional ones.

[0212] Specific examples

[0213] A user accesses the system for the first time and enters that they like the "action" and "comedy" genres and have watched many "popular series." The device sends this information to the server, which stores it in a database. The system then uses a generative AI model to recommend "new action movies" and sends them to the device. When the user requests more information about a "new action movie" that interests them, the system provides detailed information, including director comments and interviews. The server also generates hybrid recommendations for new "action comedies" that combine different genres based on the user profile and sends them to the device. This allows users to discover new genres and styles.

[0214] Example prompt sentence:

[0215] "Using the profile information of user ID: '12345', please generate the best entertainment recommendations based on the following criteria: Favorite genres - 'action', 'comedy', viewing history - 'popular series'. Also, please provide hybrid recommendations that combine different genres."

[0216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0217] Step 1:

[0218] When a user logs in to the system for the first time, they enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. For example, the user may enter that they prefer "action" and "comedy" genres and that they like works from a particular production company. The input data is temporarily stored on the device.

[0219] Step 2:

[0220] The device encrypts the preferences and browsing history data entered by the user and sends it to the server. The server receives this data and stores it in a database. At this time, the information is managed consistently by associating it with the user ID as a key.

[0221] Step 3:

[0222] The server reads the user profile information stored in the database and generates content recommendations using a generative AI model. The user's profile information is provided as input to the AI ​​model, and suitable entertainment candidates are obtained as output. The generative AI model used includes deep learning frameworks such as TensorFlow and PyTorch. The model takes into account the user's preferences, past browsing history, and the latest trending information.

[0223] Step 4:

[0224] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions of each work.

[0225] Step 5:

[0226] The user selects an interesting work from the displayed recommendation results and requests its detailed information. The device sends this request to the server, providing the work ID as input and obtaining the related detailed information as output.

[0227] Step 6:

[0228] The server collects detailed information related to the specified work from external APIs and databases and sends it to the device. The detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The device visually displays this information to the user.

[0229] Step 7:

[0230] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. The generative AI model is used again, providing the user's profile information and past viewing data as input and obtaining works in new genres and styles as output.

[0231] Step 8:

[0232] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from the conventional ones. The user can further enhance their viewing experience by selecting content to watch from the new candidates and requesting more information again.

[0233] 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.

[0234] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[0235] 1. Collecting user profiles

[0236] 1.1 Entering information when logging in for the first time

[0237] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, they may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[0238] On your device: The information you enter is temporarily stored locally and then sent to a server. The data is encrypted to protect your privacy.

[0239] 2. Saving User Profile Information

[0240] 2.1 Saving Profile Data

[0241] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[0242] 3. Generating Recommendations

[0243] 3.1 Recommendation Algorithm Implementation

[0244] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[0245] 3.2 Presentation of recommendation results

[0246] Server: Sends the generated recommendation results to the device.

[0247] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[0248] 4. Providing additional information

[0249] 4.1 Requesting and Providing More Information

[0250] User: Select the title of interest from the displayed recommendations and request more information.

[0251] Terminal: Sends the request to the server.

[0252] Server: Retrieves detailed information related to a specified film from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[0253] Terminal: Visually displays the received details to the user.

[0254] 5. Generating Hybrid Recommendations

[0255] 5.1 Implementing the Hybrid Recommendation Algorithm

[0256] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data.

[0257] 5.2 Presenting a new proposal

[0258] Server: Sends the generated hybrid recommendation results to the device.

[0259] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[0260] 6. Leveraging Emotional Engines

[0261] 6.1 Initial setup and operation of the emotion engine

[0262] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects facial and voice data from the user through the camera and microphone.

[0263] Device: Analyzes collected facial and voice data in real time to identify the user's current emotions.

[0264] 6.2 Emotion Data Analysis and Storage

[0265] Server: Receives the emotion data sent from the device and stores it in a database along with the profile information, making it possible to understand the user's emotional tendencies over the long term.

[0266] 6.3 Adjusting Recommendations Based on Sentiment

[0267] Server: The generative AI model adjusts the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[0268] Specific examples

[0269] Here are some concrete examples:

[0270] 1. User: This is the first time the system is accessed and the user enters that they like action and comedy and have watched many Marvel movies. They also authorize the use of the emotion engine.

[0271] 2. Terminal: Sends input information and emotion engine settings to the server.

[0272] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[0273] 4. Device: Display the recommendation results to the user.

[0274] 5. User: Requests more information about "Action X" that interests them.

[0275] 6. Terminal: Sends the request to the server.

[0276] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[0277] 8. Terminal: Display detailed information to the user.

[0278] 9. Server: Based on the user profile and emotion data, generate a hybrid recommendation for a new movie, "Action Laughter," which combines different genres, and send it to the device.

[0279] 10. Terminal: Display the hybrid recommendation results to the user.

[0280] 11. Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[0281] 12. Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that is relaxing.

[0282] 13. Terminal: Displays the recommendations generated in real time to the user.

[0283] This allows users to find the entertainment content that best suits their preferences, deepening their understanding and attachment to the content through detailed information.In addition, the emotion engine provides personalized recommendations that reflect the user's emotional state, enabling a more fulfilling entertainment experience.

[0284] The processing flow will be explained below.

[0285] Collecting user profiles

[0286] Step 1:

[0287] User: When accessing the system for the first time, the user logs in. After that, the user enters their preferred genre (e.g., action, comedy), favorite writers and directors, and a list of works they have watched. The user also authorizes the use of the emotion engine.

[0288] Step 2:

[0289] Terminal: The entered information is temporarily stored locally and a confirmation screen is displayed, where the user can confirm and correct the entered information.

[0290] Step 3:

[0291] Terminal: The input information is sent to the server. The transmitted data is encrypted to protect privacy.

[0292] Storing user profile information

[0293] Step 4:

[0294] Server: Stores the profile information received from the device in a database. Manages the information by linking it to the user ID.

[0295] Generating recommendations

[0296] Step 5:

[0297] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[0298] Step 6:

[0299] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[0300] Step 7:

[0301] Server: Generates a list of selected works and sends it to the device.

[0302] Step 8:

[0303] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[0304] Providing additional information

[0305] Step 9:

[0306] User: Click on a recommendation that interests them and request more information.

[0307] Step 10:

[0308] Terminal: Sends the request to the server.

[0309] Step 11:

[0310] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[0311] Step 12:

[0312] Server: Sends the collected details to the device.

[0313] Step 13:

[0314] Terminal: Displays the received details to the user.

[0315] Generating Hybrid Recommendations

[0316] Step 14:

[0317] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[0318] Step 15:

[0319] Server: Sends the generated hybrid recommendation results to the device.

[0320] Step 16:

[0321] Terminal: Displays the received hybrid recommendation results to the user.

[0322] Utilizing the Emotion Engine

[0323] Step 17:

[0324] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice data in real time via the camera and microphone.

[0325] Step 18:

[0326] Device: Analyzes facial and voice data collected by the emotion engine to identify the user's current emotion. For example, if the user is smiling, it is determined to be "joy."

[0327] Step 19:

[0328] Device: Sends analyzed emotion data to the server.

[0329] Step 20:

[0330] Server: The received emotional data is stored in a database along with the user's profile information, allowing for a long-term understanding of the user's emotional tendencies.

[0331] Step 21:

[0332] Server: The generative AI model adjusts the recommendation results based on real-time emotional data. For example, if the user is feeling stressed, it will prioritize relaxing works.

[0333] Step 22:

[0334] Server: Sends the adjusted recommendation results to the device.

[0335] Step 23:

[0336] Device: Displays real-time generated recommendations to the user.

[0337] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, utilizing the emotion engine, and adjusting the recommendations in real time, allowing users to efficiently and effectively find the entertainment content that best suits them, deepen their understanding and attachment to the content through detailed information, and enjoy a personalized entertainment experience through the emotion engine.

[0338] Example 2

[0339] 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."

[0340] Conventional entertainment recommendation systems often make recommendations based on simple user preferences and past viewing history, and lack the ability to present personalized content that reflects the user's emotions and momentary mood. Furthermore, they are limited in their ability to suggest new content that combines different genres and styles, making it difficult for users to discover new content without becoming bored.

[0341] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input device for a user to input preferences and past browsing history, data storage means for saving the user's profile information, generation AI means for selecting works based on the profile information, a display device for presenting the selected works to the user, information provision means for collecting and presenting detailed information about the works, means for generating hybrid recommendations that combine different genres and styles, and emotion engine means for recognizing the user's emotions and adjusting the recommendations. This allows the user to receive personalized recommendations for entertainment works that reflect their own emotional state and also enables them to discover works in new genres and styles.

[0342] An "input device" is a device that allows a user to input their preferences and past browsing history into the system.

[0343] "Data Storage Means" means a storage device or storage means for storing user profile information.

[0344] The "generative AI means" refers to an artificial intelligence algorithm and its execution environment for selecting the most suitable entertainment works based on the user's profile information.

[0345] A "display device" is a device for visually presenting selected entertainment content to a user.

[0346] "Information providing means" refers to means for collecting detailed information about entertainment works and presenting it to users.

[0347] A "means for generating hybrid recommendations" is an algorithm and its execution environment for generating entertainment works that combine different genres and styles.

[0348] "Emotion engine means" refers to techniques and devices for recognizing a user's emotions and tailoring entertainment recommendations based thereon.

[0349] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[0350] Collecting user profiles

[0351] Entering information when logging in for the first time

[0352] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. For example, the user may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[0353] Terminal: The terminal temporarily stores the entered information locally, encrypts it (using AES, etc.), and sends it to the server.

[0354] Storing user profile information

[0355] Server: The server receives information about the user's preferences and browsing history from the device and stores it in a database (e.g., MySQL or PostgreSQL). The information is linked to the user ID and used for subsequent recommendation processing.

[0356] Generating recommendations

[0357] Running the recommendation algorithm

[0358] Server: The server runs a generative AI model (e.g., TensorFlow or PyTorch) based on the user profile stored in the database. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past viewing history, and the latest trend information. Specifically, it rates genres that users have watched most frequently and uses this to rank similar content.

[0359] Presenting recommendation results

[0360] Server: The server sends the generated recommendation results to the device. HTTPS is used for communication.

[0361] Device: The device displays the received recommendation results to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[0362] Providing additional information

[0363] Requesting and Providing More Information

[0364] User: The user selects the work of interest from the displayed recommendations and requests more information.

[0365] Terminal: The terminal sends the user's request to the server.

[0366] Server: The server retrieves details related to the specified film from a database or external sources (e.g., IMDb API), including director's comments, interviews, and behind-the-scenes information about the film.

[0367] Terminal: The terminal visually displays the received details to the user.

[0368] Generating Hybrid Recommendations

[0369] Running a hybrid recommendation algorithm

[0370] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data, using the COLAB (Collaborative Filtering) algorithm and Content-Based Filtering algorithm.

[0371] Presenting a new proposal

[0372] Server: The server sends the generated hybrid recommendation results to the terminal.

[0373] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover works in new genres and styles that they have never seen before.

[0374] Utilizing the Emotion Engine

[0375] Initial settings and operation of the emotion engine

[0376] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[0377] Device: The device analyzes the collected facial and voice data to determine the user's current emotion using technologies such as OpenCV and Google Cloud Speech-to-Text.

[0378] Emotion data analysis and storage

[0379] Server: The server receives the emotion data sent from the device and stores it in a database, which makes it possible to understand the user's emotional tendencies over the long term.

[0380] Tailoring recommendations based on sentiment

[0381] Server: The server uses a generative AI model to adjust the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[0382] Specific examples

[0383] User: This is the first time they access the system and they state that they like action and comedy and have watched a lot of Marvel movies. They also allow the use of the emotion engine.

[0384] Device: Sends input information and emotion engine settings to the server.

[0385] Server: Stores user profiles and uses generative AI models to create optimal recommendations, such as selecting "Action X" and sending them to the device.

[0386] Device: Display the recommendation results to the user.

[0387] User: Requests more information about "Action X" that interests them.

[0388] Terminal: Sends the request to the server.

[0389] Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[0390] Terminal: Display detailed information to the user.

[0391] Server: Based on the user profile and emotional data, generate a hybrid recommendation for the new movie "Action Laughter," which combines different genres, and send it to the device.

[0392] Device: Display hybrid recommendation results to the user.

[0393] Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[0394] Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that will help you relax.

[0395] Device: Displays real-time generated recommendations to the user.

[0396] Examples of prompt statements

[0397] 1. "Generate recommendations for users who like action movies."

[0398] 2. "Use the emotion engine to recommend relaxing movies to users who are feeling stressed."

[0399] 3. "Suggest a new genre of film that combines action and comedy."

[0400] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0401] Step 1: Collecting user profiles

[0402] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. Specifically, they enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies." The input is done through a form, in the form of text and multiple choice.

[0403] Terminal: The terminal temporarily stores the information entered by the user in local storage. The input data is structured in JSON format and then transferred to the server using AES encryption technology. Based on the input, the initial user profile data JSON is generated.

[0404] Step 2: Save user profile information

[0405] Server: The server receives the encrypted user profile data from the device. It decrypts the data and stores it in a database using a database management system (e.g., MySQL or PostgreSQL). During the storage process, it associates the information with the user ID and stores it, converting it from JSON to SQL format.

[0406] Step 3: Run the recommendation algorithm

[0407] Server: The server runs a generative AI model based on the user profile data stored in the database. The AI ​​model uses machine learning frameworks such as TensorFlow and PyTorch to select the most suitable entertainment content, taking into account the user's preferences, past viewing history, and the latest trend information. The input data is the user profile and viewing history data, and the output data is a recommendation list.

[0408] Step 4: Presenting the Recommendation Results

[0409] Server: The server sends the generated recommendation results to the device using the HTTPS protocol, and the recommendation data is structured in JSON format.

[0410] Device: The device interprets the received recommendations and displays them to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[0411] Step 5: Request and provide more information

[0412] User: The user selects an item they are interested in from the displayed recommendations and requests more information. For example, the user may request details about "Action X."

[0413] Terminal: The terminal sends the user's request to the server, which is structured in JSON and sent to the server using HTTPS.

[0414] Server: The server retrieves details related to the specified movie from a database or external source (e.g., IMDb API). These details may include director's comments, interviews, and behind-the-scenes information. The retrieved data is converted into JSON format and sent back to the device.

[0415] Terminal: The terminal visually displays the received details to the user in the form of text, images, or video.

[0416] Step 6: Running the hybrid recommendation algorithm

[0417] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data. The algorithm combines collaborative filtering and content-based filtering. The input data is the user profile and viewing history, and the output data is a hybrid recommendation list.

[0418] Step 7: Presenting a new proposal

[0419] Server: The server sends the generated hybrid recommendation results to the device. The data is in JSON format and is securely transmitted via HTTPS.

[0420] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover new genres and styles.

[0421] Step 8: Initial setup and operation of the emotion engine

[0422] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[0423] Device: The device analyzes the collected facial and voice data in real time using OpenCV and Google Cloud Speech-to-Text to identify the user's emotional state. The analysis results are converted into JSON format and sent to the server.

[0424] Step 9: Emotion Data Analysis and Storage

[0425] Server: The server receives the emotion data sent from the device and stores it in a database. This allows for a long-term understanding of the user's emotional trends. The stored data is used for subsequent analysis and recommendations.

[0426] Step 10: Adjusting recommendations based on sentiment

[0427] Server: The server uses a generative AI model to adjust recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works. The input data is real-time emotional data and profile data, and the output data is an adjusted recommendation list.

[0428] Terminal: The terminal displays the recommendations generated in real time to the user.

[0429] (Application example 2)

[0430] 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."

[0431] Conventional entertainment recommendation systems make recommendations based on a user's past viewing history or simple preferences. However, this alone makes it difficult to provide optimal recommendations that reflect the user's current emotional state, limiting the user experience. Furthermore, the provision of detailed information is limited, leaving users with few opportunities to gain a deeper understanding of the work's background and production process. This creates a problem that can easily lead to a decrease in satisfaction with the entertainment experience.

[0432] 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.

[0433] In this invention, the server includes a device for users to input their preferences and past browsing history, a database for storing user profile information, a generative AI model for selecting works based on the user profile information, a display for presenting the selected works to the user, a means for collecting and presenting detailed information about the works, a means for generating hybrid recommendations that combine different genres and styles, and an emotion engine for analyzing the user's emotions in real time and adjusting recommendations based on the user's emotional state. This makes it possible to provide personalized recommendations that reflect the user's emotional state in real time. Furthermore, comprehensive collection and presentation of detailed information can deepen the user's understanding and attachment to the works, improving the satisfaction of the entertainment experience.

[0434] "User" means an individual who utilizes the System to receive entertainment recommendations.

[0435] A "device" is a device through which a user inputs preferences and past browsing history.

[0436] "Database" means a storage area within the system for storing user profile information.

[0437] The "generative AI model means" is a function that executes an algorithm using generative AI to select works based on the user's profile information.

[0438] "Display means" refers to a display device for visually presenting the selected entertainment piece to the user.

[0439] The "means for collecting detailed information" is a function that collects detailed information about the presented work, such as comments and interviews with the creator, behind-the-scenes information, and provides it to the user.

[0440] "Means for generating hybrid recommendations" is a function that generates new recommendations by combining different genres and styles.

[0441] The "emotion engine means" is a function that analyzes the user's emotions in real time and adjusts recommendations based on the user's emotional state.

[0442] This invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves more accurate recommendations. Below, we will explain the system in detail from the perspectives of the server, the device, and the user.

[0443] The server first collects user information using a device that allows the user to input preferences and past browsing history, then stores the user profile information in a database. This device can be a smartphone or a personal computer. The stored information is encrypted to protect the user's privacy.

[0444] The device then analyzes the user's emotions in real time through the camera and microphone and sends the data to a server. This emotion engine is realized using software such as Facial Recognition SDK and Speech Analysis SDK. Once the emotion data is sent to the server, the server runs a generative AI model based on it to select the entertainment content that best suits the user's current emotional state.

[0445] The generated recommendations are presented to the user through the device's display. For example, if the user is feeling stressed, a relaxing comedy will be recommended first. If the user shows interest, the device requests detailed information, which is then retrieved and displayed from the server. The detailed information includes comments and interviews with the creators and behind-the-scenes information.

[0446] The system also has the ability to generate hybrid recommendations that combine different genres and styles based on user profiles and emotional data, allowing users to discover new genres and styles.

[0447] As a concrete example, a user registers with a smartphone app and inputs that they like "action" and "comedy" and have watched many "Marvel movies." They also authorize the use of an emotion engine. When the app is opened, the camera and microphone analyze the user's facial expressions and voice, and the current emotional state is determined to be "stressed." Based on this data, the server recommends relaxing comedy movies.

[0448] Example prompt sentence:

[0449] Show personalized entertainment based on the user's profile data and emotional information. If the user's current emotional state is stressful, prioritize recommendations for "relaxing content."

[0450] Genre: Action, Comedy

[0451] Movies I've seen: Marvel movies

[0452] Current emotional state: Stress

[0453] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0454] Step 1:

[0455] When a user logs in for the first time, they enter their preferences and past browsing history and authorize the use of the emotion engine.

[0456] Input: The user enters information into the input form, such as action, comedy, Marvel movies, etc. Also, turns on permission to use the emotion engine.

[0457] Data processing: The device temporarily stores the entered data locally and encrypts it.

[0458] Output: The encrypted user data is sent to the server.

[0459] Step 2:

[0460] The server stores the received user profile information in a database.

[0461] Input: Encrypted user profile information sent from the device.

[0462] Data calculation: The encrypted data is decrypted, linked to the user ID, and stored in the database.

[0463] Output: A database entry containing the user's profile information.

[0464] Step 3:

[0465] The device analyzes the user's emotions in real time.

[0466] Input: User facial and voice data collected through the camera and microphone.

[0467] Data Computation: Analyze emotions using Facial Recognition SDK and Speech Analysis SDK to determine current emotional state.

[0468] Output: The parsed emotion data is generated.

[0469] Step 4:

[0470] The device transmits the analyzed emotion data to the server.

[0471] Input: Emotion data generated in the previous step.

[0472] Data calculation: The device encrypts the emotion data and sends it to the server.

[0473] Output: The encrypted emotion data is sent to the server.

[0474] Step 5:

[0475] The server runs a generative AI model based on the user profile and emotion data to generate recommendations.

[0476] Input: User profile information stored in a database and emotion data sent from the device.

[0477] Data calculation: The generative AI model takes into account the user's preferences and current emotional state, and uses AI algorithms to select the most suitable entertainment content.

[0478] Output: Recommendation results are generated.

[0479] Step 6:

[0480] The server sends the generated recommendations to the device.

[0481] Input: Recommendation results selected by the generative AI model.

[0482] Data calculation: Format the recommendation results and send them to the device.

[0483] Output: The formatted recommendation results are sent to the device.

[0484] Step 7:

[0485] The device displays the recommendation results to the user.

[0486] Input: The formatted recommendation results sent from the server.

[0487] Data Computation: Rendering the recommendation results for display in a format suitable for the user interface.

[0488] Output: A visual display that allows users to see the recommendation results.

[0489] Step 8:

[0490] The user is interested in the recommendations and requests more information.

[0491] Input: The user selects an item of interest from the recommendation results and requests more information.

[0492] Data Calculation: Formatting the request for sending to the server.

[0493] Output: The formatted request is sent to the server.

[0494] Step 9:

[0495] The server collects the details and sends them to the device.

[0496] Input: More information request sent from the terminal.

[0497] Data Calculation: Collecting information about the specified work from databases and external sources, formatting it, and sending it to the device.

[0498] Output: Formatted details are sent to the terminal.

[0499] Step 10:

[0500] The terminal displays the received detailed information to the user.

[0501] Input: The details sent by the server.

[0502] Data Calculation: Rendering detailed information for display in a format suitable for a user interface.

[0503] Output: A visual display that allows the user to see detailed information.

[0504] Step 11:

[0505] The server generates hybrid recommendations that combine different genres based on the user profile and emotional data, and sends them to the device.

[0506] Input: User profile information and emotion data.

[0507] Data calculation: The generative AI model generates hybrid recommendations that combine different genres and styles.

[0508] Output: The generated hybrid recommendation is sent to the device.

[0509] Step 12:

[0510] The terminal displays the hybrid recommendation results to the user.

[0511] Input: Hybrid recommendation results sent from the server.

[0512] Data Computation: Rendering the hybrid recommendation results for display in a format suitable for the user interface.

[0513] Output: A visual display that allows users to check the hybrid recommendation results.

[0514] Step 13:

[0515] The device analyzes the user's real-time emotional data, and the server readjusts the recommendations.

[0516] Input: Real-time user emotion data collected through camera and microphone.

[0517] Data calculation: The device analyzes the emotion data and sends the results to the server.

[0518] Output: Based on the analysis results, the server generates recommendations again and sends them to the device.

[0519] Through these steps, we can provide users with personalized entertainment recommendations, and improve the quality of the user experience by making recommendations that reflect the user's emotional state in real time.

[0520] 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.

[0521] 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.

[0522] 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.

[0523] [Second embodiment]

[0524] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0525] 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.

[0526] 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).

[0527] 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.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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."

[0536] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. The embodiments of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[0537] 1. Collecting user profiles

[0538] 1.1 Entering information when logging in for the first time

[0539] User: When logging into the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, if they like the "action" and "comedy" genres and have a preference for specific writers and directors, they enter that information.

[0540] On your device: The information you enter is temporarily stored and then sent to a server. The data is encrypted to protect your privacy.

[0541] 2. Saving User Profile Information

[0542] 2.1 Saving Profile Data

[0543] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[0544] 3. Generating Recommendations

[0545] 3.1 Recommendation Algorithm Implementation

[0546] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[0547] 3.2 Presentation of recommendation results

[0548] Server: Sends the generated recommendation results to the device.

[0549] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[0550] 4. Providing additional information

[0551] 4.1 Requesting and Providing More Information

[0552] User: Select the title of interest from the displayed recommendations and request more information.

[0553] Terminal: Sends the request to the server.

[0554] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[0555] Terminal: Visually displays the received details to the user.

[0556] 5. Generating Hybrid Recommendations

[0557] 5.1 Implementing the Hybrid Recommendation Algorithm

[0558] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits.

[0559] 5.2 Presenting a new proposal

[0560] Server: Sends the generated hybrid recommendation results to the device.

[0561] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[0562] Specific examples

[0563] Here are some concrete examples:

[0564] 1. User: This is the first time they visit the system and they state that they like action and comedy and have watched a lot of "Marvel movies."

[0565] 2. Terminal: Sends input information to the server.

[0566] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[0567] 4. Device: Display the recommendation results to the user.

[0568] 5. User: Requests more information about "Action X" that interests them.

[0569] 6. Terminal: Sends the request to the server.

[0570] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[0571] 8. Terminal: Display detailed information to the user.

[0572] 9. Server: Generates a hybrid recommendation of the new movie "Action Laughter" that combines different genres based on the user profile and sends it to the device.

[0573] 10. Terminal: Display the hybrid recommendation results to the user.

[0574] This allows users to find the entertainment that best suits their tastes, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[0575] The processing flow will be explained below.

[0576] I understand. The process steps are explained in detail below.

[0577] Collecting user profiles

[0578] Step 1:

[0579] User: Enter their preferences and past viewing history into a questionnaire-style input screen. For example, they may enter that they like movies in the "action" and "comedy" genres and that they have watched many "Marvel movies."

[0580] Step 2:

[0581] On the device: Temporarily store the information entered by the user locally and display a confirmation screen for the entered information.

[0582] Step 3:

[0583] Terminal: After the user confirms and corrects the input, the data is sent to the server. At this time, the data is encrypted before being transferred.

[0584] Storing user profile information

[0585] Step 4:

[0586] Server: Receives profile information sent from the device.

[0587] Step 5:

[0588] Server: The received profile information is stored in a database and managed in association with the user ID.

[0589] Generating recommendations

[0590] Step 6:

[0591] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[0592] Step 7:

[0593] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[0594] Step 8:

[0595] Server: Generates a list of selected works and sends it to the device.

[0596] Step 9:

[0597] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[0598] Providing additional information

[0599] Step 10:

[0600] User: Click on a recommendation that interests them and request more information.

[0601] Step 11:

[0602] Terminal: Sends the request to the server.

[0603] Step 12:

[0604] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[0605] Step 13:

[0606] Server: Sends the collected details to the device.

[0607] Step 14:

[0608] Terminal: Displays the received details to the user.

[0609] Generating Hybrid Recommendations

[0610] Step 15:

[0611] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[0612] Step 16:

[0613] Server: Sends the generated hybrid recommendation results to the device.

[0614] Step 17:

[0615] Terminal: Displays the received hybrid recommendation results to the user.

[0616] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, and generating hybrid recommendations, allowing users to efficiently and effectively find the entertainment content that best suits them, and deepening their understanding and attachment to the content through detailed information.

[0617] Example 1

[0618] 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."

[0619] Conventional entertainment recommendation systems only suggest a limited number of works based on a user's preferences and past viewing history, limiting the opportunities for users to be exposed to new genres and styles. Furthermore, there was a lack of a way for users to quickly obtain detailed information about works. This made it difficult for users to find entertainment works that matched their preferences, and to deepen their understanding and attachment to works.

[0620] 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.

[0621] In this invention, the server includes a terminal means for users to input their preferences and past browsing history, a server means for storing the user's profile information, and a generative AI model means for selecting entertainment works based on the profile information. This enables users to quickly find the entertainment works that best suit their preferences, and provides detailed work information and opportunities to experience new genres and styles.

[0622] "Terminal means" refers to a device through which a user inputs preferences and past browsing history.

[0623] "Server means" refers to a device or system for storing said user profile information.

[0624] "Generative AI model means" refers to an artificial intelligence model for selecting entertainment works based on the profile information.

[0625] "Display means" refers to a device or interface for presenting selected entertainment pieces to a user.

[0626] "Detailed information gathering means" refers to a device or system for gathering and presenting detailed information about said entertainment work.

[0627] "Means for generating hybrid recommendations" refers to a device or system for generating recommendations that combine different genres or styles.

[0628] The system of the present invention provides entertainment recommendations based on user input of preferences and past browsing history, and includes a terminal means, a server means, a generating AI model means, a display means, a detailed information collection means, and a means for generating hybrid recommendations.

[0629] 1. Collecting user profiles

[0630] 1.1 Entering information when logging in for the first time

[0631] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, say they like "action" and "comedy" and have watched many "Marvel movies." They enter this information and provide it to the system.

[0632] Terminal: The information entered by the user is temporarily stored in the terminal's memory. The stored information is then encrypted and sent to the server. This encryption process uses standard encryption techniques (e.g., AES-256).

[0633] 2. Saving User Profile Information

[0634] Server: Stores information received from the device about the user's preferences and past browsing history in a database. The information is managed by linking it to the user ID and used in subsequent processing. A general relational database (e.g., MySQL or PostgreSQL) can be used as the database.

[0635] 3. Generating Recommendations

[0636] Server: Launches the generative AI model based on the saved user profile. Prompts include the user's preferences, past browsing history, and the latest trending information. The AI ​​model uses this information to select the most suitable entertainment title. For example, for a user who likes "action" and "comedy," the AI ​​model might recommend "Action X."

[0637] Examples of prompts:

[0638] User Profile Data:

[0639] Favorite genres: Action, comedy

[0640] Viewing history: Many Marvel movies

[0641] Generate recommendations based on algorithms, taking into account the latest trends.

[0642] Server: Sends the generated recommendation results to the device.

[0643] On the device: The received recommendation results are displayed to the user in list and grid format, with thumbnail images and brief descriptions.

[0644] 4. Providing additional information

[0645] User: Selects an item from the recommendations that interests them and requests more information about it.

[0646] Terminal: Sends requests to the server.

[0647] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[0648] Terminal: Visually displays the received details to the user.

[0649] 5. Generating Hybrid Recommendations

[0650] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy."

[0651] Server: Sends the generated hybrid recommendation results to the device.

[0652] Device: The received hybrid recommendation results are displayed to the user, allowing them to discover new genres and styles.

[0653] This allows users to quickly find the entertainment works that best suit their preferences, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[0654] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0655] Step 1:

[0656] When a user logs in for the first time, they enter their preferences and past browsing history through the application or web interface. Specifically, the user enters that they like "action" and "comedy" and have watched many "Marvel movies." The entered data is temporarily stored on the device as the user's profile information.

[0657] Step 2:

[0658] The device encrypts the stored user profile information and sends it to the server. This encryption process uses, for example, AES-256. The server decodes the received information and stores it in a database along with the user ID. The input data is the user's preferences and past browsing history, and the output data is the user profile information stored in the database.

[0659] Step 3:

[0660] The server launches a generative AI model based on the stored user profile information. The AI ​​model runs an algorithm to recommend the most suitable entertainment titles, taking into account the user's preferences, past browsing history, and the latest trend information. The input data is the user profile information and the latest trend information, and the output data is the recommendation results. An example of a prompt is as follows:

[0661] User Profile Data:

[0662] Favorite genres: Action, comedy

[0663] Viewing history: Many Marvel movies

[0664] Generate recommendations based on algorithms, taking into account the latest trends.

[0665] Step 4:

[0666] The server sends the generated recommendation results to the terminal. The input data is the recommendation results, and the output data is the data sent to the terminal.

[0667] Step 5:

[0668] The terminal visually displays the received recommendation results to the user in a list or grid format, including thumbnail images and brief descriptions. The input data are the recommendation results received from the server, and the output data are the recommendation results displayed to the user.

[0669] Step 6:

[0670] The user selects an item of interest from the displayed recommendation results and requests detailed information about it. The input data is the item selected by the user, and the output data is a request for detailed information.

[0671] Step 7:

[0672] The terminal sends the user's request to the server, where the input data is the user's request and the output data is the request sent to the server.

[0673] Step 8:

[0674] In response to the request, the server collects detailed information related to the specified work and sends it to the terminal. The collected detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The input data is the work information related to the user's request, and the output data is the detailed information sent to the terminal.

[0675] Step 9:

[0676] The terminal visually displays the received detailed information to the user, with the input data being the detailed information received from the server and the output data being the detailed information displayed to the user.

[0677] Step 10:

[0678] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy." The input data is the user profile and viewing habits, and the output data is the hybrid recommendation results.

[0679] Step 11:

[0680] The server sends the generated hybrid recommendation result to the terminal, where the input data is the hybrid recommendation result and the output data is the data sent to the terminal.

[0681] Step 12:

[0682] The terminal displays the received hybrid recommendation results to the user, allowing the user to experience new genres and styles. The input data is the hybrid recommendation results received from the server, and the output data is the results displayed to the user.

[0683] (Application example 1)

[0684] 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."

[0685] Conventional content distribution services lack personalized recommendation systems based on user preferences and past browsing history, making it difficult for users to efficiently find the content they really want to watch. Furthermore, they lack innovative recommendations that combine different genres and the ability to provide detailed background information, limiting the user experience.

[0686] 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.

[0687] In this invention, the server includes a device for users to input their preferences and past browsing history, a database that stores the user's profile information, a generative AI model means that selects works based on the profile information, a display means that presents the selected works to the user, a means that collects and presents detailed information about the works, a means that generates hybrid recommendations that combine different genres and styles, and a content distribution service application means that is installed on the smartphone. This enables highly accurate recommendations based on the user's preferences and past browsing history, as well as new proposals that combine detailed work information and different genres.

[0688] The "device for a user to input preferences and past viewing history" is a terminal for a user to input his or her own viewing preferences and a history of content that has been viewed in the past.

[0689] The "database that stores the user's profile information" is a database system that organizes and stores the viewing preferences and past history information entered by the user.

[0690] The "generative AI model means for selecting works based on the profile information" refers to an artificial intelligence model that uses the saved user profile information to select the most suitable content.

[0691] "Display means for presenting selected works to a user" means a device or screen for visually displaying to a user the content selected by the generative AI model.

[0692] The "means for collecting and presenting detailed information about the work" is a function for collecting detailed information about the content that the user wishes to view, such as background information, comments and interviews from the creator, and displaying this information to the user.

[0693] "Means for generating hybrid recommendations that combine different genres and styles" is a mechanism for generating novel content recommendations that combine different genres and styles based on user profile information.

[0694] The "content distribution service application means installed on a smartphone" is an application that runs on a smartphone and distributes and recommends content to users.

[0695] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Hereinafter, specific embodiments of the present invention will be described.

[0696] 1. Collecting user profiles

[0697] 1.1 Entering information when logging in for the first time

[0698] When users log in to the system for the first time, they must enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. They can enter their preferred genres, specific authors, or production companies. For example, a user might enter that they like "action" and "comedy," and that they particularly prefer works from "popular series."

[0699] 1.2 Data storage

[0700] The device temporarily stores the information entered by the user and then transmits it to the server. The transmitted data is encrypted and appropriate security measures are used to protect the user's privacy. The server stores the received data in a database and manages it by linking it to the user ID.

[0701] 2. Generating Recommendations

[0702] 2.1 Organization and analysis

[0703] The server uses the stored user profile information to generate appropriate content recommendations using a generative AI model that considers the user's preferences, past browsing history, and the latest trends to select the most suitable entertainment content. The AI ​​model used includes popular deep learning frameworks such as TensorFlow and PyTorch.

[0704] 2.2 Presenting Recommendations

[0705] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions.

[0706] 3. Providing additional information

[0707] 3.1 Requesting and Providing More Information

[0708] The user selects a work of interest from the displayed recommendation results and requests detailed information. The device then sends this request to the server. The server collects relevant detailed information and sends it to the device. The detailed information may include director's comments, interviews with the writers, behind-the-scenes information, etc. The device then visually displays this information to the user.

[0709] 4. Generating Hybrid Recommendations

[0710] 4.1 Hybridization

[0711] The server generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data, again using generative AI models.

[0712] 4.2 Presenting a new proposal

[0713] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from conventional ones.

[0714] Specific examples

[0715] A user accesses the system for the first time and enters that they like the "action" and "comedy" genres and have watched many "popular series." The device sends this information to the server, which stores it in a database. The system then uses a generative AI model to recommend "new action movies" and sends them to the device. When the user requests more information about a "new action movie" that interests them, the system provides detailed information, including director comments and interviews. The server also generates hybrid recommendations for new "action comedies" that combine different genres based on the user profile and sends them to the device. This allows users to discover new genres and styles.

[0716] Example prompt sentence:

[0717] "Using the profile information of user ID: '12345', please generate the best entertainment recommendations based on the following criteria: Favorite genres - 'action', 'comedy', viewing history - 'popular series'. Also, please provide hybrid recommendations that combine different genres."

[0718] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0719] Step 1:

[0720] When a user logs in to the system for the first time, they enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. For example, the user may enter that they prefer "action" and "comedy" genres and that they like works from a particular production company. The input data is temporarily stored on the device.

[0721] Step 2:

[0722] The device encrypts the preferences and browsing history data entered by the user and sends it to the server. The server receives this data and stores it in a database. At this time, the information is managed consistently by associating it with the user ID as a key.

[0723] Step 3:

[0724] The server reads the user profile information stored in the database and generates content recommendations using a generative AI model. The user's profile information is provided as input to the AI ​​model, and suitable entertainment candidates are obtained as output. The generative AI model used includes deep learning frameworks such as TensorFlow and PyTorch. The model takes into account the user's preferences, past browsing history, and the latest trending information.

[0725] Step 4:

[0726] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions of each work.

[0727] Step 5:

[0728] The user selects an interesting work from the displayed recommendation results and requests its detailed information. The device sends this request to the server, providing the work ID as input and obtaining the related detailed information as output.

[0729] Step 6:

[0730] The server collects detailed information related to the specified work from external APIs and databases and sends it to the device. The detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The device visually displays this information to the user.

[0731] Step 7:

[0732] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. The generative AI model is used again, providing the user's profile information and past viewing data as input and obtaining works in new genres and styles as output.

[0733] Step 8:

[0734] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from the conventional ones. The user can further enhance their viewing experience by selecting content to watch from the new candidates and requesting more information again.

[0735] 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.

[0736] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[0737] 1. Collecting user profiles

[0738] 1.1 Entering information when logging in for the first time

[0739] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, they may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[0740] On your device: The information you enter is temporarily stored locally and then sent to a server. The data is encrypted to protect your privacy.

[0741] 2. Saving User Profile Information

[0742] 2.1 Saving Profile Data

[0743] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[0744] 3. Generating Recommendations

[0745] 3.1 Recommendation Algorithm Implementation

[0746] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[0747] 3.2 Presentation of recommendation results

[0748] Server: Sends the generated recommendation results to the device.

[0749] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[0750] 4. Providing additional information

[0751] 4.1 Requesting and Providing More Information

[0752] User: Select the title of interest from the displayed recommendations and request more information.

[0753] Terminal: Sends the request to the server.

[0754] Server: Retrieves detailed information related to a specified film from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[0755] Terminal: Visually displays the received details to the user.

[0756] 5. Generating Hybrid Recommendations

[0757] 5.1 Implementing the Hybrid Recommendation Algorithm

[0758] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data.

[0759] 5.2 Presenting a new proposal

[0760] Server: Sends the generated hybrid recommendation results to the device.

[0761] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[0762] 6. Leveraging Emotional Engines

[0763] 6.1 Initial setup and operation of the emotion engine

[0764] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects facial and voice data from the user through the camera and microphone.

[0765] Device: Analyzes collected facial and voice data in real time to identify the user's current emotions.

[0766] 6.2 Emotion Data Analysis and Storage

[0767] Server: Receives the emotion data sent from the device and stores it in a database along with the profile information, making it possible to understand the user's emotional tendencies over the long term.

[0768] 6.3 Adjusting Recommendations Based on Sentiment

[0769] Server: The generative AI model adjusts the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[0770] Specific examples

[0771] Here are some concrete examples:

[0772] 1. User: This is the first time the system is accessed and the user enters that they like action and comedy and have watched many Marvel movies. They also authorize the use of the emotion engine.

[0773] 2. Terminal: Sends input information and emotion engine settings to the server.

[0774] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[0775] 4. Device: Display the recommendation results to the user.

[0776] 5. User: Requests more information about "Action X" that interests them.

[0777] 6. Terminal: Sends the request to the server.

[0778] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[0779] 8. Terminal: Display detailed information to the user.

[0780] 9. Server: Based on the user profile and emotion data, generate a hybrid recommendation for a new movie, "Action Laughter," which combines different genres, and send it to the device.

[0781] 10. Terminal: Display the hybrid recommendation results to the user.

[0782] 11. Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[0783] 12. Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that is relaxing.

[0784] 13. Terminal: Displays the recommendations generated in real time to the user.

[0785] This allows users to find the entertainment content that best suits their preferences, deepening their understanding and attachment to the content through detailed information.In addition, the emotion engine provides personalized recommendations that reflect the user's emotional state, enabling a more fulfilling entertainment experience.

[0786] The processing flow will be explained below.

[0787] Collecting user profiles

[0788] Step 1:

[0789] User: When accessing the system for the first time, the user logs in. After that, the user enters their preferred genre (e.g., action, comedy), favorite writers and directors, and a list of works they have watched. The user also authorizes the use of the emotion engine.

[0790] Step 2:

[0791] Terminal: The entered information is temporarily stored locally and a confirmation screen is displayed, where the user can confirm and correct the entered information.

[0792] Step 3:

[0793] Terminal: The input information is sent to the server. The transmitted data is encrypted to protect privacy.

[0794] Storing user profile information

[0795] Step 4:

[0796] Server: Stores the profile information received from the device in a database. Manages the information by linking it to the user ID.

[0797] Generating recommendations

[0798] Step 5:

[0799] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[0800] Step 6:

[0801] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[0802] Step 7:

[0803] Server: Generates a list of selected works and sends it to the device.

[0804] Step 8:

[0805] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[0806] Providing additional information

[0807] Step 9:

[0808] User: Click on a recommendation that interests them and request more information.

[0809] Step 10:

[0810] Terminal: Sends the request to the server.

[0811] Step 11:

[0812] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[0813] Step 12:

[0814] Server: Sends the collected details to the device.

[0815] Step 13:

[0816] Terminal: Displays the received details to the user.

[0817] Generating Hybrid Recommendations

[0818] Step 14:

[0819] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[0820] Step 15:

[0821] Server: Sends the generated hybrid recommendation results to the device.

[0822] Step 16:

[0823] Terminal: Displays the received hybrid recommendation results to the user.

[0824] Utilizing the Emotion Engine

[0825] Step 17:

[0826] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice data in real time via the camera and microphone.

[0827] Step 18:

[0828] Device: Analyzes facial and voice data collected by the emotion engine to identify the user's current emotion. For example, if the user is smiling, it is determined to be "joy."

[0829] Step 19:

[0830] Device: Sends analyzed emotion data to the server.

[0831] Step 20:

[0832] Server: The received emotional data is stored in a database along with the user's profile information, allowing for a long-term understanding of the user's emotional tendencies.

[0833] Step 21:

[0834] Server: The generative AI model adjusts the recommendation results based on real-time emotional data. For example, if the user is feeling stressed, it will prioritize relaxing works.

[0835] Step 22:

[0836] Server: Sends the adjusted recommendation results to the device.

[0837] Step 23:

[0838] Device: Displays real-time generated recommendations to the user.

[0839] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, utilizing the emotion engine, and adjusting the recommendations in real time, allowing users to efficiently and effectively find the entertainment content that best suits them, deepen their understanding and attachment to the content through detailed information, and enjoy a personalized entertainment experience through the emotion engine.

[0840] Example 2

[0841] 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."

[0842] Conventional entertainment recommendation systems often make recommendations based on simple user preferences and past viewing history, and lack the ability to present personalized content that reflects the user's emotions and momentary mood. Furthermore, they are limited in their ability to suggest new content that combines different genres and styles, making it difficult for users to discover new content without becoming bored.

[0843] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input device for a user to input preferences and past browsing history, data storage means for saving the user's profile information, generation AI means for selecting works based on the profile information, a display device for presenting the selected works to the user, information provision means for collecting and presenting detailed information about the works, means for generating hybrid recommendations that combine different genres and styles, and emotion engine means for recognizing the user's emotions and adjusting the recommendations. This allows the user to receive personalized recommendations for entertainment works that reflect their own emotional state and also enables them to discover works in new genres and styles.

[0844] An "input device" is a device that allows a user to input their preferences and past browsing history into the system.

[0845] "Data Storage Means" means a storage device or storage means for storing user profile information.

[0846] The "generative AI means" refers to an artificial intelligence algorithm and its execution environment for selecting the most suitable entertainment works based on the user's profile information.

[0847] A "display device" is a device for visually presenting selected entertainment content to a user.

[0848] "Information providing means" refers to means for collecting detailed information about entertainment works and presenting it to users.

[0849] A "means for generating hybrid recommendations" is an algorithm and its execution environment for generating entertainment works that combine different genres and styles.

[0850] "Emotion engine means" refers to techniques and devices for recognizing a user's emotions and tailoring entertainment recommendations based thereon.

[0851] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[0852] Collecting user profiles

[0853] Entering information when logging in for the first time

[0854] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. For example, the user may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[0855] Terminal: The terminal temporarily stores the entered information locally, encrypts it (using AES, etc.), and sends it to the server.

[0856] Storing user profile information

[0857] Server: The server receives information about the user's preferences and browsing history from the device and stores it in a database (e.g., MySQL or PostgreSQL). The information is linked to the user ID and used for subsequent recommendation processing.

[0858] Generating recommendations

[0859] Running the recommendation algorithm

[0860] Server: The server runs a generative AI model (e.g., TensorFlow or PyTorch) based on the user profile stored in the database. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past viewing history, and the latest trend information. Specifically, it rates genres that users have watched most frequently and uses this to rank similar content.

[0861] Presenting recommendation results

[0862] Server: The server sends the generated recommendation results to the device. HTTPS is used for communication.

[0863] Device: The device displays the received recommendation results to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[0864] Providing additional information

[0865] Requesting and Providing More Information

[0866] User: The user selects the work of interest from the displayed recommendations and requests more information.

[0867] Terminal: The terminal sends the user's request to the server.

[0868] Server: The server retrieves details related to the specified film from a database or external sources (e.g., IMDb API), including director's comments, interviews, and behind-the-scenes information about the film.

[0869] Terminal: The terminal visually displays the received details to the user.

[0870] Generating Hybrid Recommendations

[0871] Running a hybrid recommendation algorithm

[0872] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data, using the COLAB (Collaborative Filtering) algorithm and Content-Based Filtering algorithm.

[0873] Presenting a new proposal

[0874] Server: The server sends the generated hybrid recommendation results to the terminal.

[0875] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover works in new genres and styles that they have never seen before.

[0876] Utilizing the Emotion Engine

[0877] Initial settings and operation of the emotion engine

[0878] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[0879] Device: The device analyzes the collected facial and voice data to determine the user's current emotion using technologies such as OpenCV and Google Cloud Speech-to-Text.

[0880] Emotion data analysis and storage

[0881] Server: The server receives the emotion data sent from the device and stores it in a database, which makes it possible to understand the user's emotional tendencies over the long term.

[0882] Tailoring recommendations based on sentiment

[0883] Server: The server uses a generative AI model to adjust the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[0884] Specific examples

[0885] User: This is the first time they access the system and they state that they like action and comedy and have watched a lot of Marvel movies. They also allow the use of the emotion engine.

[0886] Device: Sends input information and emotion engine settings to the server.

[0887] Server: Stores user profiles and uses generative AI models to create optimal recommendations, such as selecting "Action X" and sending them to the device.

[0888] Device: Display the recommendation results to the user.

[0889] User: Requests more information about "Action X" that interests them.

[0890] Terminal: Sends the request to the server.

[0891] Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[0892] Terminal: Display detailed information to the user.

[0893] Server: Based on the user profile and emotional data, generate a hybrid recommendation for the new movie "Action Laughter," which combines different genres, and send it to the device.

[0894] Device: Display hybrid recommendation results to the user.

[0895] Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[0896] Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that will help you relax.

[0897] Device: Displays real-time generated recommendations to the user.

[0898] Examples of prompt statements

[0899] 1. "Generate recommendations for users who like action movies."

[0900] 2. "Use the emotion engine to recommend relaxing movies to users who are feeling stressed."

[0901] 3. "Suggest a new genre of film that combines action and comedy."

[0902] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0903] Step 1: Collecting user profiles

[0904] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. Specifically, they enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies." The input is done through a form, in the form of text and multiple choice.

[0905] Terminal: The terminal temporarily stores the information entered by the user in local storage. The input data is structured in JSON format and then transferred to the server using AES encryption technology. Based on the input, the initial user profile data JSON is generated.

[0906] Step 2: Save user profile information

[0907] Server: The server receives the encrypted user profile data from the device. It decrypts the data and stores it in a database using a database management system (e.g., MySQL or PostgreSQL). During the storage process, it associates the information with the user ID and stores it, converting it from JSON to SQL format.

[0908] Step 3: Run the recommendation algorithm

[0909] Server: The server runs a generative AI model based on the user profile data stored in the database. The AI ​​model uses machine learning frameworks such as TensorFlow and PyTorch to select the most suitable entertainment content, taking into account the user's preferences, past viewing history, and the latest trend information. The input data is the user profile and viewing history data, and the output data is a recommendation list.

[0910] Step 4: Presenting the Recommendation Results

[0911] Server: The server sends the generated recommendation results to the device using the HTTPS protocol, and the recommendation data is structured in JSON format.

[0912] Device: The device interprets the received recommendations and displays them to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[0913] Step 5: Request and provide more information

[0914] User: The user selects an item they are interested in from the displayed recommendations and requests more information. For example, the user may request details about "Action X."

[0915] Terminal: The terminal sends the user's request to the server, which is structured in JSON and sent to the server using HTTPS.

[0916] Server: The server retrieves details related to the specified movie from a database or external source (e.g., IMDb API). These details may include director's comments, interviews, and behind-the-scenes information. The retrieved data is converted into JSON format and sent back to the device.

[0917] Terminal: The terminal visually displays the received details to the user in the form of text, images, or video.

[0918] Step 6: Running the hybrid recommendation algorithm

[0919] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data. The algorithm combines collaborative filtering and content-based filtering. The input data is the user profile and viewing history, and the output data is a hybrid recommendation list.

[0920] Step 7: Presenting a new proposal

[0921] Server: The server sends the generated hybrid recommendation results to the device. The data is in JSON format and is securely transmitted via HTTPS.

[0922] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover new genres and styles.

[0923] Step 8: Initial setup and operation of the emotion engine

[0924] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[0925] Device: The device analyzes the collected facial and voice data in real time using OpenCV and Google Cloud Speech-to-Text to identify the user's emotional state. The analysis results are converted into JSON format and sent to the server.

[0926] Step 9: Emotion Data Analysis and Storage

[0927] Server: The server receives the emotion data sent from the device and stores it in a database. This allows for a long-term understanding of the user's emotional trends. The stored data is used for subsequent analysis and recommendations.

[0928] Step 10: Adjusting recommendations based on sentiment

[0929] Server: The server uses a generative AI model to adjust recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works. The input data is real-time emotional data and profile data, and the output data is an adjusted recommendation list.

[0930] Terminal: The terminal displays the recommendations generated in real time to the user.

[0931] (Application example 2)

[0932] 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."

[0933] Conventional entertainment recommendation systems make recommendations based on a user's past viewing history or simple preferences. However, this alone makes it difficult to provide optimal recommendations that reflect the user's current emotional state, limiting the user experience. Furthermore, the provision of detailed information is limited, leaving users with few opportunities to gain a deeper understanding of the work's background and production process. This creates a problem that can easily lead to a decrease in satisfaction with the entertainment experience.

[0934] 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.

[0935] In this invention, the server includes a device for users to input their preferences and past browsing history, a database for storing user profile information, a generative AI model for selecting works based on the user profile information, a display for presenting the selected works to the user, a means for collecting and presenting detailed information about the works, a means for generating hybrid recommendations that combine different genres and styles, and an emotion engine for analyzing the user's emotions in real time and adjusting recommendations based on the user's emotional state. This makes it possible to provide personalized recommendations that reflect the user's emotional state in real time. Furthermore, comprehensive collection and presentation of detailed information can deepen the user's understanding and attachment to the works, improving the satisfaction of the entertainment experience.

[0936] "User" means an individual who utilizes the System to receive entertainment recommendations.

[0937] A "device" is a device through which a user inputs preferences and past browsing history.

[0938] "Database" means a storage area within the system for storing user profile information.

[0939] The "generative AI model means" is a function that executes an algorithm using generative AI to select works based on the user's profile information.

[0940] "Display means" refers to a display device for visually presenting the selected entertainment piece to the user.

[0941] The "means for collecting detailed information" is a function that collects detailed information about the presented work, such as comments and interviews with the creator, behind-the-scenes information, and provides it to the user.

[0942] "Means for generating hybrid recommendations" is a function that generates new recommendations by combining different genres and styles.

[0943] The "emotion engine means" is a function that analyzes the user's emotions in real time and adjusts recommendations based on the user's emotional state.

[0944] This invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves more accurate recommendations. Below, we will explain the system in detail from the perspectives of the server, the device, and the user.

[0945] The server first collects user information using a device that allows the user to input preferences and past browsing history, then stores the user profile information in a database. This device can be a smartphone or a personal computer. The stored information is encrypted to protect the user's privacy.

[0946] The device then analyzes the user's emotions in real time through the camera and microphone and sends the data to a server. This emotion engine is realized using software such as Facial Recognition SDK and Speech Analysis SDK. Once the emotion data is sent to the server, the server runs a generative AI model based on it to select the entertainment content that best suits the user's current emotional state.

[0947] The generated recommendations are presented to the user through the device's display. For example, if the user is feeling stressed, a relaxing comedy will be recommended first. If the user shows interest, the device requests detailed information, which is then retrieved and displayed from the server. The detailed information includes comments and interviews with the creators and behind-the-scenes information.

[0948] The system also has the ability to generate hybrid recommendations that combine different genres and styles based on user profiles and emotional data, allowing users to discover new genres and styles.

[0949] As a concrete example, a user registers with a smartphone app and inputs that they like "action" and "comedy" and have watched many "Marvel movies." They also authorize the use of an emotion engine. When the app is opened, the camera and microphone analyze the user's facial expressions and voice, and the current emotional state is determined to be "stressed." Based on this data, the server recommends relaxing comedy movies.

[0950] Example prompt sentence:

[0951] Show personalized entertainment based on the user's profile data and emotional information. If the user's current emotional state is stressful, prioritize recommendations for "relaxing content."

[0952] Genre: Action, Comedy

[0953] Movies I've seen: Marvel movies

[0954] Current emotional state: Stress

[0955] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0956] Step 1:

[0957] When a user logs in for the first time, they enter their preferences and past browsing history and authorize the use of the emotion engine.

[0958] Input: The user enters information into the input form, such as action, comedy, Marvel movies, etc. Also, turns on permission to use the emotion engine.

[0959] Data processing: The device temporarily stores the entered data locally and encrypts it.

[0960] Output: The encrypted user data is sent to the server.

[0961] Step 2:

[0962] The server stores the received user profile information in a database.

[0963] Input: Encrypted user profile information sent from the device.

[0964] Data calculation: The encrypted data is decrypted, linked to the user ID, and stored in the database.

[0965] Output: A database entry containing the user's profile information.

[0966] Step 3:

[0967] The device analyzes the user's emotions in real time.

[0968] Input: User facial and voice data collected through the camera and microphone.

[0969] Data Computation: Analyze emotions using Facial Recognition SDK and Speech Analysis SDK to determine current emotional state.

[0970] Output: The parsed emotion data is generated.

[0971] Step 4:

[0972] The device transmits the analyzed emotion data to the server.

[0973] Input: Emotion data generated in the previous step.

[0974] Data calculation: The device encrypts the emotion data and sends it to the server.

[0975] Output: The encrypted emotion data is sent to the server.

[0976] Step 5:

[0977] The server runs a generative AI model based on the user profile and emotion data to generate recommendations.

[0978] Input: User profile information stored in a database and emotion data sent from the device.

[0979] Data calculation: The generative AI model takes into account the user's preferences and current emotional state, and uses AI algorithms to select the most suitable entertainment content.

[0980] Output: Recommendation results are generated.

[0981] Step 6:

[0982] The server sends the generated recommendations to the device.

[0983] Input: Recommendation results selected by the generative AI model.

[0984] Data calculation: Format the recommendation results and send them to the device.

[0985] Output: The formatted recommendation results are sent to the device.

[0986] Step 7:

[0987] The device displays the recommendation results to the user.

[0988] Input: The formatted recommendation results sent from the server.

[0989] Data Computation: Rendering the recommendation results for display in a format suitable for the user interface.

[0990] Output: A visual display that allows users to see the recommendation results.

[0991] Step 8:

[0992] The user is interested in the recommendations and requests more information.

[0993] Input: The user selects an item of interest from the recommendation results and requests more information.

[0994] Data Calculation: Formatting the request for sending to the server.

[0995] Output: The formatted request is sent to the server.

[0996] Step 9:

[0997] The server collects the details and sends them to the device.

[0998] Input: More information request sent from the terminal.

[0999] Data Calculation: Collecting information about the specified work from databases and external sources, formatting it, and sending it to the device.

[1000] Output: Formatted details are sent to the terminal.

[1001] Step 10:

[1002] The terminal displays the received detailed information to the user.

[1003] Input: The details sent by the server.

[1004] Data Calculation: Rendering detailed information for display in a format suitable for a user interface.

[1005] Output: A visual display that allows the user to see detailed information.

[1006] Step 11:

[1007] The server generates hybrid recommendations that combine different genres based on the user profile and emotional data, and sends them to the device.

[1008] Input: User profile information and emotion data.

[1009] Data calculation: The generative AI model generates hybrid recommendations that combine different genres and styles.

[1010] Output: The generated hybrid recommendation is sent to the device.

[1011] Step 12:

[1012] The terminal displays the hybrid recommendation results to the user.

[1013] Input: Hybrid recommendation results sent from the server.

[1014] Data Computation: Rendering the hybrid recommendation results for display in a format suitable for the user interface.

[1015] Output: A visual display that allows users to check the hybrid recommendation results.

[1016] Step 13:

[1017] The device analyzes the user's real-time emotional data, and the server readjusts the recommendations.

[1018] Input: Real-time user emotion data collected through camera and microphone.

[1019] Data calculation: The device analyzes the emotion data and sends the results to the server.

[1020] Output: Based on the analysis results, the server generates recommendations again and sends them to the device.

[1021] Through these steps, we can provide users with personalized entertainment recommendations, and improve the quality of the user experience by making recommendations that reflect the user's emotional state in real time.

[1022] 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.

[1023] 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.

[1024] 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.

[1025] [Third embodiment]

[1026] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1027] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1028] 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).

[1029] 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.

[1030] 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.

[1031] 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).

[1032] 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.

[1033] 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.

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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."

[1038] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. The embodiments of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[1039] 1. Collecting user profiles

[1040] 1.1 Entering information when logging in for the first time

[1041] User: When logging into the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, if they like the "action" and "comedy" genres and have a preference for specific writers and directors, they enter that information.

[1042] On your device: The information you enter is temporarily stored and then sent to a server. The data is encrypted to protect your privacy.

[1043] 2. Saving User Profile Information

[1044] 2.1 Saving Profile Data

[1045] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[1046] 3. Generating Recommendations

[1047] 3.1 Recommendation Algorithm Implementation

[1048] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[1049] 3.2 Presentation of recommendation results

[1050] Server: Sends the generated recommendation results to the device.

[1051] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[1052] 4. Providing additional information

[1053] 4.1 Requesting and Providing More Information

[1054] User: Select the title of interest from the displayed recommendations and request more information.

[1055] Terminal: Sends the request to the server.

[1056] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[1057] Terminal: Visually displays the received details to the user.

[1058] 5. Generating Hybrid Recommendations

[1059] 5.1 Implementing the Hybrid Recommendation Algorithm

[1060] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits.

[1061] 5.2 Presenting a new proposal

[1062] Server: Sends the generated hybrid recommendation results to the device.

[1063] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[1064] Specific examples

[1065] Here are some concrete examples:

[1066] 1. User: This is the first time they visit the system and they state that they like action and comedy and have watched a lot of "Marvel movies."

[1067] 2. Terminal: Sends input information to the server.

[1068] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[1069] 4. Device: Display the recommendation results to the user.

[1070] 5. User: Requests more information about "Action X" that interests them.

[1071] 6. Terminal: Sends the request to the server.

[1072] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[1073] 8. Terminal: Display detailed information to the user.

[1074] 9. Server: Generates a hybrid recommendation of the new movie "Action Laughter" that combines different genres based on the user profile and sends it to the device.

[1075] 10. Terminal: Display the hybrid recommendation results to the user.

[1076] This allows users to find the entertainment that best suits their tastes, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[1077] The processing flow will be explained below.

[1078] I understand. The process steps are explained in detail below.

[1079] Collecting user profiles

[1080] Step 1:

[1081] User: Enter their preferences and past viewing history into a questionnaire-style input screen. For example, they may enter that they like movies in the "action" and "comedy" genres and that they have watched many "Marvel movies."

[1082] Step 2:

[1083] On the device: Temporarily store the information entered by the user locally and display a confirmation screen for the entered information.

[1084] Step 3:

[1085] Terminal: After the user confirms and corrects the input, the data is sent to the server. At this time, the data is encrypted before being transferred.

[1086] Storing user profile information

[1087] Step 4:

[1088] Server: Receives profile information sent from the device.

[1089] Step 5:

[1090] Server: The received profile information is stored in a database and managed in association with the user ID.

[1091] Generating recommendations

[1092] Step 6:

[1093] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[1094] Step 7:

[1095] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[1096] Step 8:

[1097] Server: Generates a list of selected works and sends it to the device.

[1098] Step 9:

[1099] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[1100] Providing additional information

[1101] Step 10:

[1102] User: Click on a recommendation that interests them and request more information.

[1103] Step 11:

[1104] Terminal: Sends the request to the server.

[1105] Step 12:

[1106] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[1107] Step 13:

[1108] Server: Sends the collected details to the device.

[1109] Step 14:

[1110] Terminal: Displays the received details to the user.

[1111] Generating Hybrid Recommendations

[1112] Step 15:

[1113] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[1114] Step 16:

[1115] Server: Sends the generated hybrid recommendation results to the device.

[1116] Step 17:

[1117] Terminal: Displays the received hybrid recommendation results to the user.

[1118] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, and generating hybrid recommendations, allowing users to efficiently and effectively find the entertainment content that best suits them, and deepening their understanding and attachment to the content through detailed information.

[1119] Example 1

[1120] 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."

[1121] Conventional entertainment recommendation systems only suggest a limited number of works based on a user's preferences and past viewing history, limiting the opportunities for users to be exposed to new genres and styles. Furthermore, there was a lack of a way for users to quickly obtain detailed information about works. This made it difficult for users to find entertainment works that matched their preferences, and to deepen their understanding and attachment to works.

[1122] 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.

[1123] In this invention, the server includes a terminal means for users to input their preferences and past browsing history, a server means for storing the user's profile information, and a generative AI model means for selecting entertainment works based on the profile information. This enables users to quickly find the entertainment works that best suit their preferences, and provides detailed work information and opportunities to experience new genres and styles.

[1124] "Terminal means" refers to a device through which a user inputs preferences and past browsing history.

[1125] "Server means" refers to a device or system for storing said user profile information.

[1126] "Generative AI model means" refers to an artificial intelligence model for selecting entertainment works based on the profile information.

[1127] "Display means" refers to a device or interface for presenting selected entertainment pieces to a user.

[1128] "Detailed information gathering means" refers to a device or system for gathering and presenting detailed information about said entertainment work.

[1129] "Means for generating hybrid recommendations" refers to a device or system for generating recommendations that combine different genres or styles.

[1130] The system of the present invention provides entertainment recommendations based on user input of preferences and past browsing history, and includes a terminal means, a server means, a generating AI model means, a display means, a detailed information collection means, and a means for generating hybrid recommendations.

[1131] 1. Collecting user profiles

[1132] 1.1 Entering information when logging in for the first time

[1133] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, say they like "action" and "comedy" and have watched many "Marvel movies." They enter this information and provide it to the system.

[1134] Terminal: The information entered by the user is temporarily stored in the terminal's memory. The stored information is then encrypted and sent to the server. This encryption process uses standard encryption techniques (e.g., AES-256).

[1135] 2. Saving User Profile Information

[1136] Server: Stores information received from the device about the user's preferences and past browsing history in a database. The information is managed by linking it to the user ID and used in subsequent processing. A general relational database (e.g., MySQL or PostgreSQL) can be used as the database.

[1137] 3. Generating Recommendations

[1138] Server: Launches the generative AI model based on the saved user profile. Prompts include the user's preferences, past browsing history, and the latest trending information. The AI ​​model uses this information to select the most suitable entertainment title. For example, for a user who likes "action" and "comedy," the AI ​​model might recommend "Action X."

[1139] Examples of prompts:

[1140] User Profile Data:

[1141] Favorite genres: Action, comedy

[1142] Viewing history: Many Marvel movies

[1143] Generate recommendations based on algorithms, taking into account the latest trends.

[1144] Server: Sends the generated recommendation results to the device.

[1145] On the device: The received recommendation results are displayed to the user in list and grid format, with thumbnail images and brief descriptions.

[1146] 4. Providing additional information

[1147] User: Selects an item from the recommendations that interests them and requests more information about it.

[1148] Terminal: Sends requests to the server.

[1149] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[1150] Terminal: Visually displays the received details to the user.

[1151] 5. Generating Hybrid Recommendations

[1152] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy."

[1153] Server: Sends the generated hybrid recommendation results to the device.

[1154] Device: The received hybrid recommendation results are displayed to the user, allowing them to discover new genres and styles.

[1155] This allows users to quickly find the entertainment works that best suit their preferences, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[1156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1157] Step 1:

[1158] When a user logs in for the first time, they enter their preferences and past browsing history through the application or web interface. Specifically, the user enters that they like "action" and "comedy" and have watched many "Marvel movies." The entered data is temporarily stored on the device as the user's profile information.

[1159] Step 2:

[1160] The device encrypts the stored user profile information and sends it to the server. This encryption process uses, for example, AES-256. The server decodes the received information and stores it in a database along with the user ID. The input data is the user's preferences and past browsing history, and the output data is the user profile information stored in the database.

[1161] Step 3:

[1162] The server launches a generative AI model based on the stored user profile information. The AI ​​model runs an algorithm to recommend the most suitable entertainment titles, taking into account the user's preferences, past browsing history, and the latest trend information. The input data is the user profile information and the latest trend information, and the output data is the recommendation results. An example of a prompt is as follows:

[1163] User Profile Data:

[1164] Favorite genres: Action, comedy

[1165] Viewing history: Many Marvel movies

[1166] Generate recommendations based on algorithms, taking into account the latest trends.

[1167] Step 4:

[1168] The server sends the generated recommendation results to the terminal. The input data is the recommendation results, and the output data is the data sent to the terminal.

[1169] Step 5:

[1170] The terminal visually displays the received recommendation results to the user in a list or grid format, including thumbnail images and brief descriptions. The input data are the recommendation results received from the server, and the output data are the recommendation results displayed to the user.

[1171] Step 6:

[1172] The user selects an item of interest from the displayed recommendation results and requests detailed information about it. The input data is the item selected by the user, and the output data is a request for detailed information.

[1173] Step 7:

[1174] The terminal sends the user's request to the server, where the input data is the user's request and the output data is the request sent to the server.

[1175] Step 8:

[1176] In response to the request, the server collects detailed information related to the specified work and sends it to the terminal. The collected detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The input data is the work information related to the user's request, and the output data is the detailed information sent to the terminal.

[1177] Step 9:

[1178] The terminal visually displays the received detailed information to the user, with the input data being the detailed information received from the server and the output data being the detailed information displayed to the user.

[1179] Step 10:

[1180] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy." The input data is the user profile and viewing habits, and the output data is the hybrid recommendation results.

[1181] Step 11:

[1182] The server sends the generated hybrid recommendation result to the terminal, where the input data is the hybrid recommendation result and the output data is the data sent to the terminal.

[1183] Step 12:

[1184] The terminal displays the received hybrid recommendation results to the user, allowing the user to experience new genres and styles. The input data is the hybrid recommendation results received from the server, and the output data is the results displayed to the user.

[1185] (Application example 1)

[1186] 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."

[1187] Conventional content distribution services lack personalized recommendation systems based on user preferences and past browsing history, making it difficult for users to efficiently find the content they really want to watch. Furthermore, they lack innovative recommendations that combine different genres and the ability to provide detailed background information, limiting the user experience.

[1188] 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.

[1189] In this invention, the server includes a device for users to input their preferences and past browsing history, a database that stores the user's profile information, a generative AI model means that selects works based on the profile information, a display means that presents the selected works to the user, a means that collects and presents detailed information about the works, a means that generates hybrid recommendations that combine different genres and styles, and a content distribution service application means that is installed on the smartphone. This enables highly accurate recommendations based on the user's preferences and past browsing history, as well as new proposals that combine detailed work information and different genres.

[1190] The "device for a user to input preferences and past viewing history" is a terminal for a user to input his or her own viewing preferences and a history of content that has been viewed in the past.

[1191] The "database that stores the user's profile information" is a database system that organizes and stores the viewing preferences and past history information entered by the user.

[1192] The "generative AI model means for selecting works based on the profile information" refers to an artificial intelligence model that uses the saved user profile information to select the most suitable content.

[1193] "Display means for presenting selected works to a user" means a device or screen for visually displaying to a user the content selected by the generative AI model.

[1194] The "means for collecting and presenting detailed information about the work" is a function for collecting detailed information about the content that the user wishes to view, such as background information, comments and interviews from the creator, and displaying this information to the user.

[1195] "Means for generating hybrid recommendations that combine different genres and styles" is a mechanism for generating novel content recommendations that combine different genres and styles based on user profile information.

[1196] The "content distribution service application means installed on a smartphone" is an application that runs on a smartphone and distributes and recommends content to users.

[1197] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Hereinafter, specific embodiments of the present invention will be described.

[1198] 1. Collecting user profiles

[1199] 1.1 Entering information when logging in for the first time

[1200] When users log in to the system for the first time, they must enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. They can enter their preferred genres, specific authors, or production companies. For example, a user might enter that they like "action" and "comedy," and that they particularly prefer works from "popular series."

[1201] 1.2 Data storage

[1202] The device temporarily stores the information entered by the user and then transmits it to the server. The transmitted data is encrypted and appropriate security measures are used to protect the user's privacy. The server stores the received data in a database and manages it by linking it to the user ID.

[1203] 2. Generating Recommendations

[1204] 2.1 Organization and analysis

[1205] The server uses the stored user profile information to generate appropriate content recommendations using a generative AI model that considers the user's preferences, past browsing history, and the latest trends to select the most suitable entertainment content. The AI ​​model used includes popular deep learning frameworks such as TensorFlow and PyTorch.

[1206] 2.2 Presenting Recommendations

[1207] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions.

[1208] 3. Providing additional information

[1209] 3.1 Requesting and Providing More Information

[1210] The user selects a work of interest from the displayed recommendation results and requests detailed information. The device then sends this request to the server. The server collects relevant detailed information and sends it to the device. The detailed information may include director's comments, interviews with the writers, behind-the-scenes information, etc. The device then visually displays this information to the user.

[1211] 4. Generating Hybrid Recommendations

[1212] 4.1 Hybridization

[1213] The server generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data, again using generative AI models.

[1214] 4.2 Presenting a new proposal

[1215] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from conventional ones.

[1216] Specific examples

[1217] A user accesses the system for the first time and enters that they like the "action" and "comedy" genres and have watched many "popular series." The device sends this information to the server, which stores it in a database. The system then uses a generative AI model to recommend "new action movies" and sends them to the device. When the user requests more information about a "new action movie" that interests them, the system provides detailed information, including director comments and interviews. The server also generates hybrid recommendations for new "action comedies" that combine different genres based on the user profile and sends them to the device. This allows users to discover new genres and styles.

[1218] Example prompt sentence:

[1219] "Using the profile information of user ID: '12345', please generate the best entertainment recommendations based on the following criteria: Favorite genres - 'action', 'comedy', viewing history - 'popular series'. Also, please provide hybrid recommendations that combine different genres."

[1220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1221] Step 1:

[1222] When a user logs in to the system for the first time, they enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. For example, the user may enter that they prefer "action" and "comedy" genres and that they like works from a particular production company. The input data is temporarily stored on the device.

[1223] Step 2:

[1224] The device encrypts the preferences and browsing history data entered by the user and sends it to the server. The server receives this data and stores it in a database. At this time, the information is managed consistently by associating it with the user ID as a key.

[1225] Step 3:

[1226] The server reads the user profile information stored in the database and generates content recommendations using a generative AI model. The user's profile information is provided as input to the AI ​​model, and suitable entertainment candidates are obtained as output. The generative AI model used includes deep learning frameworks such as TensorFlow and PyTorch. The model takes into account the user's preferences, past browsing history, and the latest trending information.

[1227] Step 4:

[1228] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions of each work.

[1229] Step 5:

[1230] The user selects an interesting work from the displayed recommendation results and requests its detailed information. The device sends this request to the server, providing the work ID as input and obtaining the related detailed information as output.

[1231] Step 6:

[1232] The server collects detailed information related to the specified work from external APIs and databases and sends it to the device. The detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The device visually displays this information to the user.

[1233] Step 7:

[1234] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. The generative AI model is used again, providing the user's profile information and past viewing data as input and obtaining works in new genres and styles as output.

[1235] Step 8:

[1236] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from the conventional ones. The user can further enhance their viewing experience by selecting content to watch from the new candidates and requesting more information again.

[1237] 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.

[1238] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[1239] 1. Collecting user profiles

[1240] 1.1 Entering information when logging in for the first time

[1241] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, they may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[1242] On your device: The information you enter is temporarily stored locally and then sent to a server. The data is encrypted to protect your privacy.

[1243] 2. Saving User Profile Information

[1244] 2.1 Saving Profile Data

[1245] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[1246] 3. Generating Recommendations

[1247] 3.1 Recommendation Algorithm Implementation

[1248] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[1249] 3.2 Presentation of recommendation results

[1250] Server: Sends the generated recommendation results to the device.

[1251] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[1252] 4. Providing additional information

[1253] 4.1 Requesting and Providing More Information

[1254] User: Select the title of interest from the displayed recommendations and request more information.

[1255] Terminal: Sends the request to the server.

[1256] Server: Retrieves detailed information related to a specified film from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[1257] Terminal: Visually displays the received details to the user.

[1258] 5. Generating Hybrid Recommendations

[1259] 5.1 Implementing the Hybrid Recommendation Algorithm

[1260] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data.

[1261] 5.2 Presenting a new proposal

[1262] Server: Sends the generated hybrid recommendation results to the device.

[1263] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[1264] 6. Leveraging Emotional Engines

[1265] 6.1 Initial setup and operation of the emotion engine

[1266] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects facial and voice data from the user through the camera and microphone.

[1267] Device: Analyzes collected facial and voice data in real time to identify the user's current emotions.

[1268] 6.2 Emotion Data Analysis and Storage

[1269] Server: Receives the emotion data sent from the device and stores it in a database along with the profile information, making it possible to understand the user's emotional tendencies over the long term.

[1270] 6.3 Adjusting Recommendations Based on Sentiment

[1271] Server: The generative AI model adjusts the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[1272] Specific examples

[1273] Here are some concrete examples:

[1274] 1. User: This is the first time the system is accessed and the user enters that they like action and comedy and have watched many Marvel movies. They also authorize the use of the emotion engine.

[1275] 2. Terminal: Sends input information and emotion engine settings to the server.

[1276] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[1277] 4. Device: Display the recommendation results to the user.

[1278] 5. User: Requests more information about "Action X" that interests them.

[1279] 6. Terminal: Sends the request to the server.

[1280] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[1281] 8. Terminal: Display detailed information to the user.

[1282] 9. Server: Based on the user profile and emotion data, generate a hybrid recommendation for a new movie, "Action Laughter," which combines different genres, and send it to the device.

[1283] 10. Terminal: Display the hybrid recommendation results to the user.

[1284] 11. Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[1285] 12. Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that is relaxing.

[1286] 13. Terminal: Displays the recommendations generated in real time to the user.

[1287] This allows users to find the entertainment content that best suits their preferences, deepening their understanding and attachment to the content through detailed information.In addition, the emotion engine provides personalized recommendations that reflect the user's emotional state, enabling a more fulfilling entertainment experience.

[1288] The processing flow will be explained below.

[1289] Collecting user profiles

[1290] Step 1:

[1291] User: When accessing the system for the first time, the user logs in. After that, the user enters their preferred genre (e.g., action, comedy), favorite writers and directors, and a list of works they have watched. The user also authorizes the use of the emotion engine.

[1292] Step 2:

[1293] Terminal: The entered information is temporarily stored locally and a confirmation screen is displayed, where the user can confirm and correct the entered information.

[1294] Step 3:

[1295] Terminal: The input information is sent to the server. The transmitted data is encrypted to protect privacy.

[1296] Storing user profile information

[1297] Step 4:

[1298] Server: Stores the profile information received from the device in a database. Manages the information by linking it to the user ID.

[1299] Generating recommendations

[1300] Step 5:

[1301] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[1302] Step 6:

[1303] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[1304] Step 7:

[1305] Server: Generates a list of selected works and sends it to the device.

[1306] Step 8:

[1307] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[1308] Providing additional information

[1309] Step 9:

[1310] User: Click on a recommendation that interests them and request more information.

[1311] Step 10:

[1312] Terminal: Sends the request to the server.

[1313] Step 11:

[1314] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[1315] Step 12:

[1316] Server: Sends the collected details to the device.

[1317] Step 13:

[1318] Terminal: Displays the received details to the user.

[1319] Generating Hybrid Recommendations

[1320] Step 14:

[1321] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[1322] Step 15:

[1323] Server: Sends the generated hybrid recommendation results to the device.

[1324] Step 16:

[1325] Terminal: Displays the received hybrid recommendation results to the user.

[1326] Utilizing the Emotion Engine

[1327] Step 17:

[1328] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice data in real time via the camera and microphone.

[1329] Step 18:

[1330] Device: Analyzes facial and voice data collected by the emotion engine to identify the user's current emotion. For example, if the user is smiling, it is determined to be "joy."

[1331] Step 19:

[1332] Device: Sends analyzed emotion data to the server.

[1333] Step 20:

[1334] Server: The received emotional data is stored in a database along with the user's profile information, allowing for a long-term understanding of the user's emotional tendencies.

[1335] Step 21:

[1336] Server: The generative AI model adjusts the recommendation results based on real-time emotional data. For example, if the user is feeling stressed, it will prioritize relaxing works.

[1337] Step 22:

[1338] Server: Sends the adjusted recommendation results to the device.

[1339] Step 23:

[1340] Device: Displays real-time generated recommendations to the user.

[1341] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, utilizing the emotion engine, and adjusting the recommendations in real time, allowing users to efficiently and effectively find the entertainment content that best suits them, deepen their understanding and attachment to the content through detailed information, and enjoy a personalized entertainment experience through the emotion engine.

[1342] Example 2

[1343] 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."

[1344] Conventional entertainment recommendation systems often make recommendations based on simple user preferences and past viewing history, and lack the ability to present personalized content that reflects the user's emotions and momentary mood. Furthermore, they are limited in their ability to suggest new content that combines different genres and styles, making it difficult for users to discover new content without becoming bored.

[1345] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input device for a user to input preferences and past browsing history, data storage means for saving the user's profile information, generation AI means for selecting works based on the profile information, a display device for presenting the selected works to the user, information provision means for collecting and presenting detailed information about the works, means for generating hybrid recommendations that combine different genres and styles, and emotion engine means for recognizing the user's emotions and adjusting the recommendations. This allows the user to receive personalized recommendations for entertainment works that reflect their own emotional state and also enables them to discover works in new genres and styles.

[1346] An "input device" is a device that allows a user to input their preferences and past browsing history into the system.

[1347] "Data Storage Means" means a storage device or storage means for storing user profile information.

[1348] The "generative AI means" refers to an artificial intelligence algorithm and its execution environment for selecting the most suitable entertainment works based on the user's profile information.

[1349] A "display device" is a device for visually presenting selected entertainment content to a user.

[1350] "Information providing means" refers to means for collecting detailed information about entertainment works and presenting it to users.

[1351] A "means for generating hybrid recommendations" is an algorithm and its execution environment for generating entertainment works that combine different genres and styles.

[1352] "Emotion engine means" refers to techniques and devices for recognizing a user's emotions and tailoring entertainment recommendations based thereon.

[1353] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[1354] Collecting user profiles

[1355] Entering information when logging in for the first time

[1356] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. For example, the user may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[1357] Terminal: The terminal temporarily stores the entered information locally, encrypts it (using AES, etc.), and sends it to the server.

[1358] Storing user profile information

[1359] Server: The server receives information about the user's preferences and browsing history from the device and stores it in a database (e.g., MySQL or PostgreSQL). The information is linked to the user ID and used for subsequent recommendation processing.

[1360] Generating recommendations

[1361] Running the recommendation algorithm

[1362] Server: The server runs a generative AI model (e.g., TensorFlow or PyTorch) based on the user profile stored in the database. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past viewing history, and the latest trend information. Specifically, it rates genres that users have watched most frequently and uses this to rank similar content.

[1363] Presenting recommendation results

[1364] Server: The server sends the generated recommendation results to the device. HTTPS is used for communication.

[1365] Device: The device displays the received recommendation results to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[1366] Providing additional information

[1367] Requesting and Providing More Information

[1368] User: The user selects the work of interest from the displayed recommendations and requests more information.

[1369] Terminal: The terminal sends the user's request to the server.

[1370] Server: The server retrieves details related to the specified film from a database or external sources (e.g., IMDb API), including director's comments, interviews, and behind-the-scenes information about the film.

[1371] Terminal: The terminal visually displays the received details to the user.

[1372] Generating Hybrid Recommendations

[1373] Running a hybrid recommendation algorithm

[1374] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data, using the COLAB (Collaborative Filtering) algorithm and Content-Based Filtering algorithm.

[1375] Presenting a new proposal

[1376] Server: The server sends the generated hybrid recommendation results to the terminal.

[1377] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover works in new genres and styles that they have never seen before.

[1378] Utilizing the Emotion Engine

[1379] Initial settings and operation of the emotion engine

[1380] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[1381] Device: The device analyzes the collected facial and voice data to determine the user's current emotion using technologies such as OpenCV and Google Cloud Speech-to-Text.

[1382] Emotion data analysis and storage

[1383] Server: The server receives the emotion data sent from the device and stores it in a database, which makes it possible to understand the user's emotional tendencies over the long term.

[1384] Tailoring recommendations based on sentiment

[1385] Server: The server uses a generative AI model to adjust the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[1386] Specific examples

[1387] User: This is the first time they access the system and they state that they like action and comedy and have watched a lot of Marvel movies. They also allow the use of the emotion engine.

[1388] Device: Sends input information and emotion engine settings to the server.

[1389] Server: Stores user profiles and uses generative AI models to create optimal recommendations, such as selecting "Action X" and sending them to the device.

[1390] Device: Display the recommendation results to the user.

[1391] User: Requests more information about "Action X" that interests them.

[1392] Terminal: Sends the request to the server.

[1393] Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[1394] Terminal: Display detailed information to the user.

[1395] Server: Based on the user profile and emotional data, generate a hybrid recommendation for the new movie "Action Laughter," which combines different genres, and send it to the device.

[1396] Device: Display hybrid recommendation results to the user.

[1397] Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[1398] Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that will help you relax.

[1399] Device: Displays real-time generated recommendations to the user.

[1400] Examples of prompt statements

[1401] 1. "Generate recommendations for users who like action movies."

[1402] 2. "Use the emotion engine to recommend relaxing movies to users who are feeling stressed."

[1403] 3. "Suggest a new genre of film that combines action and comedy."

[1404] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1405] Step 1: Collecting user profiles

[1406] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. Specifically, they enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies." The input is done through a form, in the form of text and multiple choice.

[1407] Terminal: The terminal temporarily stores the information entered by the user in local storage. The input data is structured in JSON format and then transferred to the server using AES encryption technology. Based on the input, the initial user profile data JSON is generated.

[1408] Step 2: Save user profile information

[1409] Server: The server receives the encrypted user profile data from the device. It decrypts the data and stores it in a database using a database management system (e.g., MySQL or PostgreSQL). During the storage process, it associates the information with the user ID and stores it, converting it from JSON to SQL format.

[1410] Step 3: Run the recommendation algorithm

[1411] Server: The server runs a generative AI model based on the user profile data stored in the database. The AI ​​model uses machine learning frameworks such as TensorFlow and PyTorch to select the most suitable entertainment content, taking into account the user's preferences, past viewing history, and the latest trend information. The input data is the user profile and viewing history data, and the output data is a recommendation list.

[1412] Step 4: Presenting the Recommendation Results

[1413] Server: The server sends the generated recommendation results to the device using the HTTPS protocol, and the recommendation data is structured in JSON format.

[1414] Device: The device interprets the received recommendations and displays them to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[1415] Step 5: Request and provide more information

[1416] User: The user selects an item they are interested in from the displayed recommendations and requests more information. For example, the user may request details about "Action X."

[1417] Terminal: The terminal sends the user's request to the server, which is structured in JSON and sent to the server using HTTPS.

[1418] Server: The server retrieves details related to the specified movie from a database or external source (e.g., IMDb API). These details may include director's comments, interviews, and behind-the-scenes information. The retrieved data is converted into JSON format and sent back to the device.

[1419] Terminal: The terminal visually displays the received details to the user in the form of text, images, or video.

[1420] Step 6: Running the hybrid recommendation algorithm

[1421] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data. The algorithm combines collaborative filtering and content-based filtering. The input data is the user profile and viewing history, and the output data is a hybrid recommendation list.

[1422] Step 7: Presenting a new proposal

[1423] Server: The server sends the generated hybrid recommendation results to the device. The data is in JSON format and is securely transmitted via HTTPS.

[1424] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover new genres and styles.

[1425] Step 8: Initial setup and operation of the emotion engine

[1426] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[1427] Device: The device analyzes the collected facial and voice data in real time using OpenCV and Google Cloud Speech-to-Text to identify the user's emotional state. The analysis results are converted into JSON format and sent to the server.

[1428] Step 9: Emotion Data Analysis and Storage

[1429] Server: The server receives the emotion data sent from the device and stores it in a database. This allows for a long-term understanding of the user's emotional trends. The stored data is used for subsequent analysis and recommendations.

[1430] Step 10: Adjusting recommendations based on sentiment

[1431] Server: The server uses a generative AI model to adjust recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works. The input data is real-time emotional data and profile data, and the output data is an adjusted recommendation list.

[1432] Terminal: The terminal displays the recommendations generated in real time to the user.

[1433] (Application example 2)

[1434] 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."

[1435] Conventional entertainment recommendation systems make recommendations based on a user's past viewing history or simple preferences. However, this alone makes it difficult to provide optimal recommendations that reflect the user's current emotional state, limiting the user experience. Furthermore, the provision of detailed information is limited, leaving users with few opportunities to gain a deeper understanding of the work's background and production process. This creates a problem that can easily lead to a decrease in satisfaction with the entertainment experience.

[1436] 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.

[1437] In this invention, the server includes a device for users to input their preferences and past browsing history, a database for storing user profile information, a generative AI model for selecting works based on the user profile information, a display for presenting the selected works to the user, a means for collecting and presenting detailed information about the works, a means for generating hybrid recommendations that combine different genres and styles, and an emotion engine for analyzing the user's emotions in real time and adjusting recommendations based on the user's emotional state. This makes it possible to provide personalized recommendations that reflect the user's emotional state in real time. Furthermore, comprehensive collection and presentation of detailed information can deepen the user's understanding and attachment to the works, improving the satisfaction of the entertainment experience.

[1438] "User" means an individual who utilizes the System to receive entertainment recommendations.

[1439] A "device" is a device through which a user inputs preferences and past browsing history.

[1440] "Database" means a storage area within the system for storing user profile information.

[1441] The "generative AI model means" is a function that executes an algorithm using generative AI to select works based on the user's profile information.

[1442] "Display means" refers to a display device for visually presenting the selected entertainment piece to the user.

[1443] The "means for collecting detailed information" is a function that collects detailed information about the presented work, such as comments and interviews with the creator, behind-the-scenes information, and provides it to the user.

[1444] "Means for generating hybrid recommendations" is a function that generates new recommendations by combining different genres and styles.

[1445] The "emotion engine means" is a function that analyzes the user's emotions in real time and adjusts recommendations based on the user's emotional state.

[1446] This invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves more accurate recommendations. Below, we will explain the system in detail from the perspectives of the server, the device, and the user.

[1447] The server first collects user information using a device that allows the user to input preferences and past browsing history, then stores the user profile information in a database. This device can be a smartphone or a personal computer. The stored information is encrypted to protect the user's privacy.

[1448] The device then analyzes the user's emotions in real time through the camera and microphone and sends the data to a server. This emotion engine is realized using software such as Facial Recognition SDK and Speech Analysis SDK. Once the emotion data is sent to the server, the server runs a generative AI model based on it to select the entertainment content that best suits the user's current emotional state.

[1449] The generated recommendations are presented to the user through the device's display. For example, if the user is feeling stressed, a relaxing comedy will be recommended first. If the user shows interest, the device requests detailed information, which is then retrieved and displayed from the server. The detailed information includes comments and interviews with the creators and behind-the-scenes information.

[1450] The system also has the ability to generate hybrid recommendations that combine different genres and styles based on user profiles and emotional data, allowing users to discover new genres and styles.

[1451] As a concrete example, a user registers with a smartphone app and inputs that they like "action" and "comedy" and have watched many "Marvel movies." They also authorize the use of an emotion engine. When the app is opened, the camera and microphone analyze the user's facial expressions and voice, and the current emotional state is determined to be "stressed." Based on this data, the server recommends relaxing comedy movies.

[1452] Example prompt sentence:

[1453] Show personalized entertainment based on the user's profile data and emotional information. If the user's current emotional state is stressful, prioritize recommendations for "relaxing content."

[1454] Genre: Action, Comedy

[1455] Movies I've seen: Marvel movies

[1456] Current emotional state: Stress

[1457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1458] Step 1:

[1459] When a user logs in for the first time, they enter their preferences and past browsing history and authorize the use of the emotion engine.

[1460] Input: The user enters information into the input form, such as action, comedy, Marvel movies, etc. Also, turns on permission to use the emotion engine.

[1461] Data processing: The device temporarily stores the entered data locally and encrypts it.

[1462] Output: The encrypted user data is sent to the server.

[1463] Step 2:

[1464] The server stores the received user profile information in a database.

[1465] Input: Encrypted user profile information sent from the device.

[1466] Data calculation: The encrypted data is decrypted, linked to the user ID, and stored in the database.

[1467] Output: A database entry containing the user's profile information.

[1468] Step 3:

[1469] The device analyzes the user's emotions in real time.

[1470] Input: User facial and voice data collected through the camera and microphone.

[1471] Data Computation: Analyze emotions using Facial Recognition SDK and Speech Analysis SDK to determine current emotional state.

[1472] Output: The parsed emotion data is generated.

[1473] Step 4:

[1474] The device transmits the analyzed emotion data to the server.

[1475] Input: Emotion data generated in the previous step.

[1476] Data calculation: The device encrypts the emotion data and sends it to the server.

[1477] Output: The encrypted emotion data is sent to the server.

[1478] Step 5:

[1479] The server runs a generative AI model based on the user profile and emotion data to generate recommendations.

[1480] Input: User profile information stored in a database and emotion data sent from the device.

[1481] Data calculation: The generative AI model takes into account the user's preferences and current emotional state, and uses AI algorithms to select the most suitable entertainment content.

[1482] Output: Recommendation results are generated.

[1483] Step 6:

[1484] The server sends the generated recommendations to the device.

[1485] Input: Recommendation results selected by the generative AI model.

[1486] Data calculation: Format the recommendation results and send them to the device.

[1487] Output: The formatted recommendation results are sent to the device.

[1488] Step 7:

[1489] The device displays the recommendation results to the user.

[1490] Input: The formatted recommendation results sent from the server.

[1491] Data Computation: Rendering the recommendation results for display in a format suitable for the user interface.

[1492] Output: A visual display that allows users to see the recommendation results.

[1493] Step 8:

[1494] The user is interested in the recommendations and requests more information.

[1495] Input: The user selects an item of interest from the recommendation results and requests more information.

[1496] Data Calculation: Formatting the request for sending to the server.

[1497] Output: The formatted request is sent to the server.

[1498] Step 9:

[1499] The server collects the details and sends them to the device.

[1500] Input: More information request sent from the terminal.

[1501] Data Calculation: Collecting information about the specified work from databases and external sources, formatting it, and sending it to the device.

[1502] Output: Formatted details are sent to the terminal.

[1503] Step 10:

[1504] The terminal displays the received detailed information to the user.

[1505] Input: The details sent by the server.

[1506] Data Calculation: Rendering detailed information for display in a format suitable for a user interface.

[1507] Output: A visual display that allows the user to see detailed information.

[1508] Step 11:

[1509] The server generates hybrid recommendations that combine different genres based on the user profile and emotional data, and sends them to the device.

[1510] Input: User profile information and emotion data.

[1511] Data calculation: The generative AI model generates hybrid recommendations that combine different genres and styles.

[1512] Output: The generated hybrid recommendation is sent to the device.

[1513] Step 12:

[1514] The terminal displays the hybrid recommendation results to the user.

[1515] Input: Hybrid recommendation results sent from the server.

[1516] Data Computation: Rendering the hybrid recommendation results for display in a format suitable for the user interface.

[1517] Output: A visual display that allows users to check the hybrid recommendation results.

[1518] Step 13:

[1519] The device analyzes the user's real-time emotional data, and the server readjusts the recommendations.

[1520] Input: Real-time user emotion data collected through camera and microphone.

[1521] Data calculation: The device analyzes the emotion data and sends the results to the server.

[1522] Output: Based on the analysis results, the server generates recommendations again and sends them to the device.

[1523] Through these steps, we can provide users with personalized entertainment recommendations, and improve the quality of the user experience by making recommendations that reflect the user's emotional state in real time.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] [Fourth embodiment]

[1528] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1529] 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.

[1530] 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).

[1531] 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.

[1532] 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.

[1533] 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).

[1534] 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.

[1535] 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.

[1536] 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.

[1537] 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.

[1538] 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.

[1539] 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.

[1540] 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."

[1541] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. The embodiments of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[1542] 1. Collecting user profiles

[1543] 1.1 Entering information when logging in for the first time

[1544] User: When logging into the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, if they like the "action" and "comedy" genres and have a preference for specific writers and directors, they enter that information.

[1545] On your device: The information you enter is temporarily stored and then sent to a server. The data is encrypted to protect your privacy.

[1546] 2. Saving User Profile Information

[1547] 2.1 Saving Profile Data

[1548] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[1549] 3. Generating Recommendations

[1550] 3.1 Recommendation Algorithm Implementation

[1551] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[1552] 3.2 Presentation of recommendation results

[1553] Server: Sends the generated recommendation results to the device.

[1554] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[1555] 4. Providing additional information

[1556] 4.1 Requesting and Providing More Information

[1557] User: Select the title of interest from the displayed recommendations and request more information.

[1558] Terminal: Sends the request to the server.

[1559] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[1560] Terminal: Visually displays the received details to the user.

[1561] 5. Generating Hybrid Recommendations

[1562] 5.1 Implementing the Hybrid Recommendation Algorithm

[1563] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits.

[1564] 5.2 Presenting a new proposal

[1565] Server: Sends the generated hybrid recommendation results to the device.

[1566] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[1567] Specific examples

[1568] Here are some concrete examples:

[1569] 1. User: This is the first time they visit the system and they state that they like action and comedy and have watched a lot of "Marvel movies."

[1570] 2. Terminal: Sends input information to the server.

[1571] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[1572] 4. Device: Display the recommendation results to the user.

[1573] 5. User: Requests more information about "Action X" that interests them.

[1574] 6. Terminal: Sends the request to the server.

[1575] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[1576] 8. Terminal: Display detailed information to the user.

[1577] 9. Server: Generates a hybrid recommendation of the new movie "Action Laughter" that combines different genres based on the user profile and sends it to the device.

[1578] 10. Terminal: Display the hybrid recommendation results to the user.

[1579] This allows users to find the entertainment that best suits their tastes, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[1580] The processing flow will be explained below.

[1581] I understand. The process steps are explained in detail below.

[1582] Collecting user profiles

[1583] Step 1:

[1584] User: Enter their preferences and past viewing history into a questionnaire-style input screen. For example, they may enter that they like movies in the "action" and "comedy" genres and that they have watched many "Marvel movies."

[1585] Step 2:

[1586] On the device: Temporarily store the information entered by the user locally and display a confirmation screen for the entered information.

[1587] Step 3:

[1588] Terminal: After the user confirms and corrects the input, the data is sent to the server. At this time, the data is encrypted before being transferred.

[1589] Storing user profile information

[1590] Step 4:

[1591] Server: Receives profile information sent from the device.

[1592] Step 5:

[1593] Server: The received profile information is stored in a database and managed in association with the user ID.

[1594] Generating recommendations

[1595] Step 6:

[1596] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[1597] Step 7:

[1598] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[1599] Step 8:

[1600] Server: Generates a list of selected works and sends it to the device.

[1601] Step 9:

[1602] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[1603] Providing additional information

[1604] Step 10:

[1605] User: Click on a recommendation that interests them and request more information.

[1606] Step 11:

[1607] Terminal: Sends the request to the server.

[1608] Step 12:

[1609] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[1610] Step 13:

[1611] Server: Sends the collected details to the device.

[1612] Step 14:

[1613] Terminal: Displays the received details to the user.

[1614] Generating Hybrid Recommendations

[1615] Step 15:

[1616] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[1617] Step 16:

[1618] Server: Sends the generated hybrid recommendation results to the device.

[1619] Step 17:

[1620] Terminal: Displays the received hybrid recommendation results to the user.

[1621] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, and generating hybrid recommendations, allowing users to efficiently and effectively find the entertainment content that best suits them, and deepening their understanding and attachment to the content through detailed information.

[1622] Example 1

[1623] 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."

[1624] Conventional entertainment recommendation systems only suggest a limited number of works based on a user's preferences and past viewing history, limiting the opportunities for users to be exposed to new genres and styles. Furthermore, there was a lack of a way for users to quickly obtain detailed information about works. This made it difficult for users to find entertainment works that matched their preferences, and to deepen their understanding and attachment to works.

[1625] 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.

[1626] In this invention, the server includes a terminal means for users to input their preferences and past browsing history, a server means for storing the user's profile information, and a generative AI model means for selecting entertainment works based on the profile information. This enables users to quickly find the entertainment works that best suit their preferences, and provides detailed work information and opportunities to experience new genres and styles.

[1627] "Terminal means" refers to a device through which a user inputs preferences and past browsing history.

[1628] "Server means" refers to a device or system for storing said user profile information.

[1629] "Generative AI model means" refers to an artificial intelligence model for selecting entertainment works based on the profile information.

[1630] "Display means" refers to a device or interface for presenting selected entertainment pieces to a user.

[1631] "Detailed information gathering means" refers to a device or system for gathering and presenting detailed information about said entertainment work.

[1632] "Means for generating hybrid recommendations" refers to a device or system for generating recommendations that combine different genres or styles.

[1633] The system of the present invention provides entertainment recommendations based on user input of preferences and past browsing history, and includes a terminal means, a server means, a generating AI model means, a display means, a detailed information collection means, and a means for generating hybrid recommendations.

[1634] 1. Collecting user profiles

[1635] 1.1 Entering information when logging in for the first time

[1636] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, say they like "action" and "comedy" and have watched many "Marvel movies." They enter this information and provide it to the system.

[1637] Terminal: The information entered by the user is temporarily stored in the terminal's memory. The stored information is then encrypted and sent to the server. This encryption process uses standard encryption techniques (e.g., AES-256).

[1638] 2. Saving User Profile Information

[1639] Server: Stores information received from the device about the user's preferences and past browsing history in a database. The information is managed by linking it to the user ID and used in subsequent processing. A general relational database (e.g., MySQL or PostgreSQL) can be used as the database.

[1640] 3. Generating Recommendations

[1641] Server: Launches the generative AI model based on the saved user profile. Prompts include the user's preferences, past browsing history, and the latest trending information. The AI ​​model uses this information to select the most suitable entertainment title. For example, for a user who likes "action" and "comedy," the AI ​​model might recommend "Action X."

[1642] Examples of prompts:

[1643] User Profile Data:

[1644] Favorite genres: Action, comedy

[1645] Viewing history: Many Marvel movies

[1646] Generate recommendations based on algorithms, taking into account the latest trends.

[1647] Server: Sends the generated recommendation results to the device.

[1648] On the device: The received recommendation results are displayed to the user in list and grid format, with thumbnail images and brief descriptions.

[1649] 4. Providing additional information

[1650] User: Selects an item from the recommendations that interests them and requests more information about it.

[1651] Terminal: Sends requests to the server.

[1652] Server: Collects and transmits detailed information related to the selected work to the device, including director's comments, writer interviews, behind-the-scenes information, etc.

[1653] Terminal: Visually displays the received details to the user.

[1654] 5. Generating Hybrid Recommendations

[1655] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy."

[1656] Server: Sends the generated hybrid recommendation results to the device.

[1657] Device: The received hybrid recommendation results are displayed to the user, allowing them to discover new genres and styles.

[1658] This allows users to quickly find the entertainment works that best suit their preferences, deepen their understanding and attachment to the works through detailed information, and discover new genres and styles.

[1659] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1660] Step 1:

[1661] When a user logs in for the first time, they enter their preferences and past browsing history through the application or web interface. Specifically, the user enters that they like "action" and "comedy" and have watched many "Marvel movies." The entered data is temporarily stored on the device as the user's profile information.

[1662] Step 2:

[1663] The device encrypts the stored user profile information and sends it to the server. This encryption process uses, for example, AES-256. The server decodes the received information and stores it in a database along with the user ID. The input data is the user's preferences and past browsing history, and the output data is the user profile information stored in the database.

[1664] Step 3:

[1665] The server launches a generative AI model based on the stored user profile information. The AI ​​model runs an algorithm to recommend the most suitable entertainment titles, taking into account the user's preferences, past browsing history, and the latest trend information. The input data is the user profile information and the latest trend information, and the output data is the recommendation results. An example of a prompt is as follows:

[1666] User Profile Data:

[1667] Favorite genres: Action, comedy

[1668] Viewing history: Many Marvel movies

[1669] Generate recommendations based on algorithms, taking into account the latest trends.

[1670] Step 4:

[1671] The server sends the generated recommendation results to the terminal. The input data is the recommendation results, and the output data is the data sent to the terminal.

[1672] Step 5:

[1673] The terminal visually displays the received recommendation results to the user in a list or grid format, including thumbnail images and brief descriptions. The input data are the recommendation results received from the server, and the output data are the recommendation results displayed to the user.

[1674] Step 6:

[1675] The user selects an item of interest from the displayed recommendation results and requests detailed information about it. The input data is the item selected by the user, and the output data is a request for detailed information.

[1676] Step 7:

[1677] The terminal sends the user's request to the server, where the input data is the user's request and the output data is the request sent to the server.

[1678] Step 8:

[1679] In response to the request, the server collects detailed information related to the specified work and sends it to the terminal. The collected detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The input data is the work information related to the user's request, and the output data is the detailed information sent to the terminal.

[1680] Step 9:

[1681] The terminal visually displays the received detailed information to the user, with the input data being the detailed information received from the server and the output data being the detailed information displayed to the user.

[1682] Step 10:

[1683] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. For example, it generates a new title, "Action Laughter," that combines elements of "action" and "comedy." The input data is the user profile and viewing habits, and the output data is the hybrid recommendation results.

[1684] Step 11:

[1685] The server sends the generated hybrid recommendation result to the terminal, where the input data is the hybrid recommendation result and the output data is the data sent to the terminal.

[1686] Step 12:

[1687] The terminal displays the received hybrid recommendation results to the user, allowing the user to experience new genres and styles. The input data is the hybrid recommendation results received from the server, and the output data is the results displayed to the user.

[1688] (Application example 1)

[1689] 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."

[1690] Conventional content distribution services lack personalized recommendation systems based on user preferences and past browsing history, making it difficult for users to efficiently find the content they really want to watch. Furthermore, they lack innovative recommendations that combine different genres and the ability to provide detailed background information, limiting the user experience.

[1691] 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.

[1692] In this invention, the server includes a device for users to input their preferences and past browsing history, a database that stores the user's profile information, a generative AI model means that selects works based on the profile information, a display means that presents the selected works to the user, a means that collects and presents detailed information about the works, a means that generates hybrid recommendations that combine different genres and styles, and a content distribution service application means that is installed on the smartphone. This enables highly accurate recommendations based on the user's preferences and past browsing history, as well as new proposals that combine detailed work information and different genres.

[1693] The "device for a user to input preferences and past viewing history" is a terminal for a user to input his or her own viewing preferences and a history of content that has been viewed in the past.

[1694] The "database that stores the user's profile information" is a database system that organizes and stores the viewing preferences and past history information entered by the user.

[1695] The "generative AI model means for selecting works based on the profile information" refers to an artificial intelligence model that uses the saved user profile information to select the most suitable content.

[1696] "Display means for presenting selected works to a user" means a device or screen for visually displaying to a user the content selected by the generative AI model.

[1697] The "means for collecting and presenting detailed information about the work" is a function for collecting detailed information about the content that the user wishes to view, such as background information, comments and interviews from the creator, and displaying this information to the user.

[1698] "Means for generating hybrid recommendations that combine different genres and styles" is a mechanism for generating novel content recommendations that combine different genres and styles based on user profile information.

[1699] The "content distribution service application means installed on a smartphone" is an application that runs on a smartphone and distributes and recommends content to users.

[1700] The present invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Hereinafter, specific embodiments of the present invention will be described.

[1701] 1. Collecting user profiles

[1702] 1.1 Entering information when logging in for the first time

[1703] When users log in to the system for the first time, they must enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. They can enter their preferred genres, specific authors, or production companies. For example, a user might enter that they like "action" and "comedy," and that they particularly prefer works from "popular series."

[1704] 1.2 Data storage

[1705] The device temporarily stores the information entered by the user and then transmits it to the server. The transmitted data is encrypted and appropriate security measures are used to protect the user's privacy. The server stores the received data in a database and manages it by linking it to the user ID.

[1706] 2. Generating Recommendations

[1707] 2.1 Organization and analysis

[1708] The server uses the stored user profile information to generate appropriate content recommendations using a generative AI model that considers the user's preferences, past browsing history, and the latest trends to select the most suitable entertainment content. The AI ​​model used includes popular deep learning frameworks such as TensorFlow and PyTorch.

[1709] 2.2 Presenting Recommendations

[1710] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions.

[1711] 3. Providing additional information

[1712] 3.1 Requesting and Providing More Information

[1713] The user selects a work of interest from the displayed recommendation results and requests detailed information. The device then sends this request to the server. The server collects relevant detailed information and sends it to the device. The detailed information may include director's comments, interviews with the writers, behind-the-scenes information, etc. The device then visually displays this information to the user.

[1714] 4. Generating Hybrid Recommendations

[1715] 4.1 Hybridization

[1716] The server generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data, again using generative AI models.

[1717] 4.2 Presenting a new proposal

[1718] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from conventional ones.

[1719] Specific examples

[1720] A user accesses the system for the first time and enters that they like the "action" and "comedy" genres and have watched many "popular series." The device sends this information to the server, which stores it in a database. The system then uses a generative AI model to recommend "new action movies" and sends them to the device. When the user requests more information about a "new action movie" that interests them, the system provides detailed information, including director comments and interviews. The server also generates hybrid recommendations for new "action comedies" that combine different genres based on the user profile and sends them to the device. This allows users to discover new genres and styles.

[1721] Example prompt sentence:

[1722] "Using the profile information of user ID: '12345', please generate the best entertainment recommendations based on the following criteria: Favorite genres - 'action', 'comedy', viewing history - 'popular series'. Also, please provide hybrid recommendations that combine different genres."

[1723] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1724] Step 1:

[1725] When a user logs in to the system for the first time, they enter their viewing preferences and past viewing history. This is done through a content distribution service application installed on their smartphone. For example, the user may enter that they prefer "action" and "comedy" genres and that they like works from a particular production company. The input data is temporarily stored on the device.

[1726] Step 2:

[1727] The device encrypts the preferences and browsing history data entered by the user and sends it to the server. The server receives this data and stores it in a database. At this time, the information is managed consistently by associating it with the user ID as a key.

[1728] Step 3:

[1729] The server reads the user profile information stored in the database and generates content recommendations using a generative AI model. The user's profile information is provided as input to the AI ​​model, and suitable entertainment candidates are obtained as output. The generative AI model used includes deep learning frameworks such as TensorFlow and PyTorch. The model takes into account the user's preferences, past browsing history, and the latest trending information.

[1730] Step 4:

[1731] The server sends the generated recommendation results to the device, which displays them to the user in a list or grid format, including thumbnail images and brief descriptions of each work.

[1732] Step 5:

[1733] The user selects an interesting work from the displayed recommendation results and requests its detailed information. The device sends this request to the server, providing the work ID as input and obtaining the related detailed information as output.

[1734] Step 6:

[1735] The server collects detailed information related to the specified work from external APIs and databases and sends it to the device. The detailed information includes director's comments, writer's interviews, behind-the-scenes information, etc. The device visually displays this information to the user.

[1736] Step 7:

[1737] The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing habits. The generative AI model is used again, providing the user's profile information and past viewing data as input and obtaining works in new genres and styles as output.

[1738] Step 8:

[1739] The server sends the generated hybrid recommendation results to the device, which displays them to the user, providing an opportunity to experience new genres and styles that are different from the conventional ones. The user can further enhance their viewing experience by selecting content to watch from the new candidates and requesting more information again.

[1740] 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.

[1741] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[1742] 1. Collecting user profiles

[1743] 1.1 Entering information when logging in for the first time

[1744] User: When logging in to the system for the first time, the user enters their preferences and past browsing history through the application or web interface. For example, they may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[1745] On your device: The information you enter is temporarily stored locally and then sent to a server. The data is encrypted to protect your privacy.

[1746] 2. Saving User Profile Information

[1747] 2.1 Saving Profile Data

[1748] Server: Stores information received from the device about the user's preferences and past browsing history in a database. This information is linked to the user ID and managed for subsequent processing.

[1749] 3. Generating Recommendations

[1750] 3.1 Recommendation Algorithm Implementation

[1751] Server: Runs a generative AI model based on the stored user profile. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past browsing history, and the latest trends.

[1752] 3.2 Presentation of recommendation results

[1753] Server: Sends the generated recommendation results to the device.

[1754] On the device: The received recommendation results are displayed to the user in a list or grid format, including thumbnail images and brief descriptions.

[1755] 4. Providing additional information

[1756] 4.1 Requesting and Providing More Information

[1757] User: Select the title of interest from the displayed recommendations and request more information.

[1758] Terminal: Sends the request to the server.

[1759] Server: Retrieves detailed information related to a specified film from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[1760] Terminal: Visually displays the received details to the user.

[1761] 5. Generating Hybrid Recommendations

[1762] 5.1 Implementing the Hybrid Recommendation Algorithm

[1763] Server: Generates hybrid recommendations that combine different genres and styles based on user profiles and past viewing data.

[1764] 5.2 Presenting a new proposal

[1765] Server: Sends the generated hybrid recommendation results to the device.

[1766] Device: The received hybrid recommendation results are displayed to the user, allowing the user to discover new genres and styles that they have never seen before.

[1767] 6. Leveraging Emotional Engines

[1768] 6.1 Initial setup and operation of the emotion engine

[1769] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects facial and voice data from the user through the camera and microphone.

[1770] Device: Analyzes collected facial and voice data in real time to identify the user's current emotions.

[1771] 6.2 Emotion Data Analysis and Storage

[1772] Server: Receives the emotion data sent from the device and stores it in a database along with the profile information, making it possible to understand the user's emotional tendencies over the long term.

[1773] 6.3 Adjusting Recommendations Based on Sentiment

[1774] Server: The generative AI model adjusts the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[1775] Specific examples

[1776] Here are some concrete examples:

[1777] 1. User: This is the first time the system is accessed and the user enters that they like action and comedy and have watched many Marvel movies. They also authorize the use of the emotion engine.

[1778] 2. Terminal: Sends input information and emotion engine settings to the server.

[1779] 3. Server: Stores user profiles and uses generative AI models to create optimal recommendations. Recommendations such as "Action X" are selected and sent to the device.

[1780] 4. Device: Display the recommendation results to the user.

[1781] 5. User: Requests more information about "Action X" that interests them.

[1782] 6. Terminal: Sends the request to the server.

[1783] 7. Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[1784] 8. Terminal: Display detailed information to the user.

[1785] 9. Server: Based on the user profile and emotion data, generate a hybrid recommendation for a new movie, "Action Laughter," which combines different genres, and send it to the device.

[1786] 10. Terminal: Display the hybrid recommendation results to the user.

[1787] 11. Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[1788] 12. Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that is relaxing.

[1789] 13. Terminal: Displays the recommendations generated in real time to the user.

[1790] This allows users to find the entertainment content that best suits their preferences, deepening their understanding and attachment to the content through detailed information.In addition, the emotion engine provides personalized recommendations that reflect the user's emotional state, enabling a more fulfilling entertainment experience.

[1791] The processing flow will be explained below.

[1792] Collecting user profiles

[1793] Step 1:

[1794] User: When accessing the system for the first time, the user logs in. After that, the user enters their preferred genre (e.g., action, comedy), favorite writers and directors, and a list of works they have watched. The user also authorizes the use of the emotion engine.

[1795] Step 2:

[1796] Terminal: The entered information is temporarily stored locally and a confirmation screen is displayed, where the user can confirm and correct the entered information.

[1797] Step 3:

[1798] Terminal: The input information is sent to the server. The transmitted data is encrypted to protect privacy.

[1799] Storing user profile information

[1800] Step 4:

[1801] Server: Stores the profile information received from the device in a database. Manages the information by linking it to the user ID.

[1802] Generating recommendations

[1803] Step 5:

[1804] Server: When the user accesses the system again, the profile information is retrieved from the database based on the user ID.

[1805] Step 6:

[1806] Server: Runs a generative AI model based on profile information to select entertainment that matches the user's preferences.

[1807] Step 7:

[1808] Server: Generates a list of selected works and sends it to the device.

[1809] Step 8:

[1810] Terminal: Displays the list of received works to the user in a list format with thumbnail images or in a grid format.

[1811] Providing additional information

[1812] Step 9:

[1813] User: Click on a recommendation that interests them and request more information.

[1814] Step 10:

[1815] Terminal: Sends the request to the server.

[1816] Step 11:

[1817] Server: Receives requests and retrieves details related to the specified production from databases and external sources, including director's comments, interviews, and behind-the-scenes information.

[1818] Step 12:

[1819] Server: Sends the collected details to the device.

[1820] Step 13:

[1821] Terminal: Displays the received details to the user.

[1822] Generating Hybrid Recommendations

[1823] Step 14:

[1824] Server: Runs AI algorithms that combine different genres and styles based on user profiles and past viewing data.

[1825] Step 15:

[1826] Server: Sends the generated hybrid recommendation results to the device.

[1827] Step 16:

[1828] Terminal: Displays the received hybrid recommendation results to the user.

[1829] Utilizing the Emotion Engine

[1830] Step 17:

[1831] User: Allow the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice data in real time via the camera and microphone.

[1832] Step 18:

[1833] Device: Analyzes facial and voice data collected by the emotion engine to identify the user's current emotion. For example, if the user is smiling, it is determined to be "joy."

[1834] Step 19:

[1835] Device: Sends analyzed emotion data to the server.

[1836] Step 20:

[1837] Server: The received emotional data is stored in a database along with the user's profile information, allowing for a long-term understanding of the user's emotional tendencies.

[1838] Step 21:

[1839] Server: The generative AI model adjusts the recommendation results based on real-time emotional data. For example, if the user is feeling stressed, it will prioritize relaxing works.

[1840] Step 22:

[1841] Server: Sends the adjusted recommendation results to the device.

[1842] Step 23:

[1843] Device: Displays real-time generated recommendations to the user.

[1844] These are the specific processing steps from collecting user profiles to generating recommendations, providing detailed information, utilizing the emotion engine, and adjusting the recommendations in real time, allowing users to efficiently and effectively find the entertainment content that best suits them, deepen their understanding and attachment to the content through detailed information, and enjoy a personalized entertainment experience through the emotion engine.

[1845] Example 2

[1846] 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."

[1847] Conventional entertainment recommendation systems often make recommendations based on simple user preferences and past viewing history, and lack the ability to present personalized content that reflects the user's emotions and momentary mood. Furthermore, they are limited in their ability to suggest new content that combines different genres and styles, making it difficult for users to discover new content without becoming bored.

[1848] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input device for a user to input preferences and past browsing history, data storage means for saving the user's profile information, generation AI means for selecting works based on the profile information, a display device for presenting the selected works to the user, information provision means for collecting and presenting detailed information about the works, means for generating hybrid recommendations that combine different genres and styles, and emotion engine means for recognizing the user's emotions and adjusting the recommendations. This allows the user to receive personalized recommendations for entertainment works that reflect their own emotional state and also enables them to discover works in new genres and styles.

[1849] An "input device" is a device that allows a user to input their preferences and past browsing history into the system.

[1850] "Data Storage Means" means a storage device or storage means for storing user profile information.

[1851] The "generative AI means" refers to an artificial intelligence algorithm and its execution environment for selecting the most suitable entertainment works based on the user's profile information.

[1852] A "display device" is a device for visually presenting selected entertainment content to a user.

[1853] "Information providing means" refers to means for collecting detailed information about entertainment works and presenting it to users.

[1854] A "means for generating hybrid recommendations" is an algorithm and its execution environment for generating entertainment works that combine different genres and styles.

[1855] "Emotion engine means" refers to techniques and devices for recognizing a user's emotions and tailoring entertainment recommendations based thereon.

[1856] The present invention is a system that combines user profile data and generative AI technology to provide users with personalized entertainment recommendations. Furthermore, by combining it with an emotion engine that recognizes user emotions, more accurate recommendations can be achieved. An embodiment of the present invention will be specifically described from the perspectives of a server, a terminal, and a user.

[1857] Collecting user profiles

[1858] Entering information when logging in for the first time

[1859] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. For example, the user may enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies."

[1860] Terminal: The terminal temporarily stores the entered information locally, encrypts it (using AES, etc.), and sends it to the server.

[1861] Storing user profile information

[1862] Server: The server receives information about the user's preferences and browsing history from the device and stores it in a database (e.g., MySQL or PostgreSQL). The information is linked to the user ID and used for subsequent recommendation processing.

[1863] Generating recommendations

[1864] Running the recommendation algorithm

[1865] Server: The server runs a generative AI model (e.g., TensorFlow or PyTorch) based on the user profile stored in the database. The AI ​​model selects the most suitable entertainment content based on the user's preferences, past viewing history, and the latest trend information. Specifically, it rates genres that users have watched most frequently and uses this to rank similar content.

[1866] Presenting recommendation results

[1867] Server: The server sends the generated recommendation results to the device. HTTPS is used for communication.

[1868] Device: The device displays the received recommendation results to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[1869] Providing additional information

[1870] Requesting and Providing More Information

[1871] User: The user selects the work of interest from the displayed recommendations and requests more information.

[1872] Terminal: The terminal sends the user's request to the server.

[1873] Server: The server retrieves details related to the specified film from a database or external sources (e.g., IMDb API), including director's comments, interviews, and behind-the-scenes information about the film.

[1874] Terminal: The terminal visually displays the received details to the user.

[1875] Generating Hybrid Recommendations

[1876] Running a hybrid recommendation algorithm

[1877] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data, using the COLAB (Collaborative Filtering) algorithm and Content-Based Filtering algorithm.

[1878] Presenting a new proposal

[1879] Server: The server sends the generated hybrid recommendation results to the terminal.

[1880] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover works in new genres and styles that they have never seen before.

[1881] Utilizing the Emotion Engine

[1882] Initial settings and operation of the emotion engine

[1883] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[1884] Device: The device analyzes the collected facial and voice data to determine the user's current emotion using technologies such as OpenCV and Google Cloud Speech-to-Text.

[1885] Emotion data analysis and storage

[1886] Server: The server receives the emotion data sent from the device and stores it in a database, which makes it possible to understand the user's emotional tendencies over the long term.

[1887] Tailoring recommendations based on sentiment

[1888] Server: The server uses a generative AI model to adjust the recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works.

[1889] Specific examples

[1890] User: This is the first time they access the system and they state that they like action and comedy and have watched a lot of Marvel movies. They also allow the use of the emotion engine.

[1891] Device: Sends input information and emotion engine settings to the server.

[1892] Server: Stores user profiles and uses generative AI models to create optimal recommendations, such as selecting "Action X" and sending them to the device.

[1893] Device: Display the recommendation results to the user.

[1894] User: Requests more information about "Action X" that interests them.

[1895] Terminal: Sends the request to the server.

[1896] Server: Collects detailed information and sends it to the device, including the director's comments and interviews.

[1897] Terminal: Display detailed information to the user.

[1898] Server: Based on the user profile and emotional data, generate a hybrid recommendation for the new movie "Action Laughter," which combines different genres, and send it to the device.

[1899] Device: Display hybrid recommendation results to the user.

[1900] Device: The user's facial expression data is analyzed in real time, and the emotion engine detects stress levels.

[1901] Server: Generate new recommendations that reflect the stress state and select "Comedy Y" that will help you relax.

[1902] Device: Displays real-time generated recommendations to the user.

[1903] Examples of prompt statements

[1904] 1. "Generate recommendations for users who like action movies."

[1905] 2. "Use the emotion engine to recommend relaxing movies to users who are feeling stressed."

[1906] 3. "Suggest a new genre of film that combines action and comedy."

[1907] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1908] Step 1: Collecting user profiles

[1909] User: When a user logs into the system for the first time, they use the application or web interface to enter their preferences and past browsing history. Specifically, they enter that they like the "action" and "comedy" genres and that they have watched a lot of "Marvel movies." The input is done through a form, in the form of text and multiple choice.

[1910] Terminal: The terminal temporarily stores the information entered by the user in local storage. The input data is structured in JSON format and then transferred to the server using AES encryption technology. Based on the input, the initial user profile data JSON is generated.

[1911] Step 2: Save user profile information

[1912] Server: The server receives the encrypted user profile data from the device. It decrypts the data and stores it in a database using a database management system (e.g., MySQL or PostgreSQL). During the storage process, it associates the information with the user ID and stores it, converting it from JSON to SQL format.

[1913] Step 3: Run the recommendation algorithm

[1914] Server: The server runs a generative AI model based on the user profile data stored in the database. The AI ​​model uses machine learning frameworks such as TensorFlow and PyTorch to select the most suitable entertainment content, taking into account the user's preferences, past viewing history, and the latest trend information. The input data is the user profile and viewing history data, and the output data is a recommendation list.

[1915] Step 4: Presenting the Recommendation Results

[1916] Server: The server sends the generated recommendation results to the device using the HTTPS protocol, and the recommendation data is structured in JSON format.

[1917] Device: The device interprets the received recommendations and displays them to the user in a list or grid format, including thumbnail images of the works and brief descriptions.

[1918] Step 5: Request and provide more information

[1919] User: The user selects an item they are interested in from the displayed recommendations and requests more information. For example, the user may request details about "Action X."

[1920] Terminal: The terminal sends the user's request to the server, which is structured in JSON and sent to the server using HTTPS.

[1921] Server: The server retrieves details related to the specified movie from a database or external source (e.g., IMDb API). These details may include director's comments, interviews, and behind-the-scenes information. The retrieved data is converted into JSON format and sent back to the device.

[1922] Terminal: The terminal visually displays the received details to the user in the form of text, images, or video.

[1923] Step 6: Running the hybrid recommendation algorithm

[1924] Server: The server generates hybrid recommendations that combine different genres and styles based on the user profile and past viewing data. The algorithm combines collaborative filtering and content-based filtering. The input data is the user profile and viewing history, and the output data is a hybrid recommendation list.

[1925] Step 7: Presenting a new proposal

[1926] Server: The server sends the generated hybrid recommendation results to the device. The data is in JSON format and is securely transmitted via HTTPS.

[1927] Device: The device displays the hybrid recommendation results to the user, allowing the user to discover new genres and styles.

[1928] Step 8: Initial setup and operation of the emotion engine

[1929] User: The user allows the use of the emotion engine in the application settings screen. The emotion engine collects the user's facial expressions and voice in real time through the camera and microphone.

[1930] Device: The device analyzes the collected facial and voice data in real time using OpenCV and Google Cloud Speech-to-Text to identify the user's emotional state. The analysis results are converted into JSON format and sent to the server.

[1931] Step 9: Emotion Data Analysis and Storage

[1932] Server: The server receives the emotion data sent from the device and stores it in a database. This allows for a long-term understanding of the user's emotional trends. The stored data is used for subsequent analysis and recommendations.

[1933] Step 10: Adjusting recommendations based on sentiment

[1934] Server: The server uses a generative AI model to adjust recommendation results based on the user's real-time emotional data. For example, if the user is feeling stressed, it will prioritize recommendations for relaxing works. The input data is real-time emotional data and profile data, and the output data is an adjusted recommendation list.

[1935] Terminal: The terminal displays the recommendations generated in real time to the user.

[1936] (Application example 2)

[1937] 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 robot 414 will be referred to as a "terminal."

[1938] Conventional entertainment recommendation systems make recommendations based on a user's past viewing history or simple preferences. However, this alone makes it difficult to provide optimal recommendations that reflect the user's current emotional state, limiting the user experience. Furthermore, the provision of detailed information is limited, leaving users with few opportunities to gain a deeper understanding of the work's background and production process. This creates a problem that can easily lead to a decrease in satisfaction with the entertainment experience.

[1939] 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.

[1940] In this invention, the server includes a device for users to input their preferences and past browsing history, a database for storing user profile information, a generative AI model for selecting works based on the user profile information, a display for presenting the selected works to the user, a means for collecting and presenting detailed information about the works, a means for generating hybrid recommendations that combine different genres and styles, and an emotion engine for analyzing the user's emotions in real time and adjusting recommendations based on the user's emotional state. This makes it possible to provide personalized recommendations that reflect the user's emotional state in real time. Furthermore, comprehensive collection and presentation of detailed information can deepen the user's understanding and attachment to the works, improving the satisfaction of the entertainment experience.

[1941] "User" means an individual who utilizes the System to receive entertainment recommendations.

[1942] A "device" is a device through which a user inputs preferences and past browsing history.

[1943] "Database" means a storage area within the system for storing user profile information.

[1944] The "generative AI model means" is a function that executes an algorithm using generative AI to select works based on the user's profile information.

[1945] "Display means" refers to a display device for visually presenting the selected entertainment piece to the user.

[1946] The "means for collecting detailed information" is a function that collects detailed information about the presented work, such as comments and interviews with the creator, behind-the-scenes information, and provides it to the user.

[1947] "Means for generating hybrid recommendations" is a function that generates new recommendations by combining different genres and styles.

[1948] The "emotion engine means" is a function that analyzes the user's emotions in real time and adjusts recommendations based on the user's emotional state.

[1949] This invention is a system that combines user profile data and generative AI technology to provide personalized entertainment recommendations to users. Furthermore, by combining it with an emotion engine that recognizes user emotions, it achieves more accurate recommendations. Below, we will explain the system in detail from the perspectives of the server, the device, and the user.

[1950] The server first collects user information using a device that allows the user to input preferences and past browsing history, then stores the user profile information in a database. This device can be a smartphone or a personal computer. The stored information is encrypted to protect the user's privacy.

[1951] The device then analyzes the user's emotions in real time through the camera and microphone and sends the data to a server. This emotion engine is realized using software such as Facial Recognition SDK and Speech Analysis SDK. Once the emotion data is sent to the server, the server runs a generative AI model based on it to select the entertainment content that best suits the user's current emotional state.

[1952] The generated recommendations are presented to the user through the device's display. For example, if the user is feeling stressed, a relaxing comedy will be recommended first. If the user shows interest, the device requests detailed information, which is then retrieved and displayed from the server. The detailed information includes comments and interviews with the creators and behind-the-scenes information.

[1953] The system also has the ability to generate hybrid recommendations that combine different genres and styles based on user profiles and emotional data, allowing users to discover new genres and styles.

[1954] As a concrete example, a user registers with a smartphone app and inputs that they like "action" and "comedy" and have watched many "Marvel movies." They also authorize the use of an emotion engine. When the app is opened, the camera and microphone analyze the user's facial expressions and voice, and the current emotional state is determined to be "stressed." Based on this data, the server recommends relaxing comedy movies.

[1955] Example prompt sentence:

[1956] Show personalized entertainment based on the user's profile data and emotional information. If the user's current emotional state is stressful, prioritize recommendations for "relaxing content."

[1957] Genre: Action, Comedy

[1958] Movies I've seen: Marvel movies

[1959] Current emotional state: Stress

[1960] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1961] Step 1:

[1962] When a user logs in for the first time, they enter their preferences and past browsing history and authorize the use of the emotion engine.

[1963] Input: The user enters information into the input form, such as action, comedy, Marvel movies, etc. Also, turns on permission to use the emotion engine.

[1964] Data processing: The device temporarily stores the entered data locally and encrypts it.

[1965] Output: The encrypted user data is sent to the server.

[1966] Step 2:

[1967] The server stores the received user profile information in a database.

[1968] Input: Encrypted user profile information sent from the device.

[1969] Data calculation: The encrypted data is decrypted, linked to the user ID, and stored in the database.

[1970] Output: A database entry containing the user's profile information.

[1971] Step 3:

[1972] The device analyzes the user's emotions in real time.

[1973] Input: User facial and voice data collected through the camera and microphone.

[1974] Data Computation: Analyze emotions using Facial Recognition SDK and Speech Analysis SDK to determine current emotional state.

[1975] Output: The parsed emotion data is generated.

[1976] Step 4:

[1977] The device transmits the analyzed emotion data to the server.

[1978] Input: Emotion data generated in the previous step.

[1979] Data calculation: The device encrypts the emotion data and sends it to the server.

[1980] Output: The encrypted emotion data is sent to the server.

[1981] Step 5:

[1982] The server runs a generative AI model based on the user profile and emotion data to generate recommendations.

[1983] Input: User profile information stored in a database and emotion data sent from the device.

[1984] Data calculation: The generative AI model takes into account the user's preferences and current emotional state, and uses AI algorithms to select the most suitable entertainment content.

[1985] Output: Recommendation results are generated.

[1986] Step 6:

[1987] The server sends the generated recommendations to the device.

[1988] Input: Recommendation results selected by the generative AI model.

[1989] Data calculation: Format the recommendation results and send them to the device.

[1990] Output: The formatted recommendation results are sent to the device.

[1991] Step 7:

[1992] The device displays the recommendation results to the user.

[1993] Input: The formatted recommendation results sent from the server.

[1994] Data Computation: Rendering the recommendation results for display in a format suitable for the user interface.

[1995] Output: A visual display that allows users to see the recommendation results.

[1996] Step 8:

[1997] The user is interested in the recommendations and requests more information.

[1998] Input: The user selects an item of interest from the recommendation results and requests more information.

[1999] Data Calculation: Formatting the request for sending to the server.

[2000] Output: The formatted request is sent to the server.

[2001] Step 9:

[2002] The server collects the details and sends them to the device.

[2003] Input: More information request sent from the terminal.

[2004] Data Calculation: Collecting information about the specified work from databases and external sources, formatting it, and sending it to the device.

[2005] Output: Formatted details are sent to the terminal.

[2006] Step 10:

[2007] The terminal displays the received detailed information to the user.

[2008] Input: The details sent by the server.

[2009] Data Calculation: Rendering detailed information for display in a format suitable for a user interface.

[2010] Output: A visual display that allows the user to see detailed information.

[2011] Step 11:

[2012] The server generates hybrid recommendations that combine different genres based on the user profile and emotional data, and sends them to the device.

[2013] Input: User profile information and emotion data.

[2014] Data calculation: The generative AI model generates hybrid recommendations that combine different genres and styles.

[2015] Output: The generated hybrid recommendation is sent to the device.

[2016] Step 12:

[2017] The terminal displays the hybrid recommendation results to the user.

[2018] Input: Hybrid recommendation results sent from the server.

[2019] Data Computation: Rendering the hybrid recommendation results for display in a format suitable for the user interface.

[2020] Output: A visual display that allows users to check the hybrid recommendation results.

[2021] Step 13:

[2022] The device analyzes the user's real-time emotional data, and the server readjusts the recommendations.

[2023] Input: Real-time user emotion data collected through camera and microphone.

[2024] Data calculation: The device analyzes the emotion data and sends the results to the server.

[2025] Output: Based on the analysis results, the server generates recommendations again and sends them to the device.

[2026] Through these steps, we can provide users with personalized entertainment recommendations, and improve the quality of the user experience by making recommendations that reflect the user's emotional state in real time.

[2027] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2028] 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.

[2029] 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 robot 414.

[2030] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2031] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2032] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2033] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2034] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2035] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2036] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2037] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2038] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2039] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2040] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2041] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2042] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2043] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2044] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2045] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2046] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2047] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2048] The following is further disclosed regarding the above embodiment.

[2049] (Claim 1)

[2050] a device for a user to input preferences and past browsing history;

[2051] a database storing profile information of said users;

[2052] A generating AI model means for selecting a work based on the profile information;

[2053] a display means for presenting the selected works to the user;

[2054] means for collecting and presenting detailed information about said works;

[2055] A means to generate hybrid recommendations that combine different genres and styles.

[2056] A system including:

[2057] (Claim 2)

[2058] The system according to claim 1, characterized in that the generative AI model means uses an algorithm to select the best can...

Claims

1. a device for a user to input preferences and past browsing history; a database storing profile information of said users; A generating AI model means for selecting a work based on the profile information; a display means for presenting the selected works to the user; means for collecting and presenting detailed information about said works; A means to generate hybrid recommendations that combine different genres and styles. A system including:

2. The system according to claim 1, wherein the generating AI model means uses an algorithm that selects the best candidate from among related works based on the user's profile information.

3. 2. The system according to claim 1, wherein said detailed information gathering means gathers and presents comments from directors and writers of works, interviews, and behind-the-scenes information.

Images