system

Abstract

We provide the system. [Solution] A means for analyzing a user's past entertainment behavior to generate a preference profile, A means for collecting various publicly available entertainment information and selecting appropriate entertainment based on the aforementioned preference profile, A means of automatically booking, purchasing, or obtaining tickets for a selection of entertainment, A means of automatically generating and promoting the sharing of reviews during or after a user's entertainment experience, A means of motivating users to participate in entertainment by offering points or rewards, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is 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 an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional entertainment selection systems have insufficient personalization based on user preferences, and users could not easily find content that matches their interests. In addition, functions for comprehensively supporting the entertainment experience, such as reservation, purchase, and sharing of reviews after participation in entertainment, were lacking, and users had to perform those procedures individually. Furthermore, there was a lack of motivation to encourage participation in entertainment, and the willingness of users to participate could not be enhanced.

Means for Solving the Problems

[0005] This invention provides a system that analyzes a user's past entertainment behavior to generate a preference profile and selects appropriate content from publicly available entertainment information based on that profile. Furthermore, it includes means for automatically reserving, purchasing, or obtaining tickets for selected entertainment, and for automatically generating and promoting the sharing of reviews during or after the user's experience. In addition, it can improve the user experience by providing users with points or rewards to motivate them to participate in entertainment and by reminding them of their next activity.

[0006] "User's past entertainment behavior" refers to the history of movies, music, events, etc. that the user has watched, participated in, or rated in the past.

[0007] A "preference profile" is a unique dataset generated as a result of an analysis of the entertainment genres, artists, and types that a user prefers.

[0008] "Entertainment information" refers to detailed information about publicly available content such as movies, music, and events, including showtimes, release dates, and ticket prices.

[0009] "Reservation, purchase, or ticket acquisition" refers to the various procedures taken to secure the right to view or participate in the entertainment of the user's choice.

[0010] "Generating and promoting review sharing" is a process that automatically generates written feedback and ratings based on users' entertainment experiences and encourages them to post them on external social networking services.

[0011] Providing points or rewards is an incentive given to users for their entertainment activities, thereby increasing their motivation to participate.

[0012] "Motivating" refers to measures that stimulate users' desire to participate in entertainment, and this is promoted by utilizing gamification elements.

[0013] "Reminding" means notifying users about upcoming entertainment events to help them remember the date. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

[0022] [First Embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] To implement this invention, a system comprising several key modules is required. The following are specific embodiments thereof.

[0036] User profiling module

[0037] The server collects data on the user's past entertainment behavior and uses this to generate a user preference profile. This data includes the movies the user has watched, the music they have listened to, and the events they have attended. Through this data analysis, machine learning algorithms are used to identify the distribution of genres and artists that the user prefers, which helps in suggesting future content.

[0038] Entertainment information curation module

[0039] The server retrieves the latest entertainment information from external data sources. This information includes movie release dates, music album release information, concert dates, and more. The server then compares this information with the user's preference profile to select and list content that is highly relevant to the user.

[0040] Reservation / Purchase Support Module

[0041] The device displays selected entertainment information in a user interface and supports users in making reservations, purchases, or obtaining tickets for viewing or participation. It also integrates with external services to process payments as needed.

[0042] Review generation and sharing module

[0043] The server collects feedback after the user's entertainment experience and automatically generates reviews using natural language processing technology. These reviews are based on the user's opinions and ratings, and are shared on social media only after the user is asked to confirm them on their device and gives permission.

[0044] Gamification and rewards module

[0045] The server encourages user participation by awarding points and rewards based on users' entertainment activities. This allows users to feel a sense of accomplishment and motivates them to choose their next form of entertainment.

[0046] Reminder and Schedule Management Module

[0047] The device adds selected entertainment events to the user's schedule and sets reminder notifications. This ensures that users don't miss out on content they're interested in.

[0048] Specific example

[0049] If a user has previously watched many action movies, the server will collect the latest action movies from its data sources and present them as recommendations based on their individual preference profile. When the user selects and watches a movie, a review generation module automatically summarizes their impressions and shares them on social media, giving other users the opportunity to learn about the movie. Users also earn points for watching movies, which they can use to purchase tickets for future movies. This entire process enriches and streamlines the user's entertainment experience.

[0050] The following describes the processing flow.

[0051] Step 1:

[0052] The server retrieves the user's entertainment history from a database and analyzes the genres and frequency of content the user has watched in the past. Based on this, it creates a user preference profile.

[0053] Step 2:

[0054] The server collects data on the latest movies, music, and events from external entertainment information services. The collected data is filtered based on its content, genre, dates, and other factors.

[0055] Step 3:

[0056] The server uses the user's preference profile to select the most suitable content from the collected entertainment information. The selected content is then generated as a list.

[0057] Step 4:

[0058] The terminal displays an entertainment list received from the server on the user interface. Users can select movies, music, and events of interest from this list.

[0059] Step 5:

[0060] Users can view details of their selected entertainment through their device and indicate their intention to book, purchase, or obtain tickets. If necessary, they can proceed with payment.

[0061] Step 6:

[0062] Based on the user's selection, the server issues purchase confirmations and ticket details, and provides them to the user through the terminal.

[0063] Step 7:

[0064] After a user watches or participates in entertainment, the server collects feedback from the user. Based on the user's ratings and comments, an automated review is generated using natural language processing technology.

[0065] Step 8:

[0066] The device displays the generated review to the user and requests permission to post it to social media. If the user grants permission, the review is automatically posted to social media.

[0067] Step 9:

[0068] The server calculates points based on the user's activity log and adds them to the user's account. Furthermore, it suggests new quests and missions to encourage future entertainment activities.

[0069] Step 10:

[0070] The device checks the user's schedule and sets reminders for upcoming entertainment events. These reminders are sent to the user at the appropriate time.

[0071] (Example 1)

[0072] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0073] In today's entertainment industry, users struggle to select the most suitable content from a vast array of options. Furthermore, the time spent selecting content can lead to decreased user satisfaction. Additionally, the inability to effectively utilize feedback from experienced content hinders improvements in the accuracy of future recommendations. A system is needed that efficiently addresses these problems and enriches the user's entertainment experience.

[0074] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0075] In this invention, the server includes means for analyzing the user's past entertainment behavior and generating a preference profile using a machine learning algorithm; means for collecting various entertainment information published from external sources and selecting appropriate entertainment based on the preference profile; and means for analyzing user feedback and generated reviews and re-evaluating the entertainment content to improve the accuracy of future entertainment recommendations. This enables users to efficiently discover content that is best suited to them and to effectively utilize post-experience feedback to improve the accuracy of future recommendations.

[0076] A "user preference profile" is a collection of information that indicates an individual user's interests and preferences, created using machine learning algorithms based on the user's past entertainment behavior data.

[0077] "Entertainment information" refers to details of publicly available content such as movies, music, and events, as well as related data.

[0078] "Reservation, purchase, and ticket acquisition" refers to the actions taken by users to access or participate in entertainment content.

[0079] "Natural language processing technology" refers to a set of techniques and methodologies used by computers to understand and process human language.

[0080] "Points and rewards" refer to incentives and benefits provided in accordance with users' entertainment activities, with the aim of encouraging further user participation.

[0081] "External information sources" refer to organizations or platforms that provide various entertainment-related data and information accessible from outside the system.

[0082] This system is designed to enhance the user's entertainment experience. Specifically, it works by coordinating servers and terminals to analyze user preferences and deliver optimal content.

[0083] First, the server collects data on the user's past entertainment behavior and generates a preference profile using machine learning algorithms. This is based on viewing history, music playlists, and event attendance records stored in the database. From this information, the server identifies the user's preferred genres and artists and organizes them as a preference profile.

[0084] Next, the server collects publicly available entertainment information from external sources. This involves using external APIs and web scraping techniques to obtain the latest movie release dates, music release information, and event schedules. This information, combined with the server's generated preference profile, serves as the basis for selecting the most relevant content for the user.

[0085] The selected entertainment is presented to the user through the device's user interface. The device uses an intuitive interface to help users easily reserve and purchase content for viewing or participation. If necessary, it also integrates with external payment systems to support payment processing.

[0086] After an entertainment experience, the server collects user feedback and automatically generates a review using natural language processing technology. The generated review is then requested for user confirmation on the device, and if permission is granted, it is shared on social media.

[0087] Furthermore, the server provides points and rewards based on the user's entertainment activities. This motivates users to choose their next form of entertainment, encouraging greater participation.

[0088] For example, if a user has watched many action movies in the past, the server will collect the latest action movie information from its data sources and suggest movies based on their preference profile. When the user selects and watches a movie, a review generation module will automatically summarize their impressions and allow them to share them on social media. Furthermore, the user earns points for watching movies, which can be used towards future ticket purchases.

[0089] An example of a prompt message would be, "Based on the movies I've watched in the past, please list some action movies you recommend to me." In this way, the system leverages generative AI models to enrich the user's entertainment experience.

[0090] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0091] Step 1:

[0092] The server collects data on the user's past entertainment behavior. Its inputs include a database of movies the user has watched, music they have listened to, and events they have attended. The server transforms this data into an organized format for input into machine learning algorithms and outputs a list necessary for analyzing preferences. Specifically, the server queries the database and extracts the required data.

[0093] Step 2:

[0094] The server applies machine learning algorithms based on collected data to generate user preference profiles. It uses previously collected behavioral data as input, and clustering techniques are used to classify similar entertainment content based on this data. The output is the user preference profile, which is used for future content recommendations. Specifically, it runs the algorithm, builds the profile, and saves it to a database.

[0095] Step 3:

[0096] The server retrieves the latest entertainment information from external sources. Input includes configuration information for external APIs and web scraping tools. Using these methods, the server downloads movie release dates, music album release information, and event dates, creating a pure information list as output. Specifically, it executes scripts to automatically retrieve the latest information.

[0097] Step 4:

[0098] The server matches the acquired entertainment information with the user's preference profile. The input consists of the generated preference profile and a list of the latest information already acquired. Using a recommendation algorithm, the server selects the most relevant content for the user and outputs it as a curated list. Specifically, it utilizes matching technology to establish associations.

[0099] Step 5:

[0100] The terminal displays curated entertainment information received from the server in a user interface. The input is a recommendation list retrieved from the server, which the terminal visualizes in a user-friendly format. The output is an interface showing the user's choices of content to watch or participate in. Specifically, it updates GUI components to display the information.

[0101] Step 6:

[0102] The terminal assists with reservations and purchases based on user selections. Input is the entertainment content selected by the user, and the terminal communicates with the reservation and payment systems to complete the purchase process. Output is reservation confirmation and purchase completion messages. Specifically, it guides the user through form input and processes payments.

[0103] Step 7:

[0104] The server collects feedback after the user's entertainment experience and generates a review using natural language processing techniques. The input is user feedback, which the server analyzes and outputs a textual review. Specifically, it receives feedback, applies a language model to create a review, and presents it to the user.

[0105] Step 8:

[0106] The server calculates and provides points and rewards based on the user's entertainment activities. The input is a record of the user's completed activities; the server uses this to award points and outputs an updated point balance. Specifically, it updates account information and notifies the user of the new balance.

[0107] Step 9:

[0108] The device synchronizes selected entertainment information with the user's schedule and sets reminders. Input consists of confirmed event information and the user's calendar settings, and the device uses this information to output reminder notifications. Specifically, it synchronizes with the calendar app and generates a notification immediately before the event.

[0109] (Application Example 1)

[0110] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0111] In today's world, there is a need for methods that effectively propose entertainment content tailored to the diverse preferences of users, and that facilitate smooth viewing and experience. However, conventional systems have limitations, such as failing to fully grasp user preferences and making it difficult to easily access selected content. Furthermore, they are not adequately utilizing user feedback after their experience to improve future recommendations. It is necessary to solve these problems.

[0112] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0113] In this invention, the server includes means for analyzing the user's past viewing behavior to generate personal preference information, means for collecting the latest entertainment information from external sources and selecting appropriate content based on the preference information, and means for presenting content based on the user's preferences and enabling the user to directly access or play it. As a result, the user enjoys an individually customized content experience, and feedback is reflected in subsequent experiences, enabling highly personalized suggestions.

[0114] "User preference information" refers to information about content preferences that is individually generated based on a user's past viewing behavior and usage history.

[0115] "External information sources" refer to external data providers and open databases that provide information such as movie and music release dates and event schedules.

[0116] "Entertainment information" refers to information about various types of content such as movies, music, and events, and includes topics suggested according to the user's interests.

[0117] "Content selection" is the process of finding the content that best suits the user's preferences from among the collected entertainment information.

[0118] "Feedback" refers to opinions, impressions, and evaluations provided by users after they have experienced the content, and is information that can be used to improve future proposals.

[0119] "Schedule integration" means that the system synchronizes information with the user's schedule management and provides notifications to help them efficiently view content of interest.

[0120] To implement this invention, a system consisting of several main modules is required. The entire system is comprised of the cooperation between a server and a client (user terminal).

[0121] The server collects data such as the user's past viewing behavior and generates personalized preference information using machine learning algorithms. This process utilizes machine learning libraries such as Python and Scikit-learn, enabling the analysis of large amounts of data. Next, the server retrieves entertainment information from external sources via APIs (e.g., movie database APIs and music streaming APIs). This information is then compared with the preference information to select the most suitable content for the user.

[0122] The selected content is presented on the user's device, for example, on a modern smartphone app, allowing the user to access or play it directly. This process utilizes the Django REST Framework to build the user interface and provide seamless operation.

[0123] Furthermore, after a user's viewing experience, the server automatically generates feedback using natural language generation technology (e.g., GPT-3®) APIs and presents it as a prompt. After the user confirms it, they can easily share it via SNS APIs.

[0124] Furthermore, the system encourages continued use by offering rewards that users can earn during their experience. This allows users to maintain their motivation and plan their next entertainment experience.

[0125] As a concrete example, if a movie-loving user is looking for a new movie, this system will recommend the most suitable action movie based on the genres of movies they have watched in the past. An example of a prompt message could be, "For a user who watches a lot of action movies, please recommend the best action movie to watch next using GPT-3." This would instruct the generative AI model in that format.

[0126] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0127] Step 1:

[0128] The server collects data on users' past viewing behavior. It takes the user's viewing history (e.g., a list of movies watched or music listened to) as input and uses a machine learning algorithm to generate preference information. The output is an individual preference profile for each user. Here, a Python program is used to cleanse the viewing data and create a model using data analysis libraries.

[0129] Step 2:

[0130] The server collects the latest entertainment information from external sources. It uses data from available movie database APIs and music streaming APIs as input. The server analyzes this data and selects the most suitable content based on the user's preference profile. The output is a list of entertainment information recommended to the user. The server utilizes RESTful APIs for data retrieval and filtering.

[0131] Step 3:

[0132] The terminal presents the user with a list of content received from the server via a user interface. The input is a recommendation list sent from the server. The output is a content selection screen displayed in a user-friendly format. Django is used here to make the user-selected content playable on a streaming platform.

[0133] Step 4:

[0134] After a user selects and views content, the server automatically generates feedback using natural language generation technology. The input is the user's feedback and comments after viewing the content. The output is a generated review text, which is created by a generative AI model (e.g., GPT-3).

[0135] Step 5:

[0136] The device presents the generated review to the user and encourages sharing on social media. The input is the review text sent from the server. The output is the confirmed review, which is posted through the user's social media account. The device uses social media APIs to provide simple sharing options.

[0137] Step 6:

[0138] The server rewards users for their experience. Inputs include user participation data and activity levels. Outputs are records of points and rewards added to the user's account. Users can use these for future entertainment participation. The server manages points based on user account information.

[0139] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0140] To implement this invention, a system is required that combines multiple modules, including an emotion engine that recognizes the user's emotions during their entertainment experience and integrates them as part of the system. The following is a specific embodiment of this system.

[0141] Emotion recognition module

[0142] The server analyzes the user's emotions using emotion recognition algorithms based on data collected during the user's entertainment experience. User facial expressions, voice, and text feedback are used as input data. By processing this information in real time, the server identifies various emotions the user felt during the experience, such as joy, excitement, and sadness.

[0143] Preference profile update module

[0144] The server feeds the emotion recognition results back into the user's preference profile, improving the profile's accuracy. This profile update allows the server to suggest content that the user will better enjoy.

[0145] Entertainment proposal module

[0146] The server selects the most suitable entertainment for the user based on the updated preference profile. By incorporating emotional information, it is possible to generate more personalized content lists than ever before.

[0147] Automated review generation module

[0148] The device generates reviews incorporating emotional data. Leveraging insights provided by the emotion engine, it adds emotional elements to user feedback, creating more engaging reviews. Users can then review these reviews and choose to share them on social media.

[0149] Specific example

[0150] When a user is watching a comedy film, the server observes the user's facial expressions and laughter during key scenes and measures the intensity of their enjoyment through an emotion engine. This data is reflected in the user's preference profile in real time, helping to suggest movies that will make the user laugh more in the future. When generating reviews, comments emphasizing the overall level of laughter in the film are automatically created and presented to the user on their device. This process ensures that users enjoy entertainment that is perfectly suited to them, and that their reviews effectively express their emotions.

[0151] The following describes the processing flow.

[0152] Step 1:

[0153] The user begins watching entertainment content. The user's device continuously monitors the user's facial expressions and voice while they are watching, using its camera and microphone, and collects data.

[0154] Step 2:

[0155] The server receives user facial expressions and speech data sent from the terminal and activates an emotion recognition algorithm. This algorithm determines the user's emotional state (e.g., joy, surprise, sadness) in real time from the data.

[0156] Step 3:

[0157] The server analyzes emotional data and stores the results in the user's preference profile. This information is accumulated as new emotional experiences and serves as material for further learning the user's content preferences.

[0158] Step 4:

[0159] The server selects entertainment content to suggest next based on the user's updated preference profile and emotional data. The selected content is prioritized for its tendency to evoke feelings of excitement and laughter in the user.

[0160] Step 5:

[0161] The device displays a simple interface that prompts the user for feedback after viewing has finished. Users can enter their thoughts on the movie and any additional comments.

[0162] Step 6:

[0163] The server synthesizes user comments with sentiment data collected in real time and automatically generates reviews using natural language processing technology. These reviews incorporate the emotions users felt during their experience, resulting in compelling content.

[0164] Step 7:

[0165] The device presents the generated review to the user and offers an option to post it to social media. If the user agrees, the review is automatically posted to the selected social media platform.

[0166] Step 8:

[0167] The server calculates points related to the entertainment the user has watched and adds them to the user's account. These points can then be used for future entertainment activities.

[0168] Step 9:

[0169] The device adds upcoming entertainment events to the user's schedule and sets them as reminders. These reminders ensure users don't miss out on new entertainment experiences.

[0170] (Example 2)

[0171] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0172] Current entertainment recommendation systems rely solely on users' past behavior and feedback, failing to fully utilize real-time emotions and reactions during experiences. This makes it difficult to provide optimal content to individual users, highlighting the need for higher levels of personalization. Furthermore, the generation and sharing of reviews that adequately reflect users' post-experience emotions are insufficient, preventing the maximization of the experience's value.

[0173] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0174] In this invention, the server includes means for analyzing the user's past information to generate preference data, means for collecting diverse information and selecting appropriate entertainment based on the preference data, and means for identifying emotions during the experience and updating the profile by providing feedback. This enables more accurate personalization, recommendations based on the user's experience, and content suggestions based on emotions.

[0175] A "user" refers to an individual or group that uses the system and is the subject that enjoys the entertainment experience.

[0176] "Information" is a general term for data related to entertainment or users, including audio, video, and text.

[0177] "Preference data" refers to data that represents a user's preferences, generated based on their past behavior and experiences.

[0178] "Entertainment" refers to a series of activities and content that provide entertainment to users.

[0179] "Experience" refers to the subjective feelings and emotions that users gain through entertainment.

[0180] "Emotions" refer to internal reactions such as joy, sadness, and excitement that arise during a user's entertainment experience.

[0181] A "profile" is a data structure created based on a user's preferences, behavior, and emotional responses, and is used to provide personalized suggestions.

[0182] "Recommendation" refers to the act of presenting appropriate entertainment based on a user's profile.

[0183] "Suggestion" refers to suggesting entertainment activities that users should engage in next.

[0184] This invention provides a system for highly personalizing the user's entertainment experience. The system consists of a server and terminals, analyzes the user's experience, and recommends the most suitable entertainment.

[0185] The server first analyzes the user's past entertainment behavior to generate preference data. This preference data concretizes the user's preferences based on their selection history and content they have watched. A database system and analysis software are used for this analysis, enabling efficient data processing.

[0186] Next, the server collects diverse information and selects appropriate entertainment based on the aforementioned preference data. In selecting entertainment, it comprehensively investigates various publicly available digital content and streaming service information to extract candidates that are likely to be of the user's greatest interest. This is done using a generative AI model to comprehensively judge the content and evaluation of each form of entertainment.

[0187] Furthermore, during the user's experience, the server analyzes the user's emotions in real time using voice and facial expression data. To this end, it utilizes voice recognition software and image analysis algorithms to identify emotions during the experience. For example, while watching a comedy movie, the server captures the user's laughter and changes in facial expressions to determine their feelings of joy, and feeds that information back into their preference data in real time.

[0188] The device automatically generates evaluation statements based on collected sentiment data. These evaluation statements utilize a generative AI model to produce sentiment-based natural language text. As a result, users can obtain compelling evaluations that reflect their experiences. Users can review these evaluation statements and share them on social media.

[0189] As a concrete example, while a user is watching a comedy film, the server analyzes the user's laughter and facial expressions during key scenes to measure the intensity of their feelings of enjoyment. This data is reflected in their preference data, enabling more appropriate comedy recommendations for future viewings. After viewing, the device generates an evaluation statement emphasizing the degree of humor in the film and presents it to the user as a review.

[0190] An example of a prompt message is: "For each scene in the comedy movies the user has watched, analyze the frequency and intensity of laughter, update the preference profile, and select the next movie to suggest."

[0191] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0192] Step 1:

[0193] The server collects data on the user's past entertainment behavior. Specifically, it imports viewing history and rating information from various digital platforms into a database. Using this data as input, a preference data generation algorithm is applied to output the user's preference data. This process allows for an understanding of the genres and types of content the user prefers.

[0194] Step 2:

[0195] The server collects the latest entertainment information. It uses online databases and APIs to obtain diverse content information. Using the acquired data as input, a generative AI model selects appropriate entertainment based on the user's preferences and outputs a list of candidates. Here, it analyzes genre matching and popularity to extract the most suitable works.

[0196] Step 3:

[0197] While a user is experiencing entertainment content, the server collects the user's facial expressions and voice data in real time. This data, obtained through cameras and microphones, is processed by an emotion recognition algorithm to output the user's emotional state. This process identifies specific emotions such as joy, sadness, and excitement during viewing.

[0198] Step 4:

[0199] The server feeds back the emotional state obtained in step 3 to the user's preference data in real time. It analyzes the frequency and intensity of emotional changes and updates the preference profile. This updated data provides output that helps in making more accurate entertainment selections in the future.

[0200] Step 5:

[0201] After an entertainment experience, the device uses a generative AI model to generate a review of the experience. Taking emotional data and preference profiles as input, it outputs an evaluation statement in natural language text. This process includes automatically creating wording that includes particularly emotionally charged parts and memorable scenes.

[0202] Step 6:

[0203] Users can view reviews displayed on their devices and choose to share them on platforms such as social media. The device will have a share button, allowing for easy posting of reviews. Review sharing is a crucial output for widely disseminating user experiences.

[0204] (Application Example 2)

[0205] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0206] Conventional entertainment selection systems, relying solely on users' past behavior, struggle to provide personalized experiences based on instantaneous emotional shifts and current feelings. Furthermore, they lack automated review generation tailored to user emotions, resulting in insufficient improvement in user satisfaction and overall experience. Therefore, a method is needed to reflect users' real-time emotions and deliver more accurate and satisfying entertainment experiences.

[0207] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0208] This invention includes a server that recognizes a user's emotions in real time during their entertainment experience and reflects that data in a preference profile; a server that automatically generates reviews after the experience based on the recognized emotional data and promotes sharing; and a server that motivates users to participate in entertainment by providing rewards. This enables the provision of personalized content based on the user's emotions and the generation of emotionally charged reviews, thereby improving user satisfaction.

[0209] A "user" is an entity that consumes entertainment content and utilizes various functions of a system.

[0210] "Entertainment activities" refer to content consumption behaviors such as movies, music, and games, which users engage in for the purpose of enjoyment and relaxation.

[0211] A "preference profile" is a data structure that is generated based on a user's past behavior and emotional data, and indicates the user's preferences.

[0212] "Entertainment information" refers to a variety of data related to entertainment content, including movie titles and music artists.

[0213] "Emotion recognition" is a technology that analyzes a user's psychological state from input data such as facial expressions and voice, and identifies specific emotions.

[0214] A "review" is a document that compiles users' evaluations and opinions on entertainment content they have experienced.

[0215] "Rewards" are incentives given to motivate user behavior and may include points or perks.

[0216] To implement this invention, a system is needed that recognizes the user's emotions during their entertainment experience in real time and reflects that information in their preference profile. Specifically, it is implemented using the following components.

[0217] 1. Emotion Recognition Module

[0218] The server uses the user's smartphone camera and microphone to capture facial expressions and voice during entertainment activities. Image processing libraries (e.g., OpenCV) and voice analysis libraries (e.g., Librosa) are used to extract emotional characteristics from this data. Machine learning models (e.g., TENSORFLOW®, PyTorch) are used to identify and analyze the user's emotions in real time.

[0219] 2. Preference Profile Update Module

[0220] The server updates the user's preference profile using the analyzed sentiment data. A database management system (e.g., SQLite) is used to store and manage information about the user's preferences and interests.

[0221] 3. Entertainment Proposal Module

[0222] The server selects the most suitable entertainment content for the user based on their updated preference profile. Using algorithms, it recommends personalized content that matches the user's current mood.

[0223] 4. Automated Review Generation Module

[0224] The device uses emotional data and leverages a natural language generation model (e.g., a generative AI model) to automatically generate reviews of entertainment content experienced by the user. These reviews include emotional elements, which the user can review and share on social media.

[0225] As a specific example,

[0226] While a user is watching a movie, their smartphone captures data of their smile and laughter, identifying in real time that their emotion is "joy." This information is immediately reflected in their preference profile, and the next time they watch a movie, they will be offered suggestions for movies they will enjoy more. After watching, an automated review generation module creates a review that includes emotional elements, such as "It was a very fun movie that made me laugh a lot!", and enables sharing on social media.

[0227] Example of a prompt:

[0228] "Generate emotionally resonant reviews based on the entertainment content users experienced. Highlight scenes where they smiled frequently and create natural-sounding sentences."

[0229] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0230] Step 1:

[0231] The server activates the user's smartphone camera and microphone to capture facial expressions and audio data during entertainment activities. This input data forms the basis for analyzing the user's emotions in real time.

[0232] Step 2:

[0233] The server uses an image processing library (OpenCV) and an audio analysis library (Librosa) to extract features from the captured images and audio, respectively. This process analyzes facial movements and voice tone, outputting emotional characteristics as numerical data.

[0234] Step 3:

[0235] The server inputs the extracted emotional characteristic data into a machine learning model (TensorFlow, PyTorch) to identify the user's specific emotions (e.g., "joy," "sadness," etc.). The model processes this characteristic data and outputs a label that identifies the user's emotion.

[0236] Step 4:

[0237] The server updates the user's preference profile using identified sentiment data. It reflects this sentiment data in a database management system (SQLite), updating the profile information in real time.

[0238] Step 5:

[0239] The server runs an entertainment suggestion algorithm based on the updated preference profile. It selects content that matches the user's preferences and current mood, and generates suggestions.

[0240] Step 6:

[0241] The device uses a generative AI model to automatically generate reviews that take into account the emotions identified during the experience. Emotion labels and prompt sentences are input to the model, which then outputs a review in a natural-sounding sentence format.

[0242] Step 7:

[0243] Users can view reviews generated on their devices and share them on social media if necessary. This allows them to share their experiences with others and use that information to help them choose their next form of entertainment.

[0244] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0245] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0246] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0247] [Second Embodiment]

[0248] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0249] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0250] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0251] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0252] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0253] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0254] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0255] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0256] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0257] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0258] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0259] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0260] To implement this invention, a system comprising several key modules is required. The following are specific embodiments thereof.

[0261] User profiling module

[0262] The server collects data on the user's past entertainment behavior and uses this to generate a user preference profile. This data includes the movies the user has watched, the music they have listened to, and the events they have attended. Through this data analysis, machine learning algorithms are used to identify the distribution of genres and artists that the user prefers, which helps in suggesting future content.

[0263] Entertainment information curation module

[0264] The server retrieves the latest entertainment information from external data sources. This information includes movie release dates, music album release information, concert dates, and more. The server then compares this information with the user's preference profile to select and list content that is highly relevant to the user.

[0265] Reservation / Purchase Support Module

[0266] The device displays selected entertainment information in a user interface and supports users in making reservations, purchases, or obtaining tickets for viewing or participation. It also integrates with external services to process payments as needed.

[0267] Review generation and sharing module

[0268] The server collects feedback after the user's entertainment experience and automatically generates reviews using natural language processing technology. These reviews are based on the user's opinions and ratings, and are shared on social media only after the user is asked to confirm them on their device and gives permission.

[0269] Gamification and rewards module

[0270] The server encourages user participation by awarding points and rewards based on users' entertainment activities. This allows users to feel a sense of accomplishment and motivates them to choose their next form of entertainment.

[0271] Reminder and Schedule Management Module

[0272] The device adds selected entertainment events to the user's schedule and sets reminder notifications. This ensures that users don't miss out on content they're interested in.

[0273] Specific example

[0274] If a user has previously watched many action movies, the server will collect the latest action movies from its data sources and present them as recommendations based on their individual preference profile. When the user selects and watches a movie, a review generation module automatically summarizes their impressions and shares them on social media, giving other users the opportunity to learn about the movie. Users also earn points for watching movies, which they can use to purchase tickets for future movies. This entire process enriches and streamlines the user's entertainment experience.

[0275] The following describes the processing flow.

[0276] Step 1:

[0277] The server retrieves the user's entertainment history from a database and analyzes the genres and frequency of content the user has watched in the past. Based on this, it creates a user preference profile.

[0278] Step 2:

[0279] The server collects data on the latest movies, music, and events from external entertainment information services. The collected data is filtered based on its content, genre, dates, and other factors.

[0280] Step 3:

[0281] The server uses the user's preference profile to select the most suitable content from the collected entertainment information. The selected content is then generated as a list.

[0282] Step 4:

[0283] The terminal displays the entertainment list received from the server on the user interface. The user can select movies, music, and events of interest from this list.

[0284] Step 5:

[0285] The user checks the details of the entertainment selected through the terminal and indicates an intention to make a reservation, purchase, or obtain tickets. If necessary, payment procedures are carried out.

[0286] Step 6:

[0287] Based on the user's selection, the server issues purchase confirmations and ticket details and provides them to the user through the terminal.

[0288] Step 7:

[0289] After the user watches or participates in the entertainment, the server collects feedback from the user. Based on the user's evaluations and feelings, an automatic review is generated using natural language processing technology.

[0290] Step 8:

[0291] The terminal presents the generated review to the user and requests permission to post it on the SNS. If the user gives permission, the review is automatically posted on the SNS.

[0292] Step 9:

[0293] The server calculates points based on the user's activity records and adds them to the user account. Additionally, new quests and missions to promote the next entertainment activity are proposed to the user.

[0294] Step 10:

[0295] The device checks the user's schedule and sets reminders for upcoming entertainment events. These reminders are sent to the user at the appropriate time.

[0296] (Example 1)

[0297] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] In today's entertainment industry, users struggle to select the most suitable content from a vast array of options. Furthermore, the time spent selecting content can lead to decreased user satisfaction. Additionally, the inability to effectively utilize feedback from experienced content hinders improvements in the accuracy of future recommendations. A system is needed that efficiently addresses these problems and enriches the user's entertainment experience.

[0299] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0300] In this invention, the server includes means for analyzing the user's past entertainment behavior and generating a preference profile using a machine learning algorithm; means for collecting various entertainment information published from external sources and selecting appropriate entertainment based on the preference profile; and means for analyzing user feedback and generated reviews and re-evaluating the entertainment content to improve the accuracy of future entertainment recommendations. This enables users to efficiently discover content that is best suited to them and to effectively utilize post-experience feedback to improve the accuracy of future recommendations.

[0301] The "user preference profile" is a collection of information indicating the interests and concerns of individual users, created using machine learning algorithms based on the user's past entertainment behavior data.

[0302] "Entertainment information" refers to details of publicly available content such as movies, music, events, and related data.

[0303] "Reservation, purchase, ticket acquisition" refers to the act of a user performing the procedures necessary to watch or participate in entertainment content.

[0304] "Natural language processing technology" refers to a series of technologies and methodologies used by computers to understand and process human language.

[0305] "Points and rewards" refer to incentives and benefits provided in response to a user's entertainment activities, aiming to promote further participation by the user.

[0306] "External information sources" refer to institutions or platforms that provide various data and information related to entertainment, which are accessible from outside the system.

[0307] This system is designed to improve the user's entertainment experience. Specifically, it implements a series of processes that coordinate the server and the terminal to analyze the user's preferences and provide optimal content.

[0308] First, the server collects the user's past entertainment behavior data and generates a preference profile using machine learning algorithms. At this time, it is based on the viewing history, music playlists, records of participated events, etc. stored in the database. The server identifies the genres and artists that the user likes from this information and organizes them as a preference profile.

[0309] Next, the server collects publicly available entertainment information from external sources. This involves using external APIs and web scraping techniques to obtain the latest movie release dates, music release information, and event schedules. This information, combined with the server's generated preference profile, serves as the basis for selecting the most relevant content for the user.

[0310] The selected entertainment is presented to the user through the device's user interface. The device uses an intuitive interface to help users easily reserve and purchase content for viewing or participation. If necessary, it also integrates with external payment systems to support payment processing.

[0311] After an entertainment experience, the server collects user feedback and automatically generates a review using natural language processing technology. The generated review is then requested for user confirmation on the device, and if permission is granted, it is shared on social media.

[0312] Furthermore, the server provides points and rewards based on the user's entertainment activities. This motivates users to choose their next form of entertainment, encouraging greater participation.

[0313] For example, if a user has watched many action movies in the past, the server will collect the latest action movie information from its data sources and suggest movies based on their preference profile. When the user selects and watches a movie, a review generation module will automatically summarize their impressions and allow them to share them on social media. Furthermore, the user earns points for watching movies, which can be used towards future ticket purchases.

[0314] An example of a prompt message would be, "Based on the movies I've watched in the past, please list some action movies you recommend to me." In this way, the system leverages generative AI models to enrich the user's entertainment experience.

[0315] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0316] Step 1:

[0317] The server collects data on the user's past entertainment behavior. Its inputs include a database of movies the user has watched, music they have listened to, and events they have attended. The server transforms this data into an organized format for input into machine learning algorithms and outputs a list necessary for analyzing preferences. Specifically, the server queries the database and extracts the required data.

[0318] Step 2:

[0319] The server applies machine learning algorithms based on collected data to generate user preference profiles. It uses previously collected behavioral data as input, and clustering techniques are used to classify similar entertainment content based on this data. The output is the user preference profile, which is used for future content recommendations. Specifically, it runs the algorithm, builds the profile, and saves it to a database.

[0320] Step 3:

[0321] The server retrieves the latest entertainment information from external sources. Input includes configuration information for external APIs and web scraping tools. Using these methods, the server downloads movie release dates, music album release information, and event dates, creating a pure information list as output. Specifically, it executes scripts to automatically retrieve the latest information.

[0322] Step 4:

[0323] The server matches the acquired entertainment information with the user's preference profile. The input consists of the generated preference profile and a list of the latest information already acquired. Using a recommendation algorithm, the server selects the most relevant content for the user and outputs it as a curated list. Specifically, it utilizes matching technology to establish associations.

[0324] Step 5:

[0325] The terminal displays curated entertainment information received from the server in a user interface. The input is a recommendation list retrieved from the server, which the terminal visualizes in a user-friendly format. The output is an interface showing the user's choices of content to watch or participate in. Specifically, it updates GUI components to display the information.

[0326] Step 6:

[0327] The terminal assists with reservations and purchases based on user selections. Input is the entertainment content selected by the user, and the terminal communicates with the reservation and payment systems to complete the purchase process. Output is reservation confirmation and purchase completion messages. Specifically, it guides the user through form input and processes payments.

[0328] Step 7:

[0329] The server collects feedback after the user's entertainment experience and generates a review using natural language processing techniques. The input is user feedback, which the server analyzes and outputs a textual review. Specifically, it receives feedback, applies a language model to create a review, and presents it to the user.

[0330] Step 8:

[0331] The server calculates and provides points and rewards based on the user's entertainment activities. The input is a record of the user's completed activities; the server uses this to award points and outputs an updated point balance. Specifically, it updates account information and notifies the user of the new balance.

[0332] Step 9:

[0333] The device synchronizes selected entertainment information with the user's schedule and sets reminders. Input consists of confirmed event information and the user's calendar settings, and the device uses this information to output reminder notifications. Specifically, it synchronizes with the calendar app and generates a notification immediately before the event.

[0334] (Application Example 1)

[0335] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0336] In today's world, there is a need for methods that effectively propose entertainment content tailored to the diverse preferences of users, and that facilitate smooth viewing and experience. However, conventional systems have limitations, such as failing to fully grasp user preferences and making it difficult to easily access selected content. Furthermore, they are not adequately utilizing user feedback after their experience to improve future recommendations. It is necessary to solve these problems.

[0337] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0338] In this invention, the server includes means for analyzing the user's past viewing behavior to generate personal preference information, means for collecting the latest entertainment information from external sources and selecting appropriate content based on the preference information, and means for presenting content based on the user's preferences and enabling the user to directly access or play it. As a result, the user enjoys an individually customized content experience, and feedback is reflected in subsequent experiences, enabling highly personalized suggestions.

[0339] "User preference information" refers to information about content preferences that is individually generated based on a user's past viewing behavior and usage history.

[0340] "External information sources" refer to external data providers and open databases that provide information such as movie and music release dates and event schedules.

[0341] "Entertainment information" refers to information about various types of content such as movies, music, and events, and includes topics suggested according to the user's interests.

[0342] "Content selection" is the process of finding the content that best suits the user's preferences from among the collected entertainment information.

[0343] "Feedback" refers to opinions, impressions, and evaluations provided by users after they have experienced the content, and is information that can be used to improve future proposals.

[0344] "Schedule integration" means that the system synchronizes information with the user's schedule management and provides notifications to help them efficiently view content of interest.

[0345] To implement this invention, a system consisting of several main modules is required. The entire system is comprised of the cooperation between a server and a client (user terminal).

[0346] The server collects data such as the user's past viewing behavior and generates personalized preference information using machine learning algorithms. This process utilizes machine learning libraries such as Python and Scikit-learn, enabling the analysis of large amounts of data. Next, the server retrieves entertainment information from external sources via APIs (e.g., movie database APIs and music streaming APIs). This information is then compared with the preference information to select the most suitable content for the user.

[0347] The selected content is presented on the user's device, for example, on a modern smartphone app, allowing the user to access or play it directly. This process utilizes the Django REST Framework to build the user interface and provide seamless operation.

[0348] Furthermore, after a user's viewing experience, the server automatically generates feedback using a natural language generation technology (e.g., GPT-3) API and presents it as a prompt. After the user confirms it, they can easily share it via an SNS API.

[0349] Furthermore, the system encourages continued use by offering rewards that users can earn during their experience. This allows users to maintain their motivation and plan their next entertainment experience.

[0350] As a concrete example, if a movie-loving user is looking for a new movie, this system will recommend the most suitable action movie based on the genres of movies they have watched in the past. An example of a prompt message could be, "For a user who watches a lot of action movies, please recommend the best action movie to watch next using GPT-3." This would instruct the generative AI model in that format.

[0351] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0352] Step 1:

[0353] The server collects data on users' past viewing behavior. It takes the user's viewing history (e.g., a list of movies watched or music listened to) as input and uses a machine learning algorithm to generate preference information. The output is an individual preference profile for each user. Here, a Python program is used to cleanse the viewing data and create a model using data analysis libraries.

[0354] Step 2:

[0355] The server collects the latest entertainment information from external sources. It uses data from available movie database APIs and music streaming APIs as input. The server analyzes this data and selects the most suitable content based on the user's preference profile. The output is a list of entertainment information recommended to the user. The server utilizes RESTful APIs for data retrieval and filtering.

[0356] Step 3:

[0357] The terminal presents the user with a list of content received from the server via a user interface. The input is a recommendation list sent from the server. The output is a content selection screen displayed in a user-friendly format. Django is used here to make the user-selected content playable on a streaming platform.

[0358] Step 4:

[0359] After a user selects and views content, the server automatically generates feedback using natural language generation technology. The input is the user's feedback and comments after viewing the content. The output is a generated review text, which is created by a generative AI model (e.g., GPT-3).

[0360] Step 5:

[0361] The device presents the generated review to the user and encourages sharing on social media. The input is the review text sent from the server. The output is the confirmed review, which is posted through the user's social media account. The device uses social media APIs to provide simple sharing options.

[0362] Step 6:

[0363] The server rewards users for their experience. Inputs include user participation data and activity levels. Outputs are records of points and rewards added to the user's account. Users can use these for future entertainment participation. The server manages points based on user account information.

[0364] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0365] To implement this invention, a system is required that combines multiple modules, including an emotion engine that recognizes the user's emotions during their entertainment experience and integrates them as part of the system. The following is a specific embodiment of this system.

[0366] Emotion recognition module

[0367] The server analyzes the user's emotions using emotion recognition algorithms based on data collected during the user's entertainment experience. User facial expressions, voice, and text feedback are used as input data. By processing this information in real time, the server identifies various emotions the user felt during the experience, such as joy, excitement, and sadness.

[0368] Preference profile update module

[0369] The server feeds the emotion recognition results back into the user's preference profile, improving the profile's accuracy. This profile update allows the server to suggest content that the user will better enjoy.

[0370] Entertainment proposal module

[0371] The server selects the most suitable entertainment for the user based on the updated preference profile. By incorporating emotional information, it is possible to generate more personalized content lists than ever before.

[0372] Automated review generation module

[0373] The device generates reviews incorporating emotional data. Leveraging insights provided by the emotion engine, it adds emotional elements to user feedback, creating more engaging reviews. Users can then review these reviews and choose to share them on social media.

[0374] Specific example

[0375] When a user is watching a comedy film, the server observes the user's facial expressions and laughter during key scenes and measures the intensity of their enjoyment through an emotion engine. This data is reflected in the user's preference profile in real time, helping to suggest movies that will make the user laugh more in the future. When generating reviews, comments emphasizing the overall level of laughter in the film are automatically created and presented to the user on their device. This process ensures that users enjoy entertainment that is perfectly suited to them, and that their reviews effectively express their emotions.

[0376] The following describes the processing flow.

[0377] Step 1:

[0378] The user begins watching entertainment content. The user's device continuously monitors the user's facial expressions and voice while they are watching, using its camera and microphone, and collects data.

[0379] Step 2:

[0380] The server receives user facial expressions and speech data sent from the terminal and activates an emotion recognition algorithm. This algorithm determines the user's emotional state (e.g., joy, surprise, sadness) in real time from the data.

[0381] Step 3:

[0382] The server analyzes emotional data and stores the results in the user's preference profile. This information is accumulated as new emotional experiences and serves as material for further learning the user's content preferences.

[0383] Step 4:

[0384] The server selects entertainment content to suggest next based on the user's updated preference profile and emotional data. The selected content is prioritized for its tendency to evoke feelings of excitement and laughter in the user.

[0385] Step 5:

[0386] The device displays a simple interface that prompts the user for feedback after viewing has finished. Users can enter their thoughts on the movie and any additional comments.

[0387] Step 6:

[0388] The server synthesizes user comments with sentiment data collected in real time and automatically generates reviews using natural language processing technology. These reviews incorporate the emotions users felt during their experience, resulting in compelling content.

[0389] Step 7:

[0390] The device presents the generated review to the user and offers an option to post it to social media. If the user agrees, the review is automatically posted to the selected social media platform.

[0391] Step 8:

[0392] The server calculates points related to the entertainment the user has watched and adds them to the user's account. These points can then be used for future entertainment activities.

[0393] Step 9:

[0394] The device adds upcoming entertainment events to the user's schedule and sets them as reminders. These reminders ensure users don't miss out on new entertainment experiences.

[0395] (Example 2)

[0396] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0397] Current entertainment recommendation systems rely solely on users' past behavior and feedback, failing to fully utilize real-time emotions and reactions during experiences. This makes it difficult to provide optimal content to individual users, highlighting the need for higher levels of personalization. Furthermore, the generation and sharing of reviews that adequately reflect users' post-experience emotions are insufficient, preventing the maximization of the experience's value.

[0398] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0399] In this invention, the server includes means for analyzing the user's past information to generate preference data, means for collecting diverse information and selecting appropriate entertainment based on the preference data, and means for identifying emotions during the experience and updating the profile by providing feedback. This enables more accurate personalization, recommendations based on the user's experience, and content suggestions based on emotions.

[0400] A "user" refers to an individual or group that uses the system and is the subject that enjoys the entertainment experience.

[0401] "Information" is a general term for data related to entertainment or users, including audio, video, and text.

[0402] "Preference data" refers to data that represents a user's preferences, generated based on their past behavior and experiences.

[0403] "Entertainment" refers to a series of activities and content that provide entertainment to users.

[0404] "Experience" refers to the subjective feelings and emotions that users gain through entertainment.

[0405] "Emotions" refer to internal reactions such as joy, sadness, and excitement that arise during a user's entertainment experience.

[0406] A "profile" is a data structure created based on a user's preferences, behavior, and emotional responses, and is used to provide personalized suggestions.

[0407] "Recommendation" refers to the act of presenting appropriate entertainment based on a user's profile.

[0408] "Suggestion" refers to suggesting entertainment activities that users should engage in next.

[0409] This invention provides a system for highly personalizing the user's entertainment experience. The system consists of a server and terminals, analyzes the user's experience, and recommends the most suitable entertainment.

[0410] The server first analyzes the user's past entertainment behavior to generate preference data. This preference data concretizes the user's preferences based on their selection history and content they have watched. A database system and analysis software are used for this analysis, enabling efficient data processing.

[0411] Next, the server collects diverse information and selects appropriate entertainment based on the aforementioned preference data. In selecting entertainment, it comprehensively investigates various publicly available digital content and streaming service information to extract candidates that are likely to be of the user's greatest interest. This is done using a generative AI model to comprehensively judge the content and evaluation of each form of entertainment.

[0412] Furthermore, during the user's experience, the server analyzes the user's emotions in real time using voice and facial expression data. To this end, it utilizes voice recognition software and image analysis algorithms to identify emotions during the experience. For example, while watching a comedy movie, the server captures the user's laughter and changes in facial expressions to determine their feelings of joy, and feeds that information back into their preference data in real time.

[0413] The device automatically generates evaluation statements based on collected sentiment data. These evaluation statements utilize a generative AI model to produce sentiment-based natural language text. As a result, users can obtain compelling evaluations that reflect their experiences. Users can review these evaluation statements and share them on social media.

[0414] As a concrete example, while a user is watching a comedy film, the server analyzes the user's laughter and facial expressions during key scenes to measure the intensity of their feelings of enjoyment. This data is reflected in their preference data, enabling more appropriate comedy recommendations for future viewings. After viewing, the device generates an evaluation statement emphasizing the degree of humor in the film and presents it to the user as a review.

[0415] An example of a prompt message is: "For each scene in the comedy movies the user has watched, analyze the frequency and intensity of laughter, update the preference profile, and select the next movie to suggest."

[0416] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0417] Step 1:

[0418] The server collects data on the user's past entertainment behavior. Specifically, it imports viewing history and rating information from various digital platforms into a database. Using this data as input, a preference data generation algorithm is applied to output the user's preference data. This process allows for an understanding of the genres and types of content the user prefers.

[0419] Step 2:

[0420] The server collects the latest entertainment information. It uses online databases and APIs to obtain diverse content information. Using the acquired data as input, a generative AI model selects appropriate entertainment based on the user's preferences and outputs a list of candidates. Here, it analyzes genre matching and popularity to extract the most suitable works.

[0421] Step 3:

[0422] While a user is experiencing entertainment content, the server collects the user's facial expressions and voice data in real time. This data, obtained through cameras and microphones, is processed by an emotion recognition algorithm to output the user's emotional state. This process identifies specific emotions such as joy, sadness, and excitement during viewing.

[0423] Step 4:

[0424] The server feeds back the emotional state obtained in step 3 to the user's preference data in real time. It analyzes the frequency and intensity of emotional changes and updates the preference profile. This updated data provides output that helps in making more accurate entertainment selections in the future.

[0425] Step 5:

[0426] After an entertainment experience, the device uses a generative AI model to generate a review of the experience. Taking emotional data and preference profiles as input, it outputs an evaluation statement in natural language text. This process includes automatically creating wording that includes particularly emotionally charged parts and memorable scenes.

[0427] Step 6:

[0428] Users can view reviews displayed on their devices and choose to share them on platforms such as social media. The device will have a share button, allowing for easy posting of reviews. Review sharing is a crucial output for widely disseminating user experiences.

[0429] (Application Example 2)

[0430] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0431] Conventional entertainment selection systems, relying solely on users' past behavior, struggle to provide personalized experiences based on instantaneous emotional shifts and current feelings. Furthermore, they lack automated review generation tailored to user emotions, resulting in insufficient improvement in user satisfaction and overall experience. Therefore, a method is needed to reflect users' real-time emotions and deliver more accurate and satisfying entertainment experiences.

[0432] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0433] This invention includes a server that recognizes a user's emotions in real time during their entertainment experience and reflects that data in a preference profile; a server that automatically generates reviews after the experience based on the recognized emotional data and promotes sharing; and a server that motivates users to participate in entertainment by providing rewards. This enables the provision of personalized content based on the user's emotions and the generation of emotionally charged reviews, thereby improving user satisfaction.

[0434] A "user" is an entity that consumes entertainment content and utilizes various functions of a system.

[0435] "Entertainment activities" refer to content consumption behaviors such as movies, music, and games, which users engage in for the purpose of enjoyment and relaxation.

[0436] A "preference profile" is a data structure that is generated based on a user's past behavior and emotional data, and indicates the user's preferences.

[0437] "Entertainment information" refers to a variety of data related to entertainment content, including movie titles and music artists.

[0438] "Emotion recognition" is a technology that analyzes a user's psychological state from input data such as facial expressions and voice, and identifies specific emotions.

[0439] A "review" is a document that compiles users' evaluations and opinions on entertainment content they have experienced.

[0440] "Rewards" are incentives given to motivate user behavior and may include points or perks.

[0441] To implement this invention, a system is needed that recognizes the user's emotions during their entertainment experience in real time and reflects that information in their preference profile. Specifically, it is implemented using the following components.

[0442] 1. Emotion Recognition Module

[0443] The server uses the user's smartphone camera and microphone to capture facial expressions and voice during entertainment activities. Image processing libraries (e.g., OpenCV) and voice analysis libraries (e.g., Librosa) are used to extract emotional characteristics from this data. Machine learning models (e.g., TensorFlow, PyTorch) are used to identify the user's emotions and perform real-time analysis.

[0444] 2. Preference Profile Update Module

[0445] The server updates the user's preference profile using the analyzed sentiment data. A database management system (e.g., SQLite) is used to store and manage information about the user's preferences and interests.

[0446] 3. Entertainment Proposal Module

[0447] The server selects the most suitable entertainment content for the user based on their updated preference profile. Using algorithms, it recommends personalized content that matches the user's current mood.

[0448] 4. Automated Review Generation Module

[0449] The device uses emotional data and leverages a natural language generation model (e.g., a generative AI model) to automatically generate reviews of entertainment content experienced by the user. These reviews include emotional elements, which the user can review and share on social media.

[0450] As a specific example,

[0451] While a user is watching a movie, their smartphone captures data of their smile and laughter, identifying in real time that their emotion is "joy." This information is immediately reflected in their preference profile, and the next time they watch a movie, they will be offered suggestions for movies they will enjoy more. After watching, an automated review generation module creates a review that includes emotional elements, such as "It was a very fun movie that made me laugh a lot!", and enables sharing on social media.

[0452] Example of a prompt:

[0453] "Generate emotionally resonant reviews based on the entertainment content users experienced. Highlight scenes where they smiled frequently and create natural-sounding sentences."

[0454] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0455] Step 1:

[0456] The server activates the user's smartphone camera and microphone to capture facial expressions and audio data during entertainment activities. This input data forms the basis for analyzing the user's emotions in real time.

[0457] Step 2:

[0458] The server uses an image processing library (OpenCV) and an audio analysis library (Librosa) to extract features from the captured images and audio, respectively. This process analyzes facial movements and voice tone, outputting emotional characteristics as numerical data.

[0459] Step 3:

[0460] The server inputs the extracted emotional characteristic data into a machine learning model (TensorFlow, PyTorch) to identify the user's specific emotions (e.g., "joy," "sadness," etc.). The model processes this characteristic data and outputs a label that identifies the user's emotion.

[0461] Step 4:

[0462] The server updates the user's preference profile using identified sentiment data. It reflects this sentiment data in a database management system (SQLite), updating the profile information in real time.

[0463] Step 5:

[0464] The server runs an entertainment suggestion algorithm based on the updated preference profile. It selects content that matches the user's preferences and current mood, and generates suggestions.

[0465] Step 6:

[0466] The device uses a generative AI model to automatically generate reviews that take into account the emotions identified during the experience. Emotion labels and prompt sentences are input to the model, which then outputs a review in a natural-sounding sentence format.

[0467] Step 7:

[0468] Users can view reviews generated on their devices and share them on social media if necessary. This allows them to share their experiences with others and use that information to help them choose their next form of entertainment.

[0469] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0470] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0471] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0472] [Third Embodiment]

[0473] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0474] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0475] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0476] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0477] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0478] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0479] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0480] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0481] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0482] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0483] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0484] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0485] To implement this invention, a system comprising several key modules is required. The following are specific embodiments thereof.

[0486] User profiling module

[0487] The server collects data on the user's past entertainment behavior and uses this to generate a user preference profile. This data includes the movies the user has watched, the music they have listened to, and the events they have attended. Through this data analysis, machine learning algorithms are used to identify the distribution of genres and artists that the user prefers, which helps in suggesting future content.

[0488] Entertainment information curation module

[0489] The server retrieves the latest entertainment information from external data sources. This information includes movie release dates, music album release information, concert dates, and more. The server then compares this information with the user's preference profile to select and list content that is highly relevant to the user.

[0490] Reservation / Purchase Support Module

[0491] The device displays selected entertainment information in a user interface and supports users in making reservations, purchases, or obtaining tickets for viewing or participation. It also integrates with external services to process payments as needed.

[0492] Review generation and sharing module

[0493] The server collects feedback after the user's entertainment experience and automatically generates reviews using natural language processing technology. These reviews are based on the user's opinions and ratings, and are shared on social media only after the user is asked to confirm them on their device and gives permission.

[0494] Gamification and rewards module

[0495] The server encourages user participation by awarding points and rewards based on users' entertainment activities. This allows users to feel a sense of accomplishment and motivates them to choose their next form of entertainment.

[0496] Reminder and Schedule Management Module

[0497] The device adds selected entertainment events to the user's schedule and sets reminder notifications. This ensures that users don't miss out on content they're interested in.

[0498] Specific example

[0499] If a user has previously watched many action movies, the server will collect the latest action movies from its data sources and present them as recommendations based on their individual preference profile. When the user selects and watches a movie, a review generation module automatically summarizes their impressions and shares them on social media, giving other users the opportunity to learn about the movie. Users also earn points for watching movies, which they can use to purchase tickets for future movies. This entire process enriches and streamlines the user's entertainment experience.

[0500] The following describes the processing flow.

[0501] Step 1:

[0502] The server retrieves the user's entertainment history from a database and analyzes the genres and frequency of content the user has watched in the past. Based on this, it creates a user preference profile.

[0503] Step 2:

[0504] The server collects data on the latest movies, music, and events from external entertainment information services. The collected data is filtered based on its content, genre, dates, and other factors.

[0505] Step 3:

[0506] The server uses the user's preference profile to select the most suitable content from the collected entertainment information. The selected content is then generated as a list.

[0507] Step 4:

[0508] The terminal displays an entertainment list received from the server on the user interface. Users can select movies, music, and events of interest from this list.

[0509] Step 5:

[0510] Users can view details of their selected entertainment through their device and indicate their intention to book, purchase, or obtain tickets. If necessary, they can proceed with payment.

[0511] Step 6:

[0512] Based on the user's selection, the server issues purchase confirmations and ticket details, and provides them to the user through the terminal.

[0513] Step 7:

[0514] After a user watches or participates in entertainment, the server collects feedback from the user. Based on the user's ratings and comments, an automated review is generated using natural language processing technology.

[0515] Step 8:

[0516] The device displays the generated review to the user and requests permission to post it to social media. If the user grants permission, the review is automatically posted to social media.

[0517] Step 9:

[0518] The server calculates points based on the user's activity log and adds them to the user's account. Furthermore, it suggests new quests and missions to encourage future entertainment activities.

[0519] Step 10:

[0520] The device checks the user's schedule and sets reminders for upcoming entertainment events. These reminders are sent to the user at the appropriate time.

[0521] (Example 1)

[0522] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0523] In today's entertainment industry, users struggle to select the most suitable content from a vast array of options. Furthermore, the time spent selecting content can lead to decreased user satisfaction. Additionally, the inability to effectively utilize feedback from experienced content hinders improvements in the accuracy of future recommendations. A system is needed that efficiently addresses these problems and enriches the user's entertainment experience.

[0524] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0525] In this invention, the server includes means for analyzing the user's past entertainment behavior and generating a preference profile using a machine learning algorithm; means for collecting various entertainment information published from external sources and selecting appropriate entertainment based on the preference profile; and means for analyzing user feedback and generated reviews and re-evaluating the entertainment content to improve the accuracy of future entertainment recommendations. This enables users to efficiently discover content that is best suited to them and to effectively utilize post-experience feedback to improve the accuracy of future recommendations.

[0526] A "user preference profile" is a collection of information that indicates an individual user's interests and preferences, created using machine learning algorithms based on the user's past entertainment behavior data.

[0527] "Entertainment information" refers to details of publicly available content such as movies, music, and events, as well as related data.

[0528] "Reservation, purchase, and ticket acquisition" refers to the actions taken by users to access or participate in entertainment content.

[0529] "Natural language processing technology" refers to a set of techniques and methodologies used by computers to understand and process human language.

[0530] "Points and rewards" refer to incentives and benefits provided in accordance with users' entertainment activities, with the aim of encouraging further user participation.

[0531] "External information sources" refer to organizations or platforms that provide various entertainment-related data and information accessible from outside the system.

[0532] This system is designed to enhance the user's entertainment experience. Specifically, it works by coordinating servers and terminals to analyze user preferences and deliver optimal content.

[0533] First, the server collects data on the user's past entertainment behavior and generates a preference profile using machine learning algorithms. This is based on viewing history, music playlists, and event attendance records stored in the database. From this information, the server identifies the user's preferred genres and artists and organizes them as a preference profile.

[0534] Next, the server collects publicly available entertainment information from external sources. This involves using external APIs and web scraping techniques to obtain the latest movie release dates, music release information, and event schedules. This information, combined with the server's generated preference profile, serves as the basis for selecting the most relevant content for the user.

[0535] The selected entertainment is presented to the user through the device's user interface. The device uses an intuitive interface to help users easily reserve and purchase content for viewing or participation. If necessary, it also integrates with external payment systems to support payment processing.

[0536] After an entertainment experience, the server collects user feedback and automatically generates a review using natural language processing technology. The generated review is then requested for user confirmation on the device, and if permission is granted, it is shared on social media.

[0537] Furthermore, the server provides points and rewards based on the user's entertainment activities. This motivates users to choose their next form of entertainment, encouraging greater participation.

[0538] For example, if a user has watched many action movies in the past, the server will collect the latest action movie information from its data sources and suggest movies based on their preference profile. When the user selects and watches a movie, a review generation module will automatically summarize their impressions and allow them to share them on social media. Furthermore, the user earns points for watching movies, which can be used towards future ticket purchases.

[0539] An example of a prompt message would be, "Based on the movies I've watched in the past, please list some action movies you recommend to me." In this way, the system leverages generative AI models to enrich the user's entertainment experience.

[0540] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0541] Step 1:

[0542] The server collects data on the user's past entertainment behavior. Its inputs include a database of movies the user has watched, music they have listened to, and events they have attended. The server transforms this data into an organized format for input into machine learning algorithms and outputs a list necessary for analyzing preferences. Specifically, the server queries the database and extracts the required data.

[0543] Step 2:

[0544] The server applies machine learning algorithms based on collected data to generate user preference profiles. It uses previously collected behavioral data as input, and clustering techniques are used to classify similar entertainment content based on this data. The output is the user preference profile, which is used for future content recommendations. Specifically, it runs the algorithm, builds the profile, and saves it to a database.

[0545] Step 3:

[0546] The server retrieves the latest entertainment information from external sources. Input includes configuration information for external APIs and web scraping tools. Using these methods, the server downloads movie release dates, music album release information, and event dates, creating a pure information list as output. Specifically, it executes scripts to automatically retrieve the latest information.

[0547] Step 4:

[0548] The server matches the acquired entertainment information with the user's preference profile. The input consists of the generated preference profile and a list of the latest information already acquired. Using a recommendation algorithm, the server selects the most relevant content for the user and outputs it as a curated list. Specifically, it utilizes matching technology to establish associations.

[0549] Step 5:

[0550] The terminal displays curated entertainment information received from the server in a user interface. The input is a recommendation list retrieved from the server, which the terminal visualizes in a user-friendly format. The output is an interface showing the user's choices of content to watch or participate in. Specifically, it updates GUI components to display the information.

[0551] Step 6:

[0552] The terminal assists with reservations and purchases based on user selections. Input is the entertainment content selected by the user, and the terminal communicates with the reservation and payment systems to complete the purchase process. Output is reservation confirmation and purchase completion messages. Specifically, it guides the user through form input and processes payments.

[0553] Step 7:

[0554] The server collects feedback after the user's entertainment experience and generates a review using natural language processing techniques. The input is user feedback, which the server analyzes and outputs a textual review. Specifically, it receives feedback, applies a language model to create a review, and presents it to the user.

[0555] Step 8:

[0556] The server calculates and provides points and rewards based on the user's entertainment activities. The input is a record of the user's completed activities; the server uses this to award points and outputs an updated point balance. Specifically, it updates account information and notifies the user of the new balance.

[0557] Step 9:

[0558] The device synchronizes selected entertainment information with the user's schedule and sets reminders. Input consists of confirmed event information and the user's calendar settings, and the device uses this information to output reminder notifications. Specifically, it synchronizes with the calendar app and generates a notification immediately before the event.

[0559] (Application Example 1)

[0560] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0561] In today's world, there is a need for methods that effectively propose entertainment content tailored to the diverse preferences of users, and that facilitate smooth viewing and experience. However, conventional systems have limitations, such as failing to fully grasp user preferences and making it difficult to easily access selected content. Furthermore, they are not adequately utilizing user feedback after their experience to improve future recommendations. It is necessary to solve these problems.

[0562] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0563] In this invention, the server includes means for analyzing the user's past viewing behavior to generate personal preference information, means for collecting the latest entertainment information from external sources and selecting appropriate content based on the preference information, and means for presenting content based on the user's preferences and enabling the user to directly access or play it. As a result, the user enjoys an individually customized content experience, and feedback is reflected in subsequent experiences, enabling highly personalized suggestions.

[0564] "User preference information" refers to information about content preferences that is individually generated based on a user's past viewing behavior and usage history.

[0565] "External information sources" refer to external data providers and open databases that provide information such as movie and music release dates and event schedules.

[0566] "Entertainment information" refers to information about various types of content such as movies, music, and events, and includes topics suggested according to the user's interests.

[0567] "Content selection" is the process of finding the content that best suits the user's preferences from among the collected entertainment information.

[0568] "Feedback" refers to opinions, impressions, and evaluations provided by users after they have experienced the content, and is information that can be used to improve future proposals.

[0569] "Schedule integration" means that the system synchronizes information with the user's schedule management and provides notifications to help them efficiently view content of interest.

[0570] To implement this invention, a system consisting of several main modules is required. The entire system is comprised of the cooperation between a server and a client (user terminal).

[0571] The server collects data such as the user's past viewing behavior and generates personalized preference information using machine learning algorithms. This process utilizes machine learning libraries such as Python and Scikit-learn, enabling the analysis of large amounts of data. Next, the server retrieves entertainment information from external sources via APIs (e.g., movie database APIs and music streaming APIs). This information is then compared with the preference information to select the most suitable content for the user.

[0572] The selected content is presented on the user's device, for example, on a modern smartphone app, allowing the user to access or play it directly. This process utilizes the Django REST Framework to build the user interface and provide seamless operation.

[0573] Furthermore, after a user's viewing experience, the server automatically generates feedback using a natural language generation technology (e.g., GPT-3) API and presents it as a prompt. After the user confirms it, they can easily share it via an SNS API.

[0574] Furthermore, the system encourages continued use by offering rewards that users can earn during their experience. This allows users to maintain their motivation and plan their next entertainment experience.

[0575] As a concrete example, if a movie-loving user is looking for a new movie, this system will recommend the most suitable action movie based on the genres of movies they have watched in the past. An example of a prompt message could be, "For a user who watches a lot of action movies, please recommend the best action movie to watch next using GPT-3." This would instruct the generative AI model in that format.

[0576] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0577] Step 1:

[0578] The server collects data on users' past viewing behavior. It takes the user's viewing history (e.g., a list of movies watched or music listened to) as input and uses a machine learning algorithm to generate preference information. The output is an individual preference profile for each user. Here, a Python program is used to cleanse the viewing data and create a model using data analysis libraries.

[0579] Step 2:

[0580] The server collects the latest entertainment information from external sources. It uses data from available movie database APIs and music streaming APIs as input. The server analyzes this data and selects the most suitable content based on the user's preference profile. The output is a list of entertainment information recommended to the user. The server utilizes RESTful APIs for data retrieval and filtering.

[0581] Step 3:

[0582] The terminal presents the user with a list of content received from the server via a user interface. The input is a recommendation list sent from the server. The output is a content selection screen displayed in a user-friendly format. Django is used here to make the user-selected content playable on a streaming platform.

[0583] Step 4:

[0584] After a user selects and views content, the server automatically generates feedback using natural language generation technology. The input is the user's feedback and comments after viewing the content. The output is a generated review text, which is created by a generative AI model (e.g., GPT-3).

[0585] Step 5:

[0586] The device presents the generated review to the user and encourages sharing on social media. The input is the review text sent from the server. The output is the confirmed review, which is posted through the user's social media account. The device uses social media APIs to provide simple sharing options.

[0587] Step 6:

[0588] The server rewards users for their experience. Inputs include user participation data and activity levels. Outputs are records of points and rewards added to the user's account. Users can use these for future entertainment participation. The server manages points based on user account information.

[0589] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0590] To implement this invention, a system is required that combines multiple modules, including an emotion engine that recognizes the user's emotions during their entertainment experience and integrates them as part of the system. The following is a specific embodiment of this system.

[0591] Emotion recognition module

[0592] The server analyzes the user's emotions using emotion recognition algorithms based on data collected during the user's entertainment experience. User facial expressions, voice, and text feedback are used as input data. By processing this information in real time, the server identifies various emotions the user felt during the experience, such as joy, excitement, and sadness.

[0593] Preference profile update module

[0594] The server feeds the emotion recognition results back into the user's preference profile, improving the profile's accuracy. This profile update allows the server to suggest content that the user will better enjoy.

[0595] Entertainment proposal module

[0596] The server selects the most suitable entertainment for the user based on the updated preference profile. By incorporating emotional information, it is possible to generate more personalized content lists than ever before.

[0597] Automated review generation module

[0598] The device generates reviews incorporating emotional data. Leveraging insights provided by the emotion engine, it adds emotional elements to user feedback, creating more engaging reviews. Users can then review these reviews and choose to share them on social media.

[0599] Specific example

[0600] When a user is watching a comedy film, the server observes the user's facial expressions and laughter during key scenes and measures the intensity of their enjoyment through an emotion engine. This data is reflected in the user's preference profile in real time, helping to suggest movies that will make the user laugh more in the future. When generating reviews, comments emphasizing the overall level of laughter in the film are automatically created and presented to the user on their device. This process ensures that users enjoy entertainment that is perfectly suited to them, and that their reviews effectively express their emotions.

[0601] The following describes the processing flow.

[0602] Step 1:

[0603] The user begins watching entertainment content. The user's device continuously monitors the user's facial expressions and voice while they are watching, using its camera and microphone, and collects data.

[0604] Step 2:

[0605] The server receives user facial expressions and speech data sent from the terminal and activates an emotion recognition algorithm. This algorithm determines the user's emotional state (e.g., joy, surprise, sadness) in real time from the data.

[0606] Step 3:

[0607] The server analyzes emotional data and stores the results in the user's preference profile. This information is accumulated as new emotional experiences and serves as material for further learning the user's content preferences.

[0608] Step 4:

[0609] The server selects entertainment content to suggest next based on the user's updated preference profile and emotional data. The selected content is prioritized for its tendency to evoke feelings of excitement and laughter in the user.

[0610] Step 5:

[0611] The device displays a simple interface that prompts the user for feedback after viewing has finished. Users can enter their thoughts on the movie and any additional comments.

[0612] Step 6:

[0613] The server synthesizes user comments with sentiment data collected in real time and automatically generates reviews using natural language processing technology. These reviews incorporate the emotions users felt during their experience, resulting in compelling content.

[0614] Step 7:

[0615] The device presents the generated review to the user and offers an option to post it to social media. If the user agrees, the review is automatically posted to the selected social media platform.

[0616] Step 8:

[0617] The server calculates points related to the entertainment the user has watched and adds them to the user's account. These points can then be used for future entertainment activities.

[0618] Step 9:

[0619] The device adds upcoming entertainment events to the user's schedule and sets them as reminders. These reminders ensure users don't miss out on new entertainment experiences.

[0620] (Example 2)

[0621] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0622] Current entertainment recommendation systems rely solely on users' past behavior and feedback, failing to fully utilize real-time emotions and reactions during experiences. This makes it difficult to provide optimal content to individual users, highlighting the need for higher levels of personalization. Furthermore, the generation and sharing of reviews that adequately reflect users' post-experience emotions are insufficient, preventing the maximization of the experience's value.

[0623] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0624] In this invention, the server includes means for analyzing the user's past information to generate preference data, means for collecting diverse information and selecting appropriate entertainment based on the preference data, and means for identifying emotions during the experience and updating the profile by providing feedback. This enables more accurate personalization, recommendations based on the user's experience, and content suggestions based on emotions.

[0625] A "user" refers to an individual or group that uses the system and is the subject that enjoys the entertainment experience.

[0626] "Information" is a general term for data related to entertainment or users, including audio, video, and text.

[0627] "Preference data" refers to data that represents a user's preferences, generated based on their past behavior and experiences.

[0628] "Entertainment" refers to a series of activities and content that provide entertainment to users.

[0629] "Experience" refers to the subjective feelings and emotions that users gain through entertainment.

[0630] "Emotions" refer to internal reactions such as joy, sadness, and excitement that arise during a user's entertainment experience.

[0631] A "profile" is a data structure created based on a user's preferences, behavior, and emotional responses, and is used to provide personalized suggestions.

[0632] "Recommendation" refers to the act of presenting appropriate entertainment based on a user's profile.

[0633] "Suggestion" refers to suggesting entertainment activities that users should engage in next.

[0634] This invention provides a system for highly personalizing the user's entertainment experience. The system consists of a server and terminals, analyzes the user's experience, and recommends the most suitable entertainment.

[0635] The server first analyzes the user's past entertainment behavior to generate preference data. This preference data concretizes the user's preferences based on their selection history and content they have watched. A database system and analysis software are used for this analysis, enabling efficient data processing.

[0636] Next, the server collects diverse information and selects appropriate entertainment based on the aforementioned preference data. In selecting entertainment, it comprehensively investigates various publicly available digital content and streaming service information to extract candidates that are likely to be of the user's greatest interest. This is done using a generative AI model to comprehensively judge the content and evaluation of each form of entertainment.

[0637] Furthermore, during the user's experience, the server analyzes the user's emotions in real time using voice and facial expression data. To this end, it utilizes voice recognition software and image analysis algorithms to identify emotions during the experience. For example, while watching a comedy movie, the server captures the user's laughter and changes in facial expressions to determine their feelings of joy, and feeds that information back into their preference data in real time.

[0638] The device automatically generates evaluation statements based on collected sentiment data. These evaluation statements utilize a generative AI model to produce sentiment-based natural language text. As a result, users can obtain compelling evaluations that reflect their experiences. Users can review these evaluation statements and share them on social media.

[0639] As a concrete example, while a user is watching a comedy film, the server analyzes the user's laughter and facial expressions during key scenes to measure the intensity of their feelings of enjoyment. This data is reflected in their preference data, enabling more appropriate comedy recommendations for future viewings. After viewing, the device generates an evaluation statement emphasizing the degree of humor in the film and presents it to the user as a review.

[0640] An example of a prompt message is: "For each scene in the comedy movies the user has watched, analyze the frequency and intensity of laughter, update the preference profile, and select the next movie to suggest."

[0641] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0642] Step 1:

[0643] The server collects data on the user's past entertainment behavior. Specifically, it imports viewing history and rating information from various digital platforms into a database. Using this data as input, a preference data generation algorithm is applied to output the user's preference data. This process allows for an understanding of the genres and types of content the user prefers.

[0644] Step 2:

[0645] The server collects the latest entertainment information. It uses online databases and APIs to obtain diverse content information. Using the acquired data as input, a generative AI model selects appropriate entertainment based on the user's preferences and outputs a list of candidates. Here, it analyzes genre matching and popularity to extract the most suitable works.

[0646] Step 3:

[0647] While a user is experiencing entertainment content, the server collects the user's facial expressions and voice data in real time. This data, obtained through cameras and microphones, is processed by an emotion recognition algorithm to output the user's emotional state. This process identifies specific emotions such as joy, sadness, and excitement during viewing.

[0648] Step 4:

[0649] The server feeds back the emotional state obtained in step 3 to the user's preference data in real time. It analyzes the frequency and intensity of emotional changes and updates the preference profile. This updated data provides output that helps in making more accurate entertainment selections in the future.

[0650] Step 5:

[0651] After an entertainment experience, the device uses a generative AI model to generate a review of the experience. Taking emotional data and preference profiles as input, it outputs an evaluation statement in natural language text. This process includes automatically creating wording that includes particularly emotionally charged parts and memorable scenes.

[0652] Step 6:

[0653] Users can view reviews displayed on their devices and choose to share them on platforms such as social media. The device will have a share button, allowing for easy posting of reviews. Review sharing is a crucial output for widely disseminating user experiences.

[0654] (Application Example 2)

[0655] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0656] Conventional entertainment selection systems, relying solely on users' past behavior, struggle to provide personalized experiences based on instantaneous emotional shifts and current feelings. Furthermore, they lack automated review generation tailored to user emotions, resulting in insufficient improvement in user satisfaction and overall experience. Therefore, a method is needed to reflect users' real-time emotions and deliver more accurate and satisfying entertainment experiences.

[0657] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0658] This invention includes a server that recognizes a user's emotions in real time during their entertainment experience and reflects that data in a preference profile; a server that automatically generates reviews after the experience based on the recognized emotional data and promotes sharing; and a server that motivates users to participate in entertainment by providing rewards. This enables the provision of personalized content based on the user's emotions and the generation of emotionally charged reviews, thereby improving user satisfaction.

[0659] A "user" is an entity that consumes entertainment content and utilizes various functions of a system.

[0660] "Entertainment activities" refer to content consumption behaviors such as movies, music, and games, which users engage in for the purpose of enjoyment and relaxation.

[0661] A "preference profile" is a data structure that is generated based on a user's past behavior and emotional data, and indicates the user's preferences.

[0662] "Entertainment information" refers to a variety of data related to entertainment content, including movie titles and music artists.

[0663] "Emotion recognition" is a technology that analyzes a user's psychological state from input data such as facial expressions and voice, and identifies specific emotions.

[0664] A "review" is a document that compiles users' evaluations and opinions on entertainment content they have experienced.

[0665] "Rewards" are incentives given to motivate user behavior and may include points or perks.

[0666] To implement this invention, a system is needed that recognizes the user's emotions during their entertainment experience in real time and reflects that information in their preference profile. Specifically, it is implemented using the following components.

[0667] 1. Emotion Recognition Module

[0668] The server uses the user's smartphone camera and microphone to capture facial expressions and voice during entertainment activities. Image processing libraries (e.g., OpenCV) and voice analysis libraries (e.g., Librosa) are used to extract emotional characteristics from this data. Machine learning models (e.g., TensorFlow, PyTorch) are used to identify the user's emotions and perform real-time analysis.

[0669] 2. Preference Profile Update Module

[0670] The server updates the user's preference profile using the analyzed sentiment data. A database management system (e.g., SQLite) is used to store and manage information about the user's preferences and interests.

[0671] 3. Entertainment Proposal Module

[0672] The server selects the most suitable entertainment content for the user based on their updated preference profile. Using algorithms, it recommends personalized content that matches the user's current mood.

[0673] 4. Automated Review Generation Module

[0674] The device uses emotional data and leverages a natural language generation model (e.g., a generative AI model) to automatically generate reviews of entertainment content experienced by the user. These reviews include emotional elements, which the user can review and share on social media.

[0675] As a specific example,

[0676] While a user is watching a movie, their smartphone captures data of their smile and laughter, identifying in real time that their emotion is "joy." This information is immediately reflected in their preference profile, and the next time they watch a movie, they will be offered suggestions for movies they will enjoy more. After watching, an automated review generation module creates a review that includes emotional elements, such as "It was a very fun movie that made me laugh a lot!", and enables sharing on social media.

[0677] Example of a prompt:

[0678] "Generate emotionally resonant reviews based on the entertainment content users experienced. Highlight scenes where they smiled frequently and create natural-sounding sentences."

[0679] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0680] Step 1:

[0681] The server activates the user's smartphone camera and microphone to capture facial expressions and audio data during entertainment activities. This input data forms the basis for analyzing the user's emotions in real time.

[0682] Step 2:

[0683] The server uses an image processing library (OpenCV) and an audio analysis library (Librosa) to extract features from the captured images and audio, respectively. This process analyzes facial movements and voice tone, outputting emotional characteristics as numerical data.

[0684] Step 3:

[0685] The server inputs the extracted emotional characteristic data into a machine learning model (TensorFlow, PyTorch) to identify the user's specific emotions (e.g., "joy," "sadness," etc.). The model processes this characteristic data and outputs a label that identifies the user's emotion.

[0686] Step 4:

[0687] The server updates the user's preference profile using identified sentiment data. It reflects this sentiment data in a database management system (SQLite), updating the profile information in real time.

[0688] Step 5:

[0689] The server runs an entertainment suggestion algorithm based on the updated preference profile. It selects content that matches the user's preferences and current mood, and generates suggestions.

[0690] Step 6:

[0691] The device uses a generative AI model to automatically generate reviews that take into account the emotions identified during the experience. Emotion labels and prompt sentences are input to the model, which then outputs a review in a natural-sounding sentence format.

[0692] Step 7:

[0693] Users can view reviews generated on their devices and share them on social media if necessary. This allows them to share their experiences with others and use that information to help them choose their next form of entertainment.

[0694] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0695] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0696] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0697] [Fourth Embodiment]

[0698] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0699] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0700] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0701] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0702] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0703] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0704] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0705] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0706] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0707] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0708] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0709] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0710] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0711] To implement this invention, a system comprising several key modules is required. The following are specific embodiments thereof.

[0712] User profiling module

[0713] The server collects data on the user's past entertainment behavior and uses this to generate a user preference profile. This data includes the movies the user has watched, the music they have listened to, and the events they have attended. Through this data analysis, machine learning algorithms are used to identify the distribution of genres and artists that the user prefers, which helps in suggesting future content.

[0714] Entertainment information curation module

[0715] The server retrieves the latest entertainment information from external data sources. This information includes movie release dates, music album release information, concert dates, and more. The server then compares this information with the user's preference profile to select and list content that is highly relevant to the user.

[0716] Reservation / Purchase Support Module

[0717] The device displays selected entertainment information in a user interface and supports users in making reservations, purchases, or obtaining tickets for viewing or participation. It also integrates with external services to process payments as needed.

[0718] Review generation and sharing module

[0719] The server collects feedback after the user's entertainment experience and automatically generates reviews using natural language processing technology. These reviews are based on the user's opinions and ratings, and are shared on social media only after the user is asked to confirm them on their device and gives permission.

[0720] Gamification and rewards module

[0721] The server encourages user participation by awarding points and rewards based on users' entertainment activities. This allows users to feel a sense of accomplishment and motivates them to choose their next form of entertainment.

[0722] Reminder and Schedule Management Module

[0723] The device adds selected entertainment events to the user's schedule and sets reminder notifications. This ensures that users don't miss out on content they're interested in.

[0724] Specific example

[0725] If a user has previously watched many action movies, the server will collect the latest action movies from its data sources and present them as recommendations based on their individual preference profile. When the user selects and watches a movie, a review generation module automatically summarizes their impressions and shares them on social media, giving other users the opportunity to learn about the movie. Users also earn points for watching movies, which they can use to purchase tickets for future movies. This entire process enriches and streamlines the user's entertainment experience.

[0726] The following describes the processing flow.

[0727] Step 1:

[0728] The server retrieves the user's entertainment history from a database and analyzes the genres and frequency of content the user has watched in the past. Based on this, it creates a user preference profile.

[0729] Step 2:

[0730] The server collects data on the latest movies, music, and events from external entertainment information services. The collected data is filtered based on its content, genre, dates, and other factors.

[0731] Step 3:

[0732] The server uses the user's preference profile to select the most suitable content from the collected entertainment information. The selected content is then generated as a list.

[0733] Step 4:

[0734] The terminal displays an entertainment list received from the server on the user interface. Users can select movies, music, and events of interest from this list.

[0735] Step 5:

[0736] Users can view details of their selected entertainment through their device and indicate their intention to book, purchase, or obtain tickets. If necessary, they can proceed with payment.

[0737] Step 6:

[0738] Based on the user's selection, the server issues purchase confirmations and ticket details, and provides them to the user through the terminal.

[0739] Step 7:

[0740] After a user watches or participates in entertainment, the server collects feedback from the user. Based on the user's ratings and comments, an automated review is generated using natural language processing technology.

[0741] Step 8:

[0742] The device displays the generated review to the user and requests permission to post it to social media. If the user grants permission, the review is automatically posted to social media.

[0743] Step 9:

[0744] The server calculates points based on the user's activity log and adds them to the user's account. Furthermore, it suggests new quests and missions to encourage future entertainment activities.

[0745] Step 10:

[0746] The device checks the user's schedule and sets reminders for upcoming entertainment events. These reminders are sent to the user at the appropriate time.

[0747] (Example 1)

[0748] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0749] In today's entertainment industry, users struggle to select the most suitable content from a vast array of options. Furthermore, the time spent selecting content can lead to decreased user satisfaction. Additionally, the inability to effectively utilize feedback from experienced content hinders improvements in the accuracy of future recommendations. A system is needed that efficiently addresses these problems and enriches the user's entertainment experience.

[0750] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0751] In this invention, the server includes means for analyzing the user's past entertainment behavior and generating a preference profile using a machine learning algorithm; means for collecting various entertainment information published from external sources and selecting appropriate entertainment based on the preference profile; and means for analyzing user feedback and generated reviews and re-evaluating the entertainment content to improve the accuracy of future entertainment recommendations. This enables users to efficiently discover content that is best suited to them and to effectively utilize post-experience feedback to improve the accuracy of future recommendations.

[0752] A "user preference profile" is a collection of information that indicates an individual user's interests and preferences, created using machine learning algorithms based on the user's past entertainment behavior data.

[0753] "Entertainment information" refers to details of publicly available content such as movies, music, and events, as well as related data.

[0754] "Reservation, purchase, and ticket acquisition" refers to the actions taken by users to access or participate in entertainment content.

[0755] "Natural language processing technology" refers to a set of techniques and methodologies used by computers to understand and process human language.

[0756] "Points and rewards" refer to incentives and benefits provided in accordance with users' entertainment activities, with the aim of encouraging further user participation.

[0757] "External information sources" refer to organizations or platforms that provide various entertainment-related data and information accessible from outside the system.

[0758] This system is designed to enhance the user's entertainment experience. Specifically, it works by coordinating servers and terminals to analyze user preferences and deliver optimal content.

[0759] First, the server collects data on the user's past entertainment behavior and generates a preference profile using machine learning algorithms. This is based on viewing history, music playlists, and event attendance records stored in the database. From this information, the server identifies the user's preferred genres and artists and organizes them as a preference profile.

[0760] Next, the server collects publicly available entertainment information from external sources. This involves using external APIs and web scraping techniques to obtain the latest movie release dates, music release information, and event schedules. This information, combined with the server's generated preference profile, serves as the basis for selecting the most relevant content for the user.

[0761] The selected entertainment is presented to the user through the device's user interface. The device uses an intuitive interface to help users easily reserve and purchase content for viewing or participation. If necessary, it also integrates with external payment systems to support payment processing.

[0762] After an entertainment experience, the server collects user feedback and automatically generates a review using natural language processing technology. The generated review is then requested for user confirmation on the device, and if permission is granted, it is shared on social media.

[0763] Furthermore, the server provides points and rewards based on the user's entertainment activities. This motivates users to choose their next form of entertainment, encouraging greater participation.

[0764] For example, if a user has watched many action movies in the past, the server will collect the latest action movie information from its data sources and suggest movies based on their preference profile. When the user selects and watches a movie, a review generation module will automatically summarize their impressions and allow them to share them on social media. Furthermore, the user earns points for watching movies, which can be used towards future ticket purchases.

[0765] An example of a prompt message would be, "Based on the movies I've watched in the past, please list some action movies you recommend to me." In this way, the system leverages generative AI models to enrich the user's entertainment experience.

[0766] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0767] Step 1:

[0768] The server collects data on the user's past entertainment behavior. Its inputs include a database of movies the user has watched, music they have listened to, and events they have attended. The server transforms this data into an organized format for input into machine learning algorithms and outputs a list necessary for analyzing preferences. Specifically, the server queries the database and extracts the required data.

[0769] Step 2:

[0770] The server applies machine learning algorithms based on collected data to generate user preference profiles. It uses previously collected behavioral data as input, and clustering techniques are used to classify similar entertainment content based on this data. The output is the user preference profile, which is used for future content recommendations. Specifically, it runs the algorithm, builds the profile, and saves it to a database.

[0771] Step 3:

[0772] The server retrieves the latest entertainment information from external sources. Input includes configuration information for external APIs and web scraping tools. Using these methods, the server downloads movie release dates, music album release information, and event dates, creating a pure information list as output. Specifically, it executes scripts to automatically retrieve the latest information.

[0773] Step 4:

[0774] The server matches the acquired entertainment information with the user's preference profile. The input consists of the generated preference profile and a list of the latest information already acquired. Using a recommendation algorithm, the server selects the most relevant content for the user and outputs it as a curated list. Specifically, it utilizes matching technology to establish associations.

[0775] Step 5:

[0776] The terminal displays curated entertainment information received from the server in a user interface. The input is a recommendation list retrieved from the server, which the terminal visualizes in a user-friendly format. The output is an interface showing the user's choices of content to watch or participate in. Specifically, it updates GUI components to display the information.

[0777] Step 6:

[0778] The terminal assists with reservations and purchases based on user selections. Input is the entertainment content selected by the user, and the terminal communicates with the reservation and payment systems to complete the purchase process. Output is reservation confirmation and purchase completion messages. Specifically, it guides the user through form input and processes payments.

[0779] Step 7:

[0780] The server collects feedback after the user's entertainment experience and generates a review using natural language processing techniques. The input is user feedback, which the server analyzes and outputs a textual review. Specifically, it receives feedback, applies a language model to create a review, and presents it to the user.

[0781] Step 8:

[0782] The server calculates and provides points and rewards based on the user's entertainment activities. The input is a record of the user's completed activities; the server uses this to award points and outputs an updated point balance. Specifically, it updates account information and notifies the user of the new balance.

[0783] Step 9:

[0784] The device synchronizes selected entertainment information with the user's schedule and sets reminders. Input consists of confirmed event information and the user's calendar settings, and the device uses this information to output reminder notifications. Specifically, it synchronizes with the calendar app and generates a notification immediately before the event.

[0785] (Application Example 1)

[0786] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0787] In today's world, there is a need for methods that effectively propose entertainment content tailored to the diverse preferences of users, and that facilitate smooth viewing and experience. However, conventional systems have limitations, such as failing to fully grasp user preferences and making it difficult to easily access selected content. Furthermore, they are not adequately utilizing user feedback after their experience to improve future recommendations. It is necessary to solve these problems.

[0788] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0789] In this invention, the server includes means for analyzing the user's past viewing behavior to generate personal preference information, means for collecting the latest entertainment information from external sources and selecting appropriate content based on the preference information, and means for presenting content based on the user's preferences and enabling the user to directly access or play it. As a result, the user enjoys an individually customized content experience, and feedback is reflected in subsequent experiences, enabling highly personalized suggestions.

[0790] "User preference information" refers to information about content preferences that is individually generated based on a user's past viewing behavior and usage history.

[0791] "External information sources" refer to external data providers and open databases that provide information such as movie and music release dates and event schedules.

[0792] "Entertainment information" refers to information about various types of content such as movies, music, and events, and includes topics suggested according to the user's interests.

[0793] "Content selection" is the process of finding the content that best suits the user's preferences from among the collected entertainment information.

[0794] "Feedback" refers to opinions, impressions, and evaluations provided by users after they have experienced the content, and is information that can be used to improve future proposals.

[0795] "Schedule integration" means that the system synchronizes information with the user's schedule management and provides notifications to help them efficiently view content of interest.

[0796] To implement this invention, a system consisting of several main modules is required. The entire system is comprised of the cooperation between a server and a client (user terminal).

[0797] The server collects data such as the user's past viewing behavior and generates personalized preference information using machine learning algorithms. This process utilizes machine learning libraries such as Python and Scikit-learn, enabling the analysis of large amounts of data. Next, the server retrieves entertainment information from external sources via APIs (e.g., movie database APIs and music streaming APIs). This information is then compared with the preference information to select the most suitable content for the user.

[0798] The selected content is presented on the user's device, for example, on a modern smartphone app, allowing the user to access or play it directly. This process utilizes the Django REST Framework to build the user interface and provide seamless operation.

[0799] Furthermore, after a user's viewing experience, the server automatically generates feedback using a natural language generation technology (e.g., GPT-3) API and presents it as a prompt. After the user confirms it, they can easily share it via an SNS API.

[0800] Furthermore, the system encourages continued use by offering rewards that users can earn during their experience. This allows users to maintain their motivation and plan their next entertainment experience.

[0801] As a concrete example, if a movie-loving user is looking for a new movie, this system will recommend the most suitable action movie based on the genres of movies they have watched in the past. An example of a prompt message could be, "For a user who watches a lot of action movies, please recommend the best action movie to watch next using GPT-3." This would instruct the generative AI model in that format.

[0802] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0803] Step 1:

[0804] The server collects data on users' past viewing behavior. It takes the user's viewing history (e.g., a list of movies watched or music listened to) as input and uses a machine learning algorithm to generate preference information. The output is an individual preference profile for each user. Here, a Python program is used to cleanse the viewing data and create a model using data analysis libraries.

[0805] Step 2:

[0806] The server collects the latest entertainment information from external sources. It uses data from available movie database APIs and music streaming APIs as input. The server analyzes this data and selects the most suitable content based on the user's preference profile. The output is a list of entertainment information recommended to the user. The server utilizes RESTful APIs for data retrieval and filtering.

[0807] Step 3:

[0808] The terminal presents the user with a list of content received from the server via a user interface. The input is a recommendation list sent from the server. The output is a content selection screen displayed in a user-friendly format. Django is used here to make the user-selected content playable on a streaming platform.

[0809] Step 4:

[0810] After a user selects and views content, the server automatically generates feedback using natural language generation technology. The input is the user's feedback and comments after viewing the content. The output is a generated review text, which is created by a generative AI model (e.g., GPT-3).

[0811] Step 5:

[0812] The device presents the generated review to the user and encourages sharing on social media. The input is the review text sent from the server. The output is the confirmed review, which is posted through the user's social media account. The device uses social media APIs to provide simple sharing options.

[0813] Step 6:

[0814] The server rewards users for their experience. Inputs include user participation data and activity levels. Outputs are records of points and rewards added to the user's account. Users can use these for future entertainment participation. The server manages points based on user account information.

[0815] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0816] To implement this invention, a system is required that combines multiple modules, including an emotion engine that recognizes the user's emotions during their entertainment experience and integrates them as part of the system. The following is a specific embodiment of this system.

[0817] Emotion recognition module

[0818] The server analyzes the user's emotions using emotion recognition algorithms based on data collected during the user's entertainment experience. User facial expressions, voice, and text feedback are used as input data. By processing this information in real time, the server identifies various emotions the user felt during the experience, such as joy, excitement, and sadness.

[0819] Preference profile update module

[0820] The server feeds the emotion recognition results back into the user's preference profile, improving the profile's accuracy. This profile update allows the server to suggest content that the user will better enjoy.

[0821] Entertainment proposal module

[0822] The server selects the most suitable entertainment for the user based on the updated preference profile. By incorporating emotional information, it is possible to generate more personalized content lists than ever before.

[0823] Automated review generation module

[0824] The device generates reviews incorporating emotional data. Leveraging insights provided by the emotion engine, it adds emotional elements to user feedback, creating more engaging reviews. Users can then review these reviews and choose to share them on social media.

[0825] Specific example

[0826] When a user is watching a comedy film, the server observes the user's facial expressions and laughter during key scenes and measures the intensity of their enjoyment through an emotion engine. This data is reflected in the user's preference profile in real time, helping to suggest movies that will make the user laugh more in the future. When generating reviews, comments emphasizing the overall level of laughter in the film are automatically created and presented to the user on their device. This process ensures that users enjoy entertainment that is perfectly suited to them, and that their reviews effectively express their emotions.

[0827] The following describes the processing flow.

[0828] Step 1:

[0829] The user begins watching entertainment content. The user's device continuously monitors the user's facial expressions and voice while they are watching, using its camera and microphone, and collects data.

[0830] Step 2:

[0831] The server receives user facial expressions and speech data sent from the terminal and activates an emotion recognition algorithm. This algorithm determines the user's emotional state (e.g., joy, surprise, sadness) in real time from the data.

[0832] Step 3:

[0833] The server analyzes emotional data and stores the results in the user's preference profile. This information is accumulated as new emotional experiences and serves as material for further learning the user's content preferences.

[0834] Step 4:

[0835] The server selects entertainment content to suggest next based on the user's updated preference profile and emotional data. The selected content is prioritized for its tendency to evoke feelings of excitement and laughter in the user.

[0836] Step 5:

[0837] The device displays a simple interface that prompts the user for feedback after viewing has finished. Users can enter their thoughts on the movie and any additional comments.

[0838] Step 6:

[0839] The server synthesizes user comments with sentiment data collected in real time and automatically generates reviews using natural language processing technology. These reviews incorporate the emotions users felt during their experience, resulting in compelling content.

[0840] Step 7:

[0841] The device presents the generated review to the user and offers an option to post it to social media. If the user agrees, the review is automatically posted to the selected social media platform.

[0842] Step 8:

[0843] The server calculates points related to the entertainment the user has watched and adds them to the user's account. These points can then be used for future entertainment activities.

[0844] Step 9:

[0845] The device adds upcoming entertainment events to the user's schedule and sets them as reminders. These reminders ensure users don't miss out on new entertainment experiences.

[0846] (Example 2)

[0847] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0848] Current entertainment recommendation systems rely solely on users' past behavior and feedback, failing to fully utilize real-time emotions and reactions during experiences. This makes it difficult to provide optimal content to individual users, highlighting the need for higher levels of personalization. Furthermore, the generation and sharing of reviews that adequately reflect users' post-experience emotions are insufficient, preventing the maximization of the experience's value.

[0849] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0850] In this invention, the server includes means for analyzing the user's past information to generate preference data, means for collecting diverse information and selecting appropriate entertainment based on the preference data, and means for identifying emotions during the experience and updating the profile by providing feedback. This enables more accurate personalization, recommendations based on the user's experience, and content suggestions based on emotions.

[0851] A "user" refers to an individual or group that uses the system and is the subject that enjoys the entertainment experience.

[0852] "Information" is a general term for data related to entertainment or users, including audio, video, and text.

[0853] "Preference data" refers to data that represents a user's preferences, generated based on their past behavior and experiences.

[0854] "Entertainment" refers to a series of activities and content that provide entertainment to users.

[0855] "Experience" refers to the subjective feelings and emotions that users derive from entertainment.

[0856] "Emotions" refer to internal reactions such as joy, sadness, and excitement that arise during a user's entertainment experience.

[0857] A "profile" is a data structure created based on a user's preferences, behavior, and emotional responses, and is used to provide personalized suggestions.

[0858] "Recommendation" refers to the act of presenting appropriate entertainment based on a user's profile.

[0859] "Suggestion" refers to suggesting entertainment activities that users should engage in next.

[0860] This invention provides a system for highly personalizing the user's entertainment experience. The system consists of a server and terminals, analyzes the user's experience, and recommends the most suitable entertainment.

[0861] The server first analyzes the user's past entertainment behavior to generate preference data. This preference data concretizes the user's preferences based on their selection history and content they have watched. A database system and analysis software are used for this analysis, enabling efficient data processing.

[0862] Next, the server collects diverse information and selects appropriate entertainment based on the aforementioned preference data. In selecting entertainment, it comprehensively investigates various publicly available digital content and streaming service information to extract candidates that are likely to be of the user's greatest interest. This is done using a generative AI model to comprehensively judge the content and evaluation of each form of entertainment.

[0863] Furthermore, during the user's experience, the server analyzes the user's emotions in real time using voice and facial expression data. To this end, it utilizes voice recognition software and image analysis algorithms to identify emotions during the experience. For example, while watching a comedy movie, the server captures the user's laughter and changes in facial expressions to determine their feelings of joy, and feeds that information back into their preference data in real time.

[0864] The device automatically generates evaluation statements based on collected sentiment data. These evaluation statements utilize a generative AI model to produce sentiment-based natural language text. As a result, users can obtain compelling evaluations that reflect their experiences. Users can review these evaluation statements and share them on social media.

[0865] As a concrete example, while a user is watching a comedy film, the server analyzes the user's laughter and facial expressions during key scenes to measure the intensity of their feelings of enjoyment. This data is reflected in their preference data, enabling more appropriate comedy recommendations for future viewings. After viewing, the device generates an evaluation statement emphasizing the degree of humor in the film and presents it to the user as a review.

[0866] An example of a prompt message is: "For each scene in the comedy movies the user has watched, analyze the frequency and intensity of laughter, update the preference profile, and select the next movie to suggest."

[0867] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0868] Step 1:

[0869] The server collects data on the user's past entertainment behavior. Specifically, it imports viewing history and rating information from various digital platforms into a database. Using this data as input, a preference data generation algorithm is applied to output the user's preference data. This process allows for an understanding of the genres and types of content the user prefers.

[0870] Step 2:

[0871] The server collects the latest entertainment information. It uses online databases and APIs to obtain diverse content information. Using the acquired data as input, a generative AI model selects appropriate entertainment based on the user's preferences and outputs a list of candidates. Here, it analyzes genre matching and popularity to extract the most suitable works.

[0872] Step 3:

[0873] While a user is experiencing entertainment content, the server collects the user's facial expressions and voice data in real time. This data, obtained through cameras and microphones, is processed by an emotion recognition algorithm to output the user's emotional state. This process identifies specific emotions such as joy, sadness, and excitement during viewing.

[0874] Step 4:

[0875] The server feeds back the emotional state obtained in step 3 to the user's preference data in real time. It analyzes the frequency and intensity of emotional changes and updates the preference profile. This updated data provides output that helps in making more accurate entertainment selections in the future.

[0876] Step 5:

[0877] After an entertainment experience, the device uses a generative AI model to generate a review of the experience. Taking emotional data and preference profiles as input, it outputs an evaluation statement in natural language text. This process includes automatically creating wording that includes particularly emotionally charged parts and memorable scenes.

[0878] Step 6:

[0879] Users can view reviews displayed on their devices and choose to share them on platforms such as social media. The device will have a share button, allowing for easy posting of reviews. Review sharing is a crucial output for widely disseminating user experiences.

[0880] (Application Example 2)

[0881] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0882] Conventional entertainment selection systems, relying solely on users' past behavior, struggle to provide personalized experiences based on instantaneous emotional shifts and current feelings. Furthermore, they lack automated review generation tailored to user emotions, resulting in insufficient improvement in user satisfaction and overall experience. Therefore, a method is needed to reflect users' real-time emotions and deliver more accurate and satisfying entertainment experiences.

[0883] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0884] This invention includes a server that recognizes a user's emotions in real time during their entertainment experience and reflects that data in a preference profile; a server that automatically generates reviews after the experience based on the recognized emotional data and promotes sharing; and a server that motivates users to participate in entertainment by providing rewards. This enables the provision of personalized content based on the user's emotions and the generation of emotionally charged reviews, thereby improving user satisfaction.

[0885] A "user" is an entity that consumes entertainment content and utilizes various functions of a system.

[0886] "Entertainment activities" refer to content consumption behaviors such as movies, music, and games, which users engage in for the purpose of enjoyment and relaxation.

[0887] A "preference profile" is a data structure that is generated based on a user's past behavior and emotional data, and indicates the user's preferences.

[0888] "Entertainment information" refers to a variety of data related to entertainment content, including movie titles and music artists.

[0889] "Emotion recognition" is a technology that analyzes a user's psychological state from input data such as facial expressions and voice, and identifies specific emotions.

[0890] A "review" is a document that compiles users' evaluations and opinions on entertainment content they have experienced.

[0891] "Rewards" are incentives given to motivate user behavior and may include points or perks.

[0892] To implement this invention, a system is needed that recognizes the user's emotions during their entertainment experience in real time and reflects that information in their preference profile. Specifically, it is implemented using the following components.

[0893] 1. Emotion Recognition Module

[0894] The server uses the user's smartphone camera and microphone to capture facial expressions and voice during entertainment activities. Image processing libraries (e.g., OpenCV) and voice analysis libraries (e.g., Librosa) are used to extract emotional characteristics from this data. Machine learning models (e.g., TensorFlow, PyTorch) are used to identify the user's emotions and perform real-time analysis.

[0895] 2. Preference Profile Update Module

[0896] The server updates the user's preference profile using the analyzed sentiment data. A database management system (e.g., SQLite) is used to store and manage information about the user's preferences and interests.

[0897] 3. Entertainment Proposal Module

[0898] The server selects the most suitable entertainment content for the user based on their updated preference profile. Using algorithms, it recommends personalized content that matches the user's current mood.

[0899] 4. Automated Review Generation Module

[0900] The device uses emotional data and leverages a natural language generation model (e.g., a generative AI model) to automatically generate reviews of entertainment content experienced by the user. These reviews include emotional elements, which the user can review and share on social media.

[0901] As a specific example,

[0902] While a user is watching a movie, their smartphone captures data of their smile and laughter, identifying in real time that their emotion is "joy." This information is immediately reflected in their preference profile, and the next time they watch a movie, they will be offered suggestions for movies they will enjoy more. After watching, an automated review generation module creates a review that includes emotional elements, such as "It was a very fun movie that made me laugh a lot!", and enables sharing on social media.

[0903] Example of a prompt:

[0904] "Generate emotionally resonant reviews based on the entertainment content users experienced. Highlight scenes where they smiled frequently and create natural-sounding sentences."

[0905] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0906] Step 1:

[0907] The server activates the user's smartphone camera and microphone to capture facial expressions and audio data during entertainment activities. This input data forms the basis for analyzing the user's emotions in real time.

[0908] Step 2:

[0909] The server uses an image processing library (OpenCV) and an audio analysis library (Librosa) to extract features from the captured images and audio, respectively. This process analyzes facial movements and voice tone, outputting emotional characteristics as numerical data.

[0910] Step 3:

[0911] The server inputs the extracted emotional characteristic data into a machine learning model (TensorFlow, PyTorch) to identify the user's specific emotions (e.g., "joy," "sadness," etc.). The model processes this characteristic data and outputs a label that identifies the user's emotion.

[0912] Step 4:

[0913] The server updates the user's preference profile using identified sentiment data. It reflects this sentiment data in a database management system (SQLite), updating the profile information in real time.

[0914] Step 5:

[0915] The server runs an entertainment suggestion algorithm based on the updated preference profile. It selects content that matches the user's preferences and current mood, and generates suggestions.

[0916] Step 6:

[0917] The device uses a generative AI model to automatically generate reviews that take into account the emotions identified during the experience. Emotion labels and prompt sentences are input to the model, which then outputs a review in a natural-sounding sentence format.

[0918] Step 7:

[0919] Users can view reviews generated on their devices and share them on social media if necessary. This allows them to share their experiences with others and use that information to help them choose their next form of entertainment.

[0920] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0921] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0922] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0923] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0924] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0925] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0926] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0927] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0928] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0929] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0930] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0931] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0932] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0933] 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.

[0934] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0935] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0936] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0937] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0938] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0939] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0940] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0941] The following is further disclosed regarding the embodiments described above.

[0942] (Claim 1)

[0943] A means for analyzing a user's past entertainment behavior to generate a preference profile,

[0944] A means for collecting various publicly available entertainment information and selecting appropriate entertainment based on the aforementioned preference profile,

[0945] A means of automatically booking, purchasing, or obtaining tickets for a selection of entertainment,

[0946] A means of automatically generating and promoting the sharing of reviews during or after a user's entertainment experience,

[0947] A means of motivating users to participate in entertainment by offering points or rewards,

[0948] A system that includes this.

[0949] (Claim 2)

[0950] The system according to claim 1, which synchronizes selected entertainment information with the user's schedule, sets reminders, and suggests the user the next entertainment activity.

[0951] (Claim 3)

[0952] The system according to claim 1, which analyzes user feedback and re-evaluates entertainment content in order to improve the accuracy of suggesting future entertainment.

[0953] "Example 1"

[0954] (Claim 1)

[0955] A means for analyzing a user's past entertainment behavior and generating a preference profile using a machine learning algorithm,

[0956] A means for collecting various entertainment information released from external sources and selecting appropriate entertainment based on the aforementioned preference profile,

[0957] A means of displaying a portion of selected entertainment on a user interface via a terminal, and assisting the user in automatically making reservations, purchases, or obtaining tickets,

[0958] A means of collecting feedback after a user's entertainment experience, generating reviews using natural language processing technology, and then sharing and promoting those reviews after seeking confirmation from the user again.

[0959] A means of providing users with points or rewards in response to their entertainment activities, thereby motivating them to participate in future entertainment activities.

[0960] A system that includes this.

[0961] (Claim 2)

[0962] The system according to claim 1, which synchronizes selected entertainment information with the user's schedule, sets reminders, and suggests the user the next entertainment activity.

[0963] (Claim 3)

[0964] The system according to claim 1, which analyzes user feedback and generated reviews and re-evaluates entertainment content to improve the accuracy of future entertainment recommendations.

[0965] "Application Example 1"

[0966] (Claim 1)

[0967] A means of generating personal preference information by analyzing a user's past viewing behavior,

[0968] A means for collecting the latest entertainment information from external sources and selecting appropriate content based on the aforementioned preference information,

[0969] A means of automatically obtaining reservations, purchases, or access rights related to selected content,

[0970] A means to automatically generate feedback after a user's experience and promote information sharing,

[0971] A means of encouraging participation in the experience by offering rewards that users can earn,

[0972] A means of presenting content based on user preferences and enabling users to access or play it directly,

[0973] A system that includes this.

[0974] (Claim 2)

[0975] The system according to claim 1, which links selected content information with the user's schedule and sets up notifications.

[0976] (Claim 3)

[0977] The system according to claim 1, which analyzes user feedback and re-evaluates the information to improve the accuracy of future content suggestions.

[0978] "Example 2 of combining an emotion engine"

[0979] (Claim 1)

[0980] A means of generating preference data by analyzing the user's past information,

[0981] A means for collecting diverse information and selecting appropriate entertainment based on the aforementioned preference data,

[0982] A means of automatically reserving, purchasing, or acquiring rights to a selection of entertainment items,

[0983] A means of automatically generating and sharing evaluation statements during or after a user's experience,

[0984] A means of motivating participation by offering rewards to users,

[0985] A means of updating the profile by identifying and providing feedback on emotions during an experience,

[0986] Based on the updated profile, the means of selecting and providing information,

[0987] A system that includes this.

[0988] (Claim 2)

[0989] The system according to claim 1, which synchronizes selected information with the user's schedule to set up notifications and suggests the next activity.

[0990] (Claim 3)

[0991] The system according to claim 1, which analyzes user responses and re-evaluates the content to improve the accuracy of future suggestions.

[0992] "Application example 2 when combining with an emotional engine"

[0993] (Claim 1)

[0994] A means for analyzing a user's past entertainment activities to generate a preference profile,

[0995] A means for collecting diverse publicly available entertainment information and selecting appropriate entertainment based on the aforementioned preference profile,

[0996] A means of automatically booking, purchasing, or obtaining tickets for a selection of entertainment options,

[0997] A means of recognizing a user's emotions in real time during their entertainment experience and reflecting that data in their preference profile,

[0998] A means to automatically generate reviews after an experience based on recognized emotional data and to promote sharing,

[0999] A means of motivating users to participate in entertainment by providing them with rewards,

[1000] A system that includes this.

[1001] (Claim 2)

[1002] The system according to claim 1, which synchronizes selected entertainment information with the user's schedule to set reminders and suggests the user the next entertainment activity.

[1003] (Claim 3)

[1004] The system according to claim 1, which analyzes user feedback and re-evaluates entertainment content in order to improve the accuracy of suggesting future entertainment. [Explanation of symbols]

[1005] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing a user's past entertainment behavior to generate a preference profile, A means for collecting various publicly available entertainment information and selecting appropriate entertainment based on the aforementioned preference profile, A means of automatically booking, purchasing, or obtaining tickets for a selection of entertainment, A means of automatically generating and promoting the sharing of reviews during or after a user's entertainment experience, A means of motivating users to participate in entertainment by offering points or rewards, A system that includes this.

2. The system according to claim 1, which synchronizes selected entertainment information with the user's schedule, sets reminders, and suggests the user the next entertainment activity.

3. The system according to claim 1, which analyzes user feedback and re-evaluates entertainment content in order to improve the accuracy of suggesting future entertainment.

Images